467 results
Search Results
2. Diagnosis system for cancer disease using a single setting approach.
- Author
-
Bhuyan, Hemanta Kumar, Vijayaraj, A., and Ravi, Vinayakumar
- Subjects
DEEP learning ,CONVOLUTIONAL neural networks ,CANCER diagnosis ,ARTIFICIAL neural networks ,DATABASES ,IMAGE processing - Abstract
This paper addresses the diagnosis system of cancer disease using a single setting framework. Most of the radiologists and image specialists are identifying the disease in naked eye. When many conventional systems are used to assess or see a patient's disorder condition, it rarely detects the disease all at once in certain situations. Patients are facing difficulties, when the condition of disease is increasing. Thus, this paper focusses the condition of patient seeing the disease image and developed a single setting framework using a convolutional neural network (CNN) architecture with the help of deep learning approaches. The framework contains several deep learning strategies which are used to determine the patient's relevant illness through affected image, such as mass detection using You-Only-Look-Once (YOLO) approach and the crucial aspect of segmentation by full resolution convolutional networks (FrCN). In last the CNN model is considered for classification. This paper is considered to implement our model using breast cancer disease. The different classifiers and cross-validation tests are taken for evaluating validation matrix items. Comparisons of the existing model with the proposed model are made for improving the diagnosis system. For example, the method Inception V3 for accuracy and AUC are 86.77 and 85.89 on MIAS database whereas proposed model got 99.54 and 98.85 on same evaluation items. Our findings show that the proposed diagnostic model outperforms on conventional detection, segmentation, and classification methods. Thus, our diagnosis process worked much better using deep learning and suggested approaches which will help and facilitate the diagnosis of each contaminated region. In each stage of image processing of the infected region, the suggested diagnostics method could support radiologists. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
3. Emerging applications of Deep Learning and Spiking ANN.
- Author
-
Iliadis, Lazaros S. and Jayne, Chrisina
- Subjects
APPLIED sciences ,CONVOLUTIONAL neural networks ,DEEP learning ,PATIENT-professional relations ,ARTIFICIAL neural networks ,AIR conditioning ,BLOCKCHAINS - Published
- 2020
- Full Text
- View/download PDF
4. A review on evaluating mental stress by deep learning using EEG signals.
- Author
-
Badr, Yara, Tariq, Usman, Al-Shargie, Fares, Babiloni, Fabio, Al Mughairbi, Fadwa, and Al-Nashash, Hasan
- Subjects
- *
DEEP learning , *ARTIFICIAL neural networks , *MACHINE learning , *CONVOLUTIONAL neural networks , *ELECTROENCEPHALOGRAPHY , *REPRESENTATIONS of graphs , *JOB stress - Abstract
Mental stress is a common problem that affects individuals all over the world. Stress reduces human functionality during routine work and may lead to severe health defects. Early detection of stress is important for preventing diseases and other negative health-related consequences of stress. Several neuroimaging techniques have been utilized to assess mental stress, however, due to its ease of use, robustness, and non-invasiveness, electroencephalography (EEG) is commonly used. This paper aims to fill a knowledge gap by reviewing the different EEG-related deep learning algorithms with a focus on Convolutional Neural Networks (CNNs) and Long Short-Term Memory networks (LSTMs) for the evaluation of mental stress. The review focuses on data representation, individual deep neural network model architectures, hybrid models, and results amongst others. The contributions of the paper address important issues such as data representation and model architectures. Out of all reviewed papers, 67% used CNN, 9% LSTM, and 24% hybrid models. Based on the reviewed literature, we found that dataset size and different representations contributed to the performance of the proposed networks. Raw EEG data produced classification accuracy around 62% while using spectral and topographical representation produced up to 88%. Nevertheless, the roles of generalizability across different deep learning models and individual differences remain key areas of inquiry. The review encourages the exploration of innovative avenues, such as EEG data image representations concurrently with graph convolutional neural networks (GCN), to mitigate the impact of inter-subject variability. This novel approach not only allows us to harmonize structural nuances within the data but also facilitates the integration of temporal dynamics, thereby enabling a more comprehensive assessment of mental stress levels. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
5. Design of area-speed efficient Anurupyena Vedic multiplier for deep learning applications.
- Author
-
Kalaiselvi, C. M. and Sabeenian, R. S.
- Subjects
DEEP learning ,ARTIFICIAL neural networks ,MACHINE learning ,FIELD programmable gate arrays ,CONVOLUTIONAL neural networks ,ELECTRONIC systems - Abstract
Hardware such as multipliers and dividers is necessary for all electronic systems. This paper explores Vedic mathematics techniques for high-speed and low-area multiplication. In the study of multiplication algorithms, various bits-width ranges of the Anurupyena sutra are used. Parallelism is employed to address challenging problems in recent studies. Various designs have been developed for the Field Programmable Gate Array (FPGA) implementation employing Very Large-Scale integration (VLSI) design approaches and parallel computing technology. Signal processing, machine learning, and reconfigurable computing research should be closely monitored as artificial intelligence develops. Multipliers and adders are key components of deep learning algorithms. The multiplier is an energy-intensive component of signal processing in Arithmetic Logic Unit (ALU), Convolutional Neural Networks (CNN), and Deep Neural Networks (DNN). For the DNN, this method introduces the Booth multiplier blocks and the carry-save multiplier in the Anurupyena architecture. Traditional multiplication methods like the array multiplier, Wallace multiplier, and Booth multiplier are contrasted with the Vedic mathematics algorithms. On a specific hardware platform, Vedic algorithms perform faster, use less power, and take up less space. Implementations were carried out using Verilog HDL and Xilinx Vivado 2019.1 on Kintex-7. The area and propagation delay were reduced compared to other multiplier architectures. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
6. Error revision during morning period for deep learning and multi-variable historical data-based day-ahead solar irradiance forecast: towards a more accurate daytime forecast.
- Author
-
Chen, Yunxiao, Bai, Mingliang, Zhang, Yilan, Liu, Jinfu, and Yu, Daren
- Subjects
DEEP learning ,ARTIFICIAL neural networks ,CONVOLUTIONAL neural networks ,SOLAR technology ,RECURRENT neural networks ,STANDARD deviations ,FORECASTING - Abstract
With the increasing proportion of solar energy in the energy system, accurate solar irradiance forecast is of great significance for low-cost energy scheduling. This paper proposes a new forecasting idea for day-ahead solar irradiance forecast on the day-ahead scale: Firstly, based on formula derivation and big data correlation analysis, this paper finds out multiple parameters related to GHI, and jointly uses these parameters to forecast GHI. Error revision during morning period (ERDMP) is innovatively proposed on this basis, towards a more accurate daytime forecast. In order to prove the reliability and universality of the method, relevant data from five different-climatic regions are respectively used in the experiment. The multi-variable historical data-based day-ahead solar irradiance forecast uses deep neural networks, including Recurrent Neural Network (RNN), Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) network. ERDMP uses a linear AutoRegressive (AR) model to predict the daytime error coefficients based on the morning error coefficients. According to the results, through the proposed ERDMP, Mean Absolute Error (MAE) decreases by about 25% to 30%, Root Mean Squared Error (RMSE) decreases by about 20%, and R
2 increases by about 5% to 10% when compared with the initial error of multi-parameter prediction models and other advanced models. [ABSTRACT FROM AUTHOR]- Published
- 2023
- Full Text
- View/download PDF
7. Special Issue on Neural Networks for Early Cancer Detection.
- Author
-
Wen, Shiping and Dhanasekaran, R.
- Subjects
EARLY detection of cancer ,DEEP learning ,CONVOLUTIONAL neural networks ,NATURAL language processing ,PARTICLE swarm optimization ,ARTIFICIAL neural networks - Abstract
Cancer poses a huge threat to human life and health. As deep learning continues to penetrate the medical field, modern CAD models based on artificial neural networks (ANN), which are data-driven models that rely on cancer-related datasets rather than specialist knowledge, are gradually replacing traditional models and are therefore friendly to areas with insufficient medical resources. According to statistics released by the International Agency for Research on Cancer (IARC) of the World Health Organization, in 2020, there were 19.29 million new cancer cases and 9.96 million cancer deaths worldwide. [Extracted from the article]
- Published
- 2023
- Full Text
- View/download PDF
8. Self-Transfer Learning Network for Multicolor Fabric Defect Detection.
- Author
-
Lin, Song, He, Zhiyong, and Sun, Lining
- Subjects
ARTIFICIAL neural networks ,CONVOLUTIONAL neural networks ,GABOR filters ,FEATURE extraction ,DEEP learning - Abstract
This paper presented a self-transfer learning network (STLN) for multicolor fabric defect detection. Deep neural networks were adopted to detect defects in objects with complex backgrounds such as multicolored fabrics. It is noteworthy that the more disturbances there are on the object surface, the more difficult it is to optimize the network and the more training samples will be required. At the same time, the distinct difference in different types of multi-colored fabrics makes model difficult to apply data information. To this end, the STLN in this paper, consisting of a dataset expansion module, a dataset filtering module, a feature extraction module, a defect detection module, and a category discrimination module, used only limited raw data without the help of external data, and expanded the training set by mining the features of the raw data to better optimize the network. It is experimentally demonstrated that the STLN can achieve higher accuracy compared to deep neural networks for detecting defects of multicolor fabrics with insufficient target data. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
9. Pedestrian detection in infrared image based on depth transfer learning.
- Author
-
Wang, Zhiwen, Feng, Jing, and Zhang, Yifeng
- Subjects
INFRARED imaging ,ARTIFICIAL neural networks ,DEEP learning ,OBJECT recognition (Computer vision) ,PEDESTRIANS ,CONVOLUTIONAL neural networks - Abstract
Because of the difficulty in feature extraction of infrared pedestrian images, the traditional methods of object detection usually make use of the labor to obtain pedestrian features, which suffer from the low-accuracy problem. With the development and the progress of science and technology, deep learning has gradually stepped into the problem of object detection, and achieved good results. In this paper, aiming at the defects of deep convolutional neural network, such as the high cost on training time and slow convergence, a new algorithm of MoblieNet V2(1.4) + SSD infrared image pedestrian detection based on transfer learning is proposed, which adopts a transfer learning method and the Adam optimization algorithm to accelerate network convergence. For the experiments, we augmented the OUS thermal infrared pedestrian dataset and our solution enjoys a higher mAP of 94.8% on the test dataset. The experimental results show that our proposed method has the characteristics of fast convergence, high detection accuracy and short detection time. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
10. Role of deep learning models and analytics in industrial multimedia environment.
- Author
-
Qureshi, Nawab Muhammad Faseeh, Menon, Varun G., Bashir, Ali Kashif, Mumtaz, Shahid, and Mehmood, Irfan
- Subjects
DEEP learning ,MACHINE learning ,ARTIFICIAL neural networks ,ARTIFICIAL intelligence ,CONVOLUTIONAL neural networks ,SOCIAL media - Abstract
There are several base types of deep learning models, such as radial basis function networks (RBFN), recurrent neural networks (RNN), generative-adversarial-networks (GANs), long-short-term memory networks (LSTMs), convolutional neural networks (CNNs), self-organizing maps (SOM), restricted Boltzmann machines (RBM), autoencoders, and multilayer-perceptron (MLP). Deep learning models and data-driven intelligent analytics are widely used components of artificial intelligence. [Extracted from the article]
- Published
- 2023
- Full Text
- View/download PDF
11. AI and augmented reality for 3D Indian dance pose reconstruction cultural revival.
- Author
-
Jayanthi, J. and Maheswari, P. Uma
- Subjects
DEEP learning ,ARTIFICIAL neural networks ,DANCE ,CONVOLUTIONAL neural networks ,HUMAN activity recognition ,DANCE techniques - Abstract
This paper delves into the specialized domain of human action recognition, focusing on the Identification of Indian classical dance poses, specifically Bharatanatyam. Within the dance context, a "Karana" embodies a synchronized and harmonious movement encompassing body, hands, and feet, as defined by the Natyashastra. The essence of Karana lies in the amalgamation of nritta hasta (hand movements), sthaana (body postures), and chaari (leg movements). Although numerous, Natyashastra codifies 108 karanas, showcased in the intricate stone carvings adorning the Nataraj temples of Chidambaram, where Lord Shiva's association with these movements is depicted. Automating pose identification in Bharatanatyam poses challenges due to the vast array of variations, encompassing hand and body postures, mudras (hand gestures), facial expressions, and head gestures. To simplify this intricate task, this research employs image processing and automation techniques. The proposed methodology comprises four stages: acquisition and pre-processing of images involving skeletonization and Data Augmentation techniques, feature extraction from images, classification of dance poses using a deep learning network-based convolution neural network model (InceptionResNetV2), and visualization of 3D models through mesh creation from point clouds. The use of advanced technologies, such as the MediaPipe library for body key point detection and deep learning networks, streamlines the identification process. Data augmentation, a pivotal step, expands small datasets, enhancing the model's accuracy. The convolution neural network model showcased its effectiveness in accurately recognizing intricate dance movements, paving the way for streamlined analysis and interpretation. This innovative approach not only simplifies the identification of Bharatanatyam poses but also sets a precedent for enhancing accessibility and efficiency for practitioners and researchers in the Indian classical dance. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
12. Deep Convolutional Neural Network for Knowledge-Infused Text Classification.
- Author
-
Malik, Sonika and Jain, Sarika
- Subjects
- *
CONVOLUTIONAL neural networks , *ARTIFICIAL neural networks , *SCIENTIFIC computing , *COMPUTER science , *TEXT mining , *DEEP learning , *NATURAL language processing - Abstract
Deep neural networks are extensively used in text mining and Natural Language Processing is to enable computers to understand, analyze, and generate natural language data, such as text or speech, but semantic resources, such as taxonomies and ontologies, are not fully included in deep learning. In this paper, we use Deep Convolutional Neural Network (Deep CNN) to classify research papers using the Computer Science Ontology, an ontology of research areas in the field of computer science. It takes as input the abstract and keywords of a particular research paper and returns the relevant research topic. To evaluate our ontology, we used a gold standard dataset that includes research articles. To further improve text classification results, we propose to design a Deep CNN model. We then used ontology matching to reduce the classes and get better results. Experimental results show that the proposed approach outperforms the one with the highest precision, recall, and F1-score. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
13. LA-RCNN: Luong attention-recurrent- convolutional neural network for EV charging load prediction.
- Author
-
Mekkaoui, Djamel Eddine, Midoun, Mohamed Amine, and Shen, Yanming
- Subjects
CONVOLUTIONAL neural networks ,ELECTRIC vehicle charging stations ,ARTIFICIAL neural networks ,ELECTRIC vehicles ,RECURRENT neural networks ,ELECTRIC automobiles ,ENERGY consumption - Abstract
This article explores the domain of accurate Electric Vehicle (EV) charge prediction, a crucial aspect of the energy consumption system. Predicting EV energy consumption is challenging due to the dynamic dependence and heterogeneity. Despite various approaches proposed in previous studies for intelligent charging, many models rely on limited inputs and ignore the non-linear interactivity between different time series. Moreover, to our knowledge, previous research has not considered the number of connected EVs during the charging procedure. This paper develops an attention-based recurrent convolutional neural network model (LA-RCNN) designed to forecast EV charging load using multivariate time series inputs, including meteorological data and the number of connected users. The proposed model incorporates multiplicative Luong Attention to identify temporal dependencies and correlations. Our objective is to predict the national charging load by considering the charging state and the number of plug-in EVs connected to various charging stations. Using real-world EV charging data from three Chinese cities, we demonstrate that the LA-RCNN model significantly enhances forecast accuracy compared to benchmark methods, reducing MAPE by 21.33% and RMSE by 18.73% as compared to LSTM models. These results highlight the importance of nonlinear attention-based architectures and diverse contextual data sources for effective EV load prediction. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
14. Deep Metallogenic prediction model construction of the Xiongcun no. II orebody based on the DNN algorithm.
- Author
-
Zhang, Di, Zhou, Zhongli, Han, Suyue, Gong, Hao, Zou, Tianyi, and Luo, Jie
- Subjects
ARTIFICIAL neural networks ,DEEP learning ,PREDICTION models ,CONVOLUTIONAL neural networks ,PROSPECTING ,ALGORITHMS ,ARTIFICIAL intelligence ,OCEAN mining - Abstract
With the continuous mining and gradual reduction of shallow deposits, deep prospecting has become a new global prospecting trend. In addition, with the development of artificial intelligence, deep learning provides a favorable means for geological big data analysis. This paper, researches the No. II Orebody of the Xiongcun deposit. First, based on previous research results and metallogenic regularity, prospecting information, namely, lithology, Au-Ag-Cu chemical elements and wall rock alteration is extracted, and the block model is established by combining the Kriging interpolation structure. Second, the datasets are divided into dataset I and dataset II according to "randomness" and "depth". Third, deep prospecting prediction models based on deep neural networks (DNN) and the convolutional neural networks (CNN) is constructed, and the model parameters are optimized. Finally, the models are applied to the deep prediction of the Xiongcun No. II Orebody. The results show that the accuracy rate and recall rate of the prediction model based on the DNN algorithm are 96.15% and 89.23%, respectively, and the AUC is 96.39%, which are higher values than those of the CNN algorithm, indicating that the performance of the prediction model based on the DNN algorithm is better. The accuracy of prediction model based on dataset I is higher than that of dataset II. The accuracy of deep metallogenic prediction based on the DNN algorithm is approximately 89%, that based on the CNN is approximately 87%, and that based on prospecting information method is approximately 61.27%. The prediction results of the DNN algorithm are relatively consistent in the spatial location and scale of the orebody. Therefore, based on the work done in this paper, it is feasible to use a deep learning method to carry out deep mineral prediction. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
15. Convolutional neural network based hurricane damage detection using satellite images.
- Author
-
Kaur, Swapandeep, Gupta, Sheifali, Singh, Swati, Koundal, Deepika, and Zaguia, Atef
- Subjects
CONVOLUTIONAL neural networks ,REMOTE-sensing images ,HURRICANE damage ,ARTIFICIAL neural networks ,COMPUTER vision ,TROPICAL storms ,HURRICANES - Abstract
Hurricanes are tropical storms that cause immense damage to human life and property. Rapid assessment of damage caused by hurricanes is extremely important for the first responders. But this process is usually slow, expensive, labor intensive and prone to errors. The advancements in remote sensing and computer vision help in observing Earth at a different scale. In this paper, a new Convolutional Neural Network model has been designed with the help of satellite images captured from the areas affected by hurricanes. The model will be able to assess the damage by detecting damaged and undamaged buildings based upon which the relief aid can be provided to the affected people on an immediate basis. The model is composed of five convolutional layers, five pooling layers, one flattening layer, one dropout layer and two dense layers. Hurricane Harvey dataset consisting of 23,000 images of size 128 × 128 pixels has been used in this paper. The proposed model is simulated on 5750 test images at a learning rate of 0.00001 and 30 epochs with the Adam optimizer obtaining an accuracy of 0.95 and precision of 0.97. The proposed model will help the emergency responders to determine whether there has been damage or not due to the hurricane and also help those to provide relief aid to the affected people. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
16. Application of machine learning methods in fault detection and classification of power transmission lines: a survey.
- Author
-
Shakiba, Fatemeh Mohammadi, Azizi, S. Mohsen, Zhou, Mengchu, and Abusorrah, Abdullah
- Subjects
CONVOLUTIONAL neural networks ,ELECTRIC lines ,MACHINE learning ,ARTIFICIAL neural networks ,SMART power grids ,FEEDFORWARD neural networks ,FUZZY neural networks - Abstract
The rising development of power systems and smart grids calls for advanced fault diagnosis techniques to prevent undesired interruptions and expenses. One of the most important part of such systems is transmission lines. This paper presents a survey on recent machine learning-based techniques for fault detection, classification, and location estimation in transmission lines. In order to provide reliable and resilient electrical power energy, faster and more accurate fault identification tools are required. Costly consequences of probable faults motivate the need for immediate actions to detect them using intelligent methods, especially emerging machine learning approaches that are powerful in solving diagnosis problems. This paper presents a comprehensive review of various machine learning methodologies including naive Bayesian classifier, decision tree, random forest, k-nearest neighbor, and support vector machine as well as artificial neural networks such as feedforward neural network, convolutional neural network, and adaptive neuro-fuzzy inference system that have been used to detect, classify, and locate faults in transmission lines. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
17. Panoramic image generation using deep neural networks.
- Author
-
Khamiyev, Izat, Issa, Dias, Akhtar, Zahid, and Demirci, M. Fatih
- Subjects
ARTIFICIAL neural networks ,COMPUTER vision ,DEEP learning ,CONVOLUTIONAL neural networks ,ABSOLUTE value - Abstract
A traditional approach for panoramic image generation consists of a random sample consensus (RANSAC) algorithm on a set of scale-invariant feature transform (SIFT) correspondences to generate a homography matrix between two images. Although producing adequate results for some type of images, hand-crafted SIFT features are not robust enough for highly varying natural images and the iterative RANSAC algorithm with its randomness does not always find the desired homography matrix. Recently, deep neural networks have been producing significant results in many challenging computer vision problems by learning features from large amounts of data. However, only very few recent works have been applied deep learning to panoramic image generation with the objective of finding feature correspondences and estimating homography matrix. Moreover, the absence of a proper dataset for the image stitching task hinders the standardization of models and comparison of their results. This paper attempts to generate panoramic images by extensively experimenting with various approaches using deep neural networks. The best proposed deep learning model achieved 7.31 and 1.07 pixels of the average absolute value loss for corner difference in X and Y directions, respectively. At the same time, qualitative results demonstrate superiority in comparison with the state-of-the-art SIFT+RANSAC algorithm. Specifically, in 72% of time the proposed framework either produced better results than SIFT+RANSAC or results of the proposed approach and SIFT+RANSAC were indistinguishable. Although SIFT + RANSAC produces better results in 28% of the time with respect to the loss function, our results are still visually comparable in many of these cases. Finally, a novel panoramic image generation dataset is introduced in this paper. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
18. Exploiting bi-directional deep neural networks for multi-domain sentiment analysis using capsule network.
- Author
-
Ghorbanali, Alireza and Sohrabi, Mohammad Karim
- Subjects
ARTIFICIAL neural networks ,CAPSULE neural networks ,SENTIMENT analysis ,CONVOLUTIONAL neural networks ,LANGUAGE models ,NATURAL language processing ,DEEP learning - Abstract
Sentiment analysis (SA) is the computational analysis of the ideas, feelings, and opinions that determines the polarity of the text documents or comments using natural language processing (NLP) and text analyses techniques. The purpose of the multi-domain SA is to train a classifier using an appropriate set of tagged data to reduce the need for large amounts of data on specific domains and to address their data scarcity challenges using existing data in other domains. A combined use of the pre-trained BERT model, convolutional neural network (CNN), bi-directional long short-term memory (LSTM) and gated recurrent unit (GRU) is exploited in the proposed method of this paper for analysing the multi-domain sentiments using capsule network (CapsuleNet). In the proposed model of this paper, the pre-trained BERT (with CNN) and LSTM extracts the proper features for the CapsuleNet. The proposed approach is evaluated using the Dranziera protocol and the experimental results show that the accuracy of the proposed method is improved in comparison with the other basic deep learning-based methods, such as Multi CNN and LSTM. The results of the experiments show the superiority of the proposed method compared to the other similar methods on in-domain and out-of-domain data. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
19. Classification of mastoid air cells by CT scan images using deep learning method.
- Author
-
Khosravi, Mohammad, Jabbari Moghaddam, Yalda, Esmaeili, Mahdad, Keshtkar, Ahmad, Jalili, Javad, and Tayefi Nasrabadi, Hamid
- Subjects
COMPUTED tomography ,DEEP learning ,ARTIFICIAL neural networks ,CONVOLUTIONAL neural networks ,COMPUTER architecture ,MIDDLE ear - Abstract
Purpose: Mastoid abnormalities show different types of ear illnesses, however inadequacy of experts and low accuracy of diagnostic demand a new approach to detect these abnormalities and reduce human mistakes. The manual analysis of mastoid CT scans is time-consuming and labor-intensive. In this paper the first and robust deep learning-based approaches is introduced to diagnose mastoid abnormalities using a large database of CT images obtained in the clinical center with remarkable accuracy. Methods: In this paper, mastoid abnormalities are classified using the Xception based Convolutional Neural Network (CNN) model, with optimizer Adamax into five categories (Complete pneumatized, Opacification in pneumatization, Partial pneumatization, Opacification in partial pneumatization, None pneumatized). For this reason, a total of 24,800 slides of 152 patients were selected that include the mastoid from most upper to the lowest part of the middle ear cavity to complete the construction of the proposed deep neural network model. Results: The proposed model had the best accuracy of 87.80% (based on grader 1) and 88.44% (based on grader 2) on the 20th epoch and 87.70% (based on grader 1) and 87.56% (based on grader 2) on average and also significantly faster than other types of implemented architectures in terms of the computer running time (in seconds). The 99% confidence interval of the average accuracy was 0.012 which means that the true accuracy is 87.80% and 87.56% ± 1.2% that indicates the power of the model. Conclusions: The manual analysis of ear cavity CT scans is often time-consuming and prone to errors due to various inter- or intra operator variability studies. The proposed method can be used to automatically analyze the middle ear cavity to classify mastoid abnormalities, which is markedly faster than most types of models with the highest accuracy. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
20. Optimized quaternion radial Hahn Moments application to deep learning for the classification of diabetic retinopathy.
- Author
-
Tahiri, Mohamed Amine, Amakdouf, Hicham, El mallahi, Mostafa, and Qjidaa, Hassan
- Subjects
DEEP learning ,ARTIFICIAL neural networks ,DIABETIC retinopathy ,CONVOLUTIONAL neural networks ,QUATERNIONS ,RECEIVER operating characteristic curves - Abstract
This paper proposes a new hybrid method of classification of fundus images provided by the Asia–Pacific Tele-Ophthalmology Society via combining the discrete moment quaternion approach, the artificial intelligence approach, and machine learning in order to automatically distinguish the stage of diabetic retinopathy using reduced databases divided into five classes. The proposed method is based on two main phases: the preprocessing phase, in which using the new radial invariant moments of Hahn in a quaternion optimized by the ant colony algorithm, in order to calculate the original n × n image moments. The second phase is devoted to introducing the calculated moments into the proposed convolutional neural network model. The present work will contribute to creating new neural network architectures that take advantage of Hahn's new 2D radial moment descriptive capability in quaternions. The K-fold cross-validation method is used to measure the proposed model's performance. Finally, graphical measures such as receiver operating characteristic and precision-rapple curves plus a confusion matrix are presented. Furthermore, numerical measures are adopted for f1-score, loss and precision. In 1795 images, the AUC yielded 94.58%, 97.02%, 94.87%, 97.83%, and 96.54% for the five classes of healthy, mild, moderate, severe, and proliferative respectively. These results prove that the proposed method can be used to detect and classify diabetic retinopathy at an early stage. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
21. A novel keyframe extraction method for video classification using deep neural networks.
- Author
-
Savran Kızıltepe, Rukiye, Gan, John Q., and Escobar, Juan José
- Subjects
ARTIFICIAL neural networks ,RECURRENT neural networks ,CONVOLUTIONAL neural networks ,ONE-way analysis of variance - Abstract
Combining convolutional neural networks (CNNs) and recurrent neural networks (RNNs) produces a powerful architecture for video classification problems as spatial–temporal information can be processed simultaneously and effectively. Using transfer learning, this paper presents a comparative study to investigate how temporal information can be utilized to improve the performance of video classification when CNNs and RNNs are combined in various architectures. To enhance the performance of the identified architecture for effective combination of CNN and RNN, a novel action template-based keyframe extraction method is proposed by identifying the informative region of each frame and selecting keyframes based on the similarity between those regions. Extensive experiments on KTH and UCF-101 datasets with ConvLSTM-based video classifiers have been conducted. Experimental results are evaluated using one-way analysis of variance, which reveals the effectiveness of the proposed keyframe extraction method in the sense that it can significantly improve video classification accuracy. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
22. Sentiment analysis: a convolutional neural networks perspective.
- Author
-
Diwan, Tausif and Tembhurne, Jitendra V.
- Subjects
ARTIFICIAL neural networks ,CONVOLUTIONAL neural networks ,SENTIMENT analysis ,DEEP learning ,SOCIAL media ,IMAGE processing ,FASHION dolls - Abstract
With the dramatic growth of various social media platforms, sentiment analysis (SA) of and emotion detection (ED) in various social network posts, blogs, and conversations are very useful and effective for mining the true opinions on different issues, entities, or aspects. During the last decade, many statistical and probabilistic models based on lexical and machine learning approaches have been employed for these tasks. Majority of the relevant literature has emphasized on improving the contemporary SA determination and emotion extraction techniques. With the recent advancements in deep neural networks, various deep learning models have been heavily used to enhance the accuracy of SA. Convolutional neural networks (CNN), a deep neural network model formerly adopted for visual data processing only, has recently gained acceptance for textual inputs as well. As the inputs for SA may be textual, visual, or any combination of these, CNN seems to be a powerful tool. Capturing spatial and contextual information in an incremental fashion respectively from visual and textual inputs proves CNN as an effective model for SA. In this paper, we present an extensive survey that covers the applicability, challenges, and issues for textual, visual, and multimodal SA using CNNs. A detailed discussion and analysis for SA using a CNN model is summarized. For both of the unimodal inputs i.e., textual and visual, we present an optimized algorithmic approach for SA determination using CNN. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
23. Offline handwritten Tai Le character recognition using ensemble deep learning.
- Author
-
Guo, Hai, Liu, Yifan, Yang, Doudou, and Zhao, Jingying
- Subjects
DEEP learning ,PATTERN recognition systems ,ARTIFICIAL neural networks ,CONVOLUTIONAL neural networks - Abstract
Handwriting recognition is an important area in pattern recognition. For many years, Tai Le has been widely used in Southwest China and Southeast Asia, which makes it of great interest for recognition research. The characteristics of the highly similar characters in Tai Le, such as its large proportion of similar characters and the randomness of its writing, bring great challenges to the task of recognition. In this paper, a method based on ensemble deep learning for offline handwritten Tai Le characters is proposed. First, the handwritten Tai Le character dataset SDH2019.2 was constructed and preprocessed. Then, an ensemble deep convolutional neural network (EDCNN) model was constructed by using a stacking strategy. Thirty deep neural network (DNN) and logistic regression algorithms were integrated into a strong Tai Le classifier by stacking. Experiments showed that the proposed model is competitive with the base DNN model and other ensemble models. The results indicate that the performance of Tai Le recognition by the stacking ensemble-based deep neural network model is high, with an accuracy of 98.85%. Additionally, its precision, recall and F1-score of 98.87%, 98.85% and 98.85%, respectively, are superior to those of other classic neural network models. To verify the general applicability of EDCNN, its effectiveness was also verified by recognizing MNIST handwritten digits and Devanagari handwritten characters. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
24. Contrastive self-supervised learning for diabetic retinopathy early detection.
- Author
-
Ouyang, Jihong, Mao, Dong, Guo, Zeqi, Liu, Siguang, Xu, Dong, and Wang, Wenting
- Subjects
DEEP learning ,ARTIFICIAL neural networks ,DIABETIC retinopathy ,COMPUTER-assisted image analysis (Medicine) ,RETINAL imaging ,MEDICAL screening - Abstract
Diabetic Retinopathy (DR) is the major cause of blindness, which seriously threatens the world's vision health. Limited medical resources make early diagnosis and a large-scale screening of DR difficult. Most of the current automatic diagnostic methods are mostly based on deep learning and large-scale labeled data. However, the insufficiency of manual annotations for medical images still is a great challenge of training deep neural networks. Self-supervised learning methods are proposed to learn general features from dataset without manual annotations. Inspired by this, we proposed a deep learning based DR classification model (SimCLR-DR). In this paper, we first use contrastive self-learning algorithm to pre-train the encoder based on convolution network with unlabeled retinal images, then retrain the encoder with classifier on a small annotated training data to detect referable DR. The experimental results on Kaggle dataset show that this proposed method can overcome the training data insufficiency problem and performs better than transfer learning. SimCLR-DR is a good beginning for other deep learning based medical image detection approaches facing the challenge of insufficient annotated data. Figure presents an overview of the proposed framework, which contains three main steps: (i) Data preprocessing; (ii) Pretext task of SimCLR-DR based on contrastive learning; (iii) Downstream Task of SimCLRDR based on CNN. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
25. Classification and identification of disease in potato leaf using hierarchical based deep learning convolutional neural network.
- Author
-
Kumar, Alok and Patel, Vijesh Kumar
- Subjects
CONVOLUTIONAL neural networks ,ARTIFICIAL neural networks ,DECISION support systems ,DEEP learning ,NOSOLOGY ,POTATOES - Abstract
Agriculture is a major source of income of a nation's economy and it plays an important role in feeding mankind. Agriculturists and scientists are working hard to maximize productivity while minimizing the impact on the environment. One important aspect of smart agriculture is disease management in crops. Crops are affected by several diseases caused by pest infestation and pathogens like viruses, bacteria, and fungus. Diseases can be detected early which damage control is aided, and yield loss is avoided. In this paper, a Hierarchical Deep Learning Convolutional Neural Network (HDLCNN) is proposed to detect the diseases in the leaf. Initially, a pre-processing step is performed utilizing the Median Filtering method. This removes the noises in the image. After processing the image, an Intuitionistic Fuzzy Local Binary pattern (IFLBP) is introduced, it extracts the features of the leaf. Then the Hierarchical Deep Learning Convolutional Neural Network is used to detect and classify the disease and the Decision Support Systems help farmers implement effective treatment programs. These allow farmers to increase the efficiency of control techniques without increasing the risks. This method is evaluated and executed in the Matlab Simulink software. While compared to different methods, the proposed technique performs better performance, existing methods are VGG-INCEP, Deep CNN, Random forest methods (RF) and other Spiking neural networks (SNN) models. The accuracy, precision, recall, and F-score of the proposed method is approximately 4%, 6%, 3%, and 3.5% higher than the other existing methods. Then the specificity, sensitivity, and PSNR of the proposed method is 4.5%, 1%, and 2% higher than the existing methods. Thus utilizing this proposed HDLCNN, its performance of the method is improved and this research alerts the former. Through this the former can prevent the leaf from diseases, thus the crop of potato is improved worldwide. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
26. Olfactory perception prediction model inspired by olfactory lateral inhibition and deep feature combination.
- Author
-
Wang, Yu, Zhao, Qilong, Ma, Mingyuan, and Xu, Jin
- Subjects
OLFACTORY perception ,ODORS ,ARTIFICIAL neural networks ,PREDICTION models ,CONVOLUTIONAL neural networks ,DEEP learning - Abstract
Finding the relationship between the chemical structure and physicochemical properties of odor molecules and olfactory perception prediction, i.e. quantitative structure-odor relationship (QSOR), remains a challenging, decades-old task. With the development of deep learning, data-driven methods such as convolutional neural networks or deep neural networks have gradually been used to predict QSOR. However, the differences between the molecular structure of different molecules are subtle and complex, the molecular feature descriptors are numerous and their interactions are complex. In this paper, we propose the Lateral Inhibition-inspired feature pyramid dynamic Convolutional Network, using the feature pyramid network as the backbone network to extract the odor molecular structure features, which can deal with multi-scale changes well. Imitating the lateral inhibition mechanism of animal olfactory, we add the lateral inhibition-inspired attention maps to the dynamic convolution, to improve the prediction accuracy of olfactory perception prediction. Besides, due to a large number of molecular feature descriptors and their complex interactions, we propose to add Attentional Factorization Mechanism to a deep neural network to obtain molecular descriptive features through weighted deep feature combination based on the attention mechanism. Our proposed olfactory perception prediction model noted as LIFMCN has achieved a state-of-the-art result and will help the product design and quality assessment in food, beverage, and fragrance industries. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
27. MatchACNN: A Multi-Granularity Deep Matching Model.
- Author
-
Chang, Guanghui, Wang, Weihan, and Hu, Shiyang
- Subjects
ARTIFICIAL neural networks ,DEEP learning ,NATURAL language processing ,COMPUTER vision ,CONVOLUTIONAL neural networks ,IMAGE recognition (Computer vision) - Abstract
This paper discusses a deep learning approach to ranking relevance in information retrieval (IR). In recent years, deep neural networks have led to exciting breakthroughs in speech recognition, computer vision, and natural language processing (NLP) tasks. However, the multi-granularity deep matching model has yielded few positive results. Existing deep IR models use the granularity of words to match the query and document. According to the human inquiry process, matching should be done at multiple granularities of words, phrases, and even sentences. MatchACNN, a new deep learning architecture for simulating the aforementioned human assessment process, is presented in this study. To solve the aforementioned problems, our model treats text matching as image recognition, extracts features from different dimensions, and employs a two-dimensional convolution neural network and an attention mechanism in image recognition. Experiments on Wiki QA Corpus, NFCorpus, and TREC QA show that MatchACNN can significantly outperform existing deep learning methods. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
28. Diabetic Retinopathy Prediction Based on Wavelet Decomposition and Modified Capsule Network.
- Author
-
Oulhadj, Mohammed, Riffi, Jamal, Khodriss, Chaimae, Mahraz, Adnane Mohamed, Bennis, Ahmed, Yahyaouy, Ali, Chraibi, Fouad, Abdellaoui, Meriem, Andaloussi, Idriss Benatiya, and Tairi, Hamid
- Subjects
DEEP learning ,SEVERITY of illness index ,SIGNAL processing ,DIABETIC retinopathy ,ARTIFICIAL neural networks ,ALGORITHMS ,EVALUATION - Abstract
Diabetic retinopathy (DR) is one of the most common consequences of diabetes. It affects the retina, causing blood vessel damage which can lead to loss of vision. Saving patients from losing their sight or at least slowing the progress of this disease depends mainly on the early detection of this pathology, on top of the detection of its specific stage. Furthermore, the early detection of diabetic retinopathy and the follow-up of the patient's condition remains an arduous task, whether for an experienced expert ophthalmologist or a computer-aided diagnosis technician. In this paper, we aim to propose a new automatic diabetic retinopathy severity level detection method. The proposed approach merges the pyramid hierarchy of the discrete wavelet transform of the retina fundus image with the modified capsule network and the modified inception block proposed, in addition to a new deep hybrid model that concatenates the inception block with capsule networks. The performance of our proposed approach has been validated on the APTOS dataset, as it achieved a high training accuracy of 97.71% and a high testing accuracy score of 86.54%, which is considered one of the best scores achieved in this field using the same dataset. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
29. Discrimination of cycling patterns using accelerometric data and deep learning techniques.
- Author
-
Procházka, Aleš, Charvátová, Hana, Vyšata, Oldřich, Jarchi, Delaram, and Sanei, Saeid
- Subjects
DEEP learning ,ARTIFICIAL neural networks ,GLOBAL Positioning System ,CONVOLUTIONAL neural networks ,SUPPORT vector machines ,ELECTRONIC data processing - Abstract
The monitoring of physical activities and recognition of motion disorders belong to important diagnostical tools in neurology and rehabilitation. The goal of the present paper is in the contribution to this topic by (1) analysis of accelerometric signals recorded by wearable sensors located at specific body positions and by (2) implementation of deep learning methods to classify signal features. This paper uses the general methodology to analysis of accelerometric signals acquired during cycling at different routes followed by the global positioning system. The experimental dataset includes 850 observations that were recorded by a mobile device in the spine area (L3 verterbra) for cycling routes with the different slope. The proposed methodology includes the use of deep learning convolutional neural networks with five layers applied to signal values transformed into the frequency domain without specification of any signal features. The accuracy of discrimination between different motion patterns for the uphill and downhill cycling and recognition of 4 classes associated with different route slopes was 96.6% with the loss criterion of 0.275 for sigmoidal activation functions. These results were compared with those evaluated for selected sets of features estimated for each observation and classified by the support vector machine, Bayesian methods, and the two-layer neural network. The best cross-validation error of 0.361 was achieved for the two-layer neural network model with the sigmoidal and softmax transfer functions. Our methodology suggests that deep learning neural networks are efficient in the assessment of motion activities for automated data processing and have a wide range of applications, including rehabilitation, early diagnosis of neurological problems, and possible use in engineering as well. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
30. A time-efficient convolutional neural network model in human activity recognition.
- Author
-
Gholamrezaii, Marjan and AlModarresi, SMT
- Subjects
ARTIFICIAL neural networks ,CONVOLUTIONAL neural networks ,HUMAN activity recognition ,DEEP learning ,FAST Fourier transforms ,MACHINE learning - Abstract
Activity recognition represents the task of classifying data derived from different sensor types into one of predefined activity classes. The most popular and beneficial sensors in the area of action recognition are inertial sensors such as accelerometer and gyroscope. Convolutional neural network (CNN) as one of the best deep learning methods has recently attracted much attention to the problem of activity recognition, where 1D kernels capture local dependency over time in a series of observations measured at inertial sensors (3-axis accelerometers and gyroscopes) while in 2D kernels apart from time dependency, dependency between signals from different axes of same sensor and also over different sensors will be considered. Most convolutional neural networks used for recognition task are built using convolution and pooling layers followed by a few number of fully connected layers but large and deep neural networks have high computational costs. In this paper, we propose a new architecture that consists solely of convolutional layers and find that with removing the pooling layers and instead adding strides to convolution layers, the computational time will decrease notably while the model performance will not change or in some cases will even improve. Also both 1D and 2D convolutional neural networks with and without pooling layer will be investigated and their performance will be compared with each other and also with some other hand-crafted feature based methods. The third point that will be discussed in this paper is the impact of applying fast fourier transform (FFT) to inputs before training learning algorithm. It will be shown that this preprocessing will enhance the model performance. Experiments on benchmark datasets demonstrate the high performance of proposed 2D CNN model with no pooling layers. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
31. Deep learning-based automatic annotation and online classification of remote multimedia images.
- Author
-
Kang, Sucheng
- Subjects
DEEP learning ,ARTIFICIAL neural networks ,CONVOLUTIONAL neural networks ,FEATURE extraction ,AUTOMATIC classification ,MACHINE learning - Abstract
In this paper, based on in-depth analysis of remote multimedia images, the automatic annotation and classification of graphics are tested and analyzed by algorithms of deep learning. To reduce the time of remote multimedia image labeling and online classification, and improve efficiency, we study the use of deep learning methods to automate annotation and online classification of remote multimedia images. An image is re-labeling algorithm based on modeling the correlation of hidden feature dimensions is proposed to improve the effect of hidden feature models by modeling the correlation between hid feature dimensions. The algorithm constructs the correlation between each pair of dimensions in the hidden features through the outer product operation to form a two-dimensional interactive graph. The information in the interaction graph is refined layer by layer by using the ability of the convolutional neural network to model local features, and finally, a representation of the correlation of all dimensions in the hidden features is formed to realize the re-labeling of social images. The experimental results show that this method can utilize the hidden feature information more effectively and improve the image re-labeling results. The light-weight feature extraction network significantly reduces the number of model parameters at the expense of a small amount of detection accuracy, and the FPN pyramid structure enhances the feature characterization ability of the feature extraction network. The performance is close to that of the Yolo algorithm. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
32. An improved real time detection of data poisoning attacks in deep learning vision systems.
- Author
-
Raghavan, Vijay, Mazzuchi, Thomas, and Sarkani, Shahram
- Subjects
DEEP learning ,ARTIFICIAL intelligence ,CONVOLUTIONAL neural networks ,ARTIFICIAL neural networks ,VISION - Abstract
The practice of using deep learning methods in safety critical vision systems such as autonomous driving has come a long way. As vision systems supported by deep learning methods become ubiquitous, the possible security threats faced by these systems have come into greater focus. As it is with any artificial intelligence system, these deep neural vision networks are first trained on a data set of interest, once they start performing well, they are deployed to a real-world environment. In the training stage, deep learning systems are susceptible to data poisoning attacks. While deep neural networks have proved to be versatile in solving a host of challenges. These systems have complex data ecosystems especially in computer vision. In practice, the security threats when training these systems are often ignored while deploying these models in the real world. However, these threats pose significant risks to the overall reliability of the system. In this paper, we present the fundamentals of data poisoning attacks when training deep learning vision systems and discuss countermeasures against these types of attacks. In addition, we simulate the risk posed by a real-world data poisoning attack on a deep learning vision system and present a novel algorithm MOVCE--Model verification with Convolutional Neural Network and Word Embeddings which provides an effective countermeasure for maintaining the reliability of the system. The countermeasure described in this paper can be used on a wide variety of use cases where the risks posed by poisoning the training data are similar. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
33. Supervised semantic segmentation based on deep learning: a survey.
- Author
-
Zhou, Yuguo, Ren, Yanbo, Xu, Erya, Liu, Shiliang, and Zhou, Lijian
- Subjects
ARTIFICIAL neural networks ,DEEP learning ,CONVOLUTIONAL neural networks ,COMPUTER vision ,SUPERVISED learning ,IMAGE segmentation ,VISUAL fields - Abstract
Recently, many semantic segmentation methods based on fully supervised learning are leading the way in the computer vision field. In particular, deep neural networks headed by convolutional neural networks can effectively solve many challenging semantic segmentation tasks. To realize more refined semantic image segmentation, this paper studies the semantic segmentation task with a novel perspective, in which three key issues affecting the segmentation effect are considered. Firstly, it is hard to predict the classification results accurately in the high-resolution map from the reduced feature map since the scales are different between them. Secondly, the multi-scale characteristics of the target and the complexity of the background make it difficult to extract semantic features. Thirdly, the problem of intra-class differences and inter-class similarities can lead to incorrect classification of the boundary. To find the solutions to the above issues based on existing methods, the inner connection between past research and ongoing research is explored in this paper. In addition, qualitative and quantitative analyses are made, which can help the researchers to establish an intuitive understanding of various methods. At last, some conclusions about the existing methods are drawn to enhance segmentation performance. Moreover, the deficiencies of existing methods are researched and criticized, and a guide for future directions is provided. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
34. Shallow and deep feature fusion for digital audio tampering detection.
- Author
-
Wang, Zhifeng, Yang, Yao, Zeng, Chunyan, Kong, Shuai, Feng, Shixiong, and Zhao, Nan
- Subjects
ARTIFICIAL neural networks ,HILBERT transform ,DISCRETE Fourier transforms ,CONVOLUTIONAL neural networks ,DIGITAL audio ,IMAGE fusion ,MACHINE learning ,FEATURE extraction - Abstract
Digital audio tampering detection can be used to verify the authenticity of digital audio. However, most current methods use standard electronic network frequency (ENF) databases for visual comparison analysis of ENF continuity of digital audio or perform feature extraction for classification by machine learning methods. ENF databases are usually tricky to obtain, visual methods have weak feature representation, and machine learning methods have more information loss in features, resulting in low detection accuracy. This paper proposes a fusion method of shallow and deep features to fully use ENF information by exploiting the complementary nature of features at different levels to more accurately describe the changes in inconsistency produced by tampering operations to raw digital audio. Firstly, the audio signal is band-pass filtered to obtain the ENF component. Then, the discrete Fourier transform (DFT) and Hilbert transform are performed to obtain the phase and instantaneous frequency of the ENF component. Secondly, the mean value of the sequence variation is used as the shallow feature; the feature matrix obtained by framing and reshaping of the ENF sequence is used as the input of the convolutional neural network; the characteristics of the fitted coefficients are obtained by curve fitting. Then, the local details of ENF are obtained from the feature matrix by the convolutional neural network, and the global information of ENF is obtained by fitting coefficient features through deep neural network (DNN). The depth features of ENF are composed of ENF global information and local information together. The shallow and deep features are fused using an attention mechanism to give greater weights to features useful for classification and suppress invalid features. Finally, the tampered audio is detected by downscaling and fitting with a DNN containing two fully connected layers, and classification is performed using a Softmax layer. The method achieves 97.03% accuracy on three classic databases: Carioca 1, Carioca 2, and New Spanish. In addition, we have achieved an accuracy of 88.31% on the newly constructed database GAUDI-DI. Experimental results show that the proposed method is superior to the state-of-the-art method. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
35. DeepAHR: a deep neural network approach for recognizing Arabic handwritten recognition.
- Author
-
AlShehri, Helala
- Subjects
- *
ARTIFICIAL neural networks , *CONVOLUTIONAL neural networks , *PATTERN recognition systems , *DEEP learning - Abstract
Automatic handwritten character recognition plays a significant role in various applications across multiple fields. With the growing interest in automatic handwriting recognition and the advancement of deep learning methods, researchers have achieved significant improvements in the development of English handwriting recognition methods. However, the recognition of Arabic handwriting has received insufficient attention. In this paper, a novel "DeepAHR" model is presented to accurately and efficiently recognize Arabic handwritten characters using deep learning techniques. The "DeepAHR" model is based on a convolutional neural network (CNN) and is trained using two recent public datasets: Hijaa and Arabic handwritten characters dataset (AHCD). The overall accuracies of the proposed model were 98.66% and 88.24% on the AHCD and Hijaa datasets, respectively.The experimental results showed that DeepAHR outperformed state-of-the-art methods in the literature. These promising results provide evidence of the successful use of the DeepAHR model for recognizing handwritten Arabic characters [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
36. Acoustic data augmentation for small passive acoustic monitoring datasets.
- Author
-
Nshimiyimana, Aime
- Subjects
ARTIFICIAL neural networks ,DATA augmentation ,PATTERN recognition systems ,DEEP learning ,AUDITORY masking ,CONVOLUTIONAL neural networks ,COMPUTER vision - Abstract
Training complex deep neural networks can result in overfitting when the networks are trained from random weight initialization on small datasets. Augmentation helps to reduce the negative effects of overfitting. The findings in computer vision and audio recognition research reveals that the performance of machine learning classifiers is significantly improved when augmentation is used. In the context of ecology, researchers conduct field surveys whereby microphones are placed in some location and audio data is recorded over a period of time. There is however no guarantee that the particular species of interest in the field survey will vocalize frequently near the microphone. Thus, the amount of data captured for the species of interest might be limited, and it may then be the source of overfitting. The main contribution of this paper is in performing experiments with time and frequency masking, and noise addition augmentation techniques in training a visual convolutional neural networks (CNN) repurposed for pattern recognition in acoustic spectrograms. These techniques increased the audio examples for the pin-tailed whydah and the Cape robin-chat to create a robust audio vocalization classifiers. To evaluate the performance of the augmentation techniques we conducted a comparison between experiments run with and without augmentation. We chose to use CNN as our classifier given that they are state-of-the-art in audio recognition tasks and they have revealed good performance. In the used augmentation techniques; time masking achieved 90.2% as the highest testing accuracy while pink noise is the most successful best classifier. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
37. Spatial Interpolation and Conditional Map Generation Using Deep Image Prior for Environmental Applications.
- Author
-
Rakotonirina, Herbert, Guridi, Ignacio, Honeine, Paul, Atteia, Olivier, and Van Exem, Antonin
- Subjects
- *
KRIGING , *ARTIFICIAL neural networks , *CONVOLUTIONAL neural networks , *INTERPOLATION , *DIGITAL elevation models , *IMAGE reconstruction - Abstract
Kriging is the most widely used spatial interpolation method in geostatistics. For many environmental applications, kriging may have to satisfy the stationarity and isotropy hypothesis, and new techniques using machine learning suffer from a lack of labeled data. In this paper, we propose the use of deep image prior, which is a U-net-like deep neural network designed for image reconstruction, to perform spatial interpolation and conditional map generation without any prior learning. This approach allows us to overcome the assumptions for kriging as well as the lack of labeled data when proposing uncertainty and probability above a certain threshold. The proposed method is based on a convolutional neural network that generates a map from random values by minimizing the difference between the output map and the observed values. With this new method of spatial interpolation, we generate n maps to obtain a map of uncertainty and a map of probability of exceeding the threshold. Experiments demonstrate the relevance of the proposed methods for spatial interpolation on both the well-known digital elevation model data and the more challenging case of pollution mapping. The results obtained with the three datasets demonstrate competitive performance compared with state-of-the-art methods. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
38. Parkinson classification neural network with mass algorithm for processing speech signals.
- Author
-
Akila, B. and Nayahi, J. Jesu Vedha
- Subjects
- *
ARTIFICIAL neural networks , *SIGNAL processing , *DEEP learning , *MACHINE learning , *CONVOLUTIONAL neural networks , *PARKINSON'S disease , *SPEECH perception , *DEEP brain stimulation - Abstract
Parkinson's disease (PD) is a condition that degenerates over time and impairs speech and pronunciation because brain cells have died. This research work aims to predict parkinson disease using the voice features extracted from speech signals recorded from PD individuals with dysphonic speech disorders by employing deep learning algorithms. PD is challenging to diagnose early on in the clinical presentation. To address the issue in machine learning methods, this paper proposes a neural network model by processing speech signals to classify PD using the University of California Irvine (UCI) machine learning repository dataset. Initially, a pre-loss reduction module is created by using pre-sampling to make the dataset balanced by reducing the dimensionality and maintaining the size of the space without influencing the learning process for data preparation. The relevant features are derived using a novel multi-agent salp swarm (MASS) algorithm, and a novel Parkinson classification neural network (PCNN) is proposed to classify Parkinson's patients with high accuracy employing these derived features. The result shows that the models that use MASS-PCNN produce higher classification accuracy of 99.1%, precision of 97.8%, recall of 94.7% and F1-score of 0.995 when paralleled to the existing models. As an outcome, the suggested model will perform superior to common convolutional neural networks. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
39. AReNet: Cascade learning of multibranch convolutional neural networks for human activity recognition.
- Author
-
Boudjema, Ali, Titouna, Faiza, and Titouna, Chafiq
- Subjects
ARTIFICIAL neural networks ,CONVOLUTIONAL neural networks ,HUMAN activity recognition ,DEEP learning ,TIME series analysis ,HUMAN-computer interaction - Abstract
Human Activity Recognition (HAR) has become a crucial area of research, driven by the advancements in wearable device sensors. HAR finds widespread applications, including elderly monitoring, security, and human-computer interaction. However, the nature of sensor-based HAR with time series data poses significant challenges in extracting relevant features, which hampers conventional methods' effectiveness, raises a substantial allocation of resources, and prolonged convergence time. researchers have proposed several techniques to solve time series classifiaciton. Deep Learning (DL) models are the most powerful and promising in terms of classification performance. Despite this, they also present challenges in the areas of hyperparameter tuning, training, and the decision models' complexity. This paper proposes AReNet, a light deep learning model for HAR that is composed of two main parts. The first involves a deep neural network architecture integrating 1D CNN blocks, and a fusion operator that aggregates convolution outputs at multiple levels. The second component employs a progressive cascade training during the learning process. This strategic approach reduces the parameters number and minimizes the training time, contributing to a more efficient and simpler model. AReNet achieves remarkable performances in accurately recognizing human activities when experimental analysis is conducted on five publicly available benchmark datasets. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
40. Apple foliar leaf disease detection through improved capsule neural network architecture.
- Author
-
S, Sapna, S, Sandhya, Acharya, Vasundhara, and Ravi, Vinayakumar
- Subjects
CAPSULE neural networks ,CONVOLUTIONAL neural networks ,ARTIFICIAL neural networks ,COMPUTER vision ,IMAGE recognition (Computer vision) ,APPLE orchards - Abstract
Apple Scab and Apple Rust are the major classes of apple leaf diseases that gravely affect the apple yield. Seeking an automatic, less expensive, fast yet precise method to detect plant diseases is crucial. Traditional approaches to detect plant diseases using computer vision involve complex and labor-intensive methodologies that rely on image enhancement methods and hand-engineered features. The deep convolutional neural network models are highly favourable in performing image classification with many target classes without involving the arduous phase of feature engineering. In this paper, we utilized the Capsule Neural Network (CapsNet) architecture and modified the network structure by adding additional convolution layers to enhance the model's learning capacity to classify the apple diseases into apple rust, apple scab, healthy, and multiple diseases on the same leaf. Model training was performed on a dataset of images that reflected complex growing conditions observed in the real world. The ability of the model to learn was improved by enhancing the images. Experimentation was conducted on the Kaggle Plant Pathology 2020 - FGVC7 dataset. Experimental study demonstrated a recognition accuracy of 91.37% on the test set, with an overall improvement of 3.67% in accuracy when compared to the research work utilizing the same dataset in literature. Therefore, the proposed method effectively achieves Apple foliar leaf disease detection and surpasses existing state-of-the-art techniques applied to the same dataset. "(Dataset Link: https://www.kaggle.com/c/plant-pathology-2020-fgvc7/data)" [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
41. The Future of Human Activity Recognition: Deep Learning or Feature Engineering?
- Author
-
Kanjilal, Ria and Uysal, Ismail
- Subjects
HUMAN activity recognition ,MACHINE learning ,DEEP learning ,ARTIFICIAL neural networks ,FEATURE extraction ,CONVOLUTIONAL neural networks ,ACTIVITIES of daily living - Abstract
A significant gap exists in our knowledge of how domain-specific feature extraction compares to unsupervised feature learning in the latent space of a deep neural network for a range of temporal applications including human activity recognition (HAR). This paper aims to address this gap specifically for fall detection and motion recognition using acceleration data. To ensure reproducibility, we use a publicly available dataset, UniMiB-SHAR, with a well-established history in the HAR literature. We methodically analyze the performance of 64 different combinations of (i) learning representations (in the form of raw temporal data or extracted features), (ii) traditional and modern classifiers with different topologies on (iii) both binary (fall detection) and multi-class (daily activities of living) datasets. We report and discuss our findings and conclude that while feature engineering may still be competitive for HAR, trainable front-ends of modern deep learning algorithms can benefit from raw temporal data especially in large quantities. In fact, this paper claims state-of-the-art where we significantly outperform the most recent literature on this dataset in both activity recognition (88.41% vs. 98.02%) and fall detection (98.71% vs. 99.82%) using raw temporal input. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
42. Intelligent routing using convolutional neural network in software-defined data center network.
- Author
-
Modi, Tejas M. and Swain, Pravati
- Subjects
CONVOLUTIONAL neural networks ,DEEP learning ,SOFTWARE-defined networking ,SERVER farms (Computer network management) ,ARTIFICIAL neural networks ,ROUTING algorithms - Abstract
A Data Center Network (DCN) is composed of a large number of computing and storage nodes that are interconnected by well-organized switches. The Software-Defined Networking (SDN) based DCN (SD-DCN) improves resource utilization and provides virtual network access by separating the data plane and control plane of DCN. However, the routing strategies in current SD-DCN systems are based on traditional mechanisms that lack in real-time modification and are less efficient in resource utilization. To overcome these limitations, Convolutional Neural Network (CNN) deep learning model is proposed in this paper to improve the routing computation in SD-DCN, i.e., FAT-tree topology. The CNN deep learning model gives intelligent paths according to online training of traffic patterns. Moreover, the achieved network performance is compared with specific existing routing algorithms for SD-DCN. It is observed that the average network throughput is almost doubled for hot-spot traffic as compared with existing routing algorithms OSPF and FlowDCN. The experimental results show that, compared to ANN, the proposed model has increased the average network throughput by approximately 40%. Also, the proposed CNN model has outperformed the Artificial Neural Network (ANN) model in terms of average network delay and packet loss rate. Similarly, the overall bandwidth utilization is achieved by approximately 70% as compared to existing mechanisms. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
43. ML-WiGR: a meta-learning-based approach for cross-domain device-free gesture recognition.
- Author
-
Gao, Zhenyue, Xue, Jianqiang, Zhang, Jianxing, and Xiao, Wendong
- Subjects
GESTURE ,TELEMEDICINE ,CONVOLUTIONAL neural networks ,ARTIFICIAL neural networks ,HUMAN-computer interaction - Abstract
Accurate sensing and understanding of gestures can improve the quality of human–computer interaction and show great theoretical significance and application potentials in the fields of smart home, assisted medical care and virtual reality. WiFi channel state information (CSI)-based device-free wireless gesture recognition requires no sensors and has a series of advantages such as permission for non-line-of-sight scenario, low cost, preserving for personal privacy and working in the dark night. Although most of the current WiFi CSI-based gesture recognition approaches can achieve good performance, they are difficult to adapt to the new domains. Therefore, this paper proposes ML-WiGR, a novel approach for device-free gesture recognition in cross-domain applications. ML-WiGR applies convolutional neural networks (CNN) and long short-term memory (LSTM) neural networks as the basic model for gesture recognition to extract spatial and temporal features. Combined with the meta-learning training mechanism, ML-WiGR can dynamically adjust the learning rate and meta-learning rate in training process adaptively and optimize the initial parameters of a basic model for gesture recognition, only using a few samples and several iterations to adapt to the new domain. In the experiments, the approach is tested under a variety of scenarios. The results show that ML-WiGR can achieve comparable performance against existing approaches with only a small number of samples for training in cross-domains. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
44. Metaheuristic algorithm based hyper-parameters optimization for skin lesion classification.
- Author
-
Golnoori, Farzad, Boroujeni, Farsad Zamani, and Monadjemi, Amirhassan
- Subjects
ARTIFICIAL neural networks ,METAHEURISTIC algorithms ,CONVOLUTIONAL neural networks ,OPTIMIZATION algorithms ,IMAGE recognition (Computer vision) ,SKIN cancer - Abstract
The most dangerous type of skin cancer in the world is Melanoma. Early diagnosis of this cancer in primary stages can increase the chance of surviving death. In recent years, automatic skin cancer detection systems have played a significant role in increasing the rate of cancer diagnosis. Although deep convolutional neural networks presented advantages over traditional methods and brought tremendous breakthroughs in many image classification tasks, accurate classification of skin lesions remains challenging due to the complexity of choosing appropriate architecture for deep neural networks and hyper-parameter tuning. The aim of this paper is to increase the performance of skin lesion classification system through optimizing hyper-parameters and architecture of deep neural network using metaheuristic optimization algorithms. For this purpose, three optimization algorithms are employed to find an optimal configuration for the convolutional neural network either in pre-trained models or model that are trained from scratch. Then the deep features extracted from the optimized models were fused together in pairs and used to train a KNN classifier. The effect of applying hyper-parameter optimization is evaluated on ISIC 2017 and ISIC 2018 datasets. The accuracy of the deep neural network produced by our method reaches to 81.6% and F1-score of 80.9% on ISIC 2017 dataset and accuracy of 90.1% and F1-score of 89.8% on ISIC 2018. The results of the present study indicate that the proposed method outperforms similar methods in classifying seven and three classes of images, without requiring heavy preprocessing and segmentation steps. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
45. PoolNet deep feature based person re-identification.
- Author
-
Rani, J. Stella Janci and Augasta, M. Gethsiyal
- Subjects
ARTIFICIAL neural networks ,CONVOLUTIONAL neural networks ,DEEP learning - Abstract
Learning with Deep Neural Networks has recently reached state-of-the-art outcomes for Person Re-Identification. Effective learning can be accomplished only with efficient features robust to illumination and viewpoint changes. This paper proposes a new feature representation method called PoolNet Deep Feature (PNDF) for person re-identification with Convolution Neural Networks. The proposed CNN architecture called PoolNet consists of two Pool Added Blocks (PAB) and a Pool Concatenated Block (PCB) to extract the more sophisticated dominant and precise features for better learning towards a person's re-identification. The efficiency of the proposed method is demonstrated in terms of re-identification accuracy by implementing it on the challenging small scale & large-scale person re-identification datasets such as VIPeR, Market1501, CUHK03, GRID, and LaST. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
46. Image denoising in the deep learning era.
- Author
-
Izadi, Saeed, Sutton, Darren, and Hamarneh, Ghassan
- Subjects
IMAGE denoising ,ARTIFICIAL neural networks ,DEEP learning ,CONVOLUTIONAL neural networks ,RECURRENT neural networks ,PHOTOGRAPHS - Abstract
Over the last decade, the number of digital images captured per day has increased exponentially, due to the accessibility of imaging devices. The visual quality of photographs captured by low cost or miniaturized imaging devices is often degraded by noise during image acquisition and data transmission. With the re-emergence of deep neural networks, the performance of image denoising techniques has been substantially improved in recent years. The objective of this paper is to provide a comprehensive survey of recent advances in image denoising techniques based on deep neural networks. We begin with a thorough description of the fundamental preliminaries of the image denoising problem, followed by an overview of the benchmark datasets and commonly used metrics for objective assessment of denoising algorithms. We study the existing deep denoisers in the supervised and unsupervised training paradigms and review the technical specifics of some representative methods within each category. We conclude the survey by remarking on trends and challenges in the development of state-of-the-art algorithms and future research. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
47. DiffMoment: an adaptive optimization technique for convolutional neural network.
- Author
-
Bhakta, Shubhankar, Nandi, Utpal, Si, Tapas, Ghosal, Sudipta Kr, Changdar, Chiranjit, and Pal, Rajat Kumar
- Subjects
CONVOLUTIONAL neural networks ,ARTIFICIAL neural networks ,MACHINE learning ,MATHEMATICAL optimization ,DEEP learning - Abstract
Stochastic Gradient Decent (SGD) is a very popular basic optimizer applied in the learning algorithms of deep neural networks. However, it has fixed-sized steps for every epoch without considering gradient behaviour to determine step size. The improved SGD optimizers like AdaGrad, Adam, AdaDelta, RAdam, and RMSProp make step sizes adaptive in every epoch. However, these optimizers depend on square roots of exponential moving averages (EMA) of squared previous gradients or momentums or both and cannot take the benefit of local change in gradients or momentums or both. To reduce these limitations, a novel optimizer has been presented in this paper where the adjustment of step size is done for each parameter based on changing information between the 1
st and the 2nd moment estimate (i.e., diffMoment). The experimental results depict that diffMoment offers better performance than AdaGrad, Adam, AdaDelta, RAdam, and RMSProp optimizers. It is also noticed that diffMoment does uniformly better for training Convolutional Neural Networks (CNN) applying different activation functions. [ABSTRACT FROM AUTHOR]- Published
- 2023
- Full Text
- View/download PDF
48. Learning Local Contrast for Crisp Edge Detection.
- Author
-
Fang, Xiao-Nan and Zhang, Song-Hai
- Subjects
ARTIFICIAL neural networks ,CONVOLUTIONAL neural networks ,DEEP learning ,IMAGE retrieval - Abstract
In recent years, the accuracy of edge detection on several benchmarks has been significantly improved by deep learning based methods. However, the prediction of deep neural networks is usually blurry and needs further post-processing including non-maximum suppression and morphological thinning. In this paper, we demonstrate that the blurry effect arises from the binary cross-entropy loss, and crisp edges could be obtained directly from deep convolutional neural networks. We propose to learn edge maps as the representation of local contrast with a novel local contrast loss. The local contrast is optimized in a stochastic way to focus on specific edge directions. Experiments show that the edge detection network trained with local contrast loss achieves a high accuracy comparable to previous methods and dramatically improves the crispness. We also present several applications of the crisp edges, including image completion, image retrieval, sketch generation, and video stylization. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
49. ECG signal classification via combining hand-engineered features with deep neural network features.
- Author
-
Zhanquan, Sun, Chaoli, Wang, Engang, Tian, and Zhong, Yin
- Subjects
SIGNAL classification ,ATRIAL arrhythmias ,ARTIFICIAL neural networks ,FEATURE extraction ,CONVOLUTIONAL neural networks ,ELECTROCARDIOGRAPHY - Abstract
The electrocardiogram (ECG) has been proven to be the most common and effective approach to investigate cardiovascular diseases because that it is simple, noninvasive and inexpensive. However, the differences among ECG signals are difficult to be distinguished. In this paper, hand-engineered ECG features and automatic ECG features extracted with deep neural networks are combined to generate high dimensional features. First, rich hand-engineered features were extracted using some extraction methods for common ECG features. Second, a convolutional neural network model was designed to extract the ECG features automatically. High dimensional feature set is obtained through combing hand-engineered features and automatic features. To get the most informative ECG feature combination, a feature selection method based on mutual information was proposed. An ensemble learning method was then used to build the classification model for abnormal ECG types. Six atrial arrhythmia subtypes' ECG signals from the Chinese cardiovascular disease database dataset were analyzed through the proposed method. The precision of the classification results reaches 98.41%, which is higher than the results based on other current methods. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
50. Hybrid deep convolutional neural models for iris image recognition.
- Author
-
Winston, J. Jenkin, Hemanth, D. Jude, Angelopoulou, Anastassia, and Kapetanios, Epaminondas
- Subjects
DEEP learning ,IRIS recognition ,IMAGE recognition (Computer vision) ,ARTIFICIAL neural networks ,RECEIVER operating characteristic curves ,CONVOLUTIONAL neural networks - Abstract
This paper briefly explains about the application of deep learning-based methods for biometric applications. This work attempts to solve the problem of limited availability of datasets which affects accuracy of the classifiers. This paper explores the iris recognition problem using a basic convolutional neural network model and hybrid deep learning models. The augmentations used to populate the dataset and their outputs are also shown in this study. An illustration of learned weights and the outputs of intermediary stages the network like convolution layer, normalization layer and activation layer are given to help better understanding of the process. The performance of the network is studied using accuracy and receiver operating characteristic curve. The empirical results of our experiments show that Adam based optimization is good at learning iris features using deep learning. Moreover, the hybrid deep learning network with SVM performs better in iris recognition with a maximum accuracy of 97.8%. These experiments have also revealed that not all hybrid networks will give better performance as the hybrid deep learning network with KNN has given lesser accuracy. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.