25 results on '"Khan, Asif A."'
Search Results
2. Anomaly Detection of Breast Cancer Using Deep Learning
- Author
-
Alloqmani, Ahad, Abushark, Yoosef B., and Khan, Asif Irshad
- Published
- 2023
- Full Text
- View/download PDF
3. Internet of Things (IoT) Security Intelligence: A Comprehensive Overview, Machine Learning Solutions and Research Directions
- Author
-
Sarker, Iqbal H., Khan, Asif Irshad, Abushark, Yoosef B., and Alsolami, Fawaz
- Published
- 2023
- Full Text
- View/download PDF
4. A Comparative Study Between Rule-Based and Transformer-Based Election Prediction Approaches: 2020 US Presidential Election as a Use Case
- Author
-
Khan, Asif, Zhang, Huaping, Boudjellal, Nada, Dai, Lin, Ahmad, Arshad, Shang, Jianyun, Haindl, Philipp, Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Prates, Raquel Oliveira, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Kotsis, Gabriele, editor, Tjoa, A Min, editor, Khalil, Ismail, editor, Moser, Bernhard, editor, Taudes, Alfred, editor, Mashkoor, Atif, editor, Sametinger, Johannes, editor, Martinez-Gil, Jorge, editor, Sobieczky, Florian, editor, Fischer, Lukas, editor, Ramler, Rudolf, editor, Khan, Maqbool, editor, and Czech, Gerald, editor
- Published
- 2022
- Full Text
- View/download PDF
5. Knowledge-based Word Tokenization System for Urdu.
- Author
-
Khan, Asif, Khan, Khairullah, Khan, Wahab, Khan, Sadiq Nawaz, and Haq, Rafiul
- Subjects
NATURAL language processing ,MACHINE learning ,ARTIFICIAL intelligence ,ARTIFICIAL neural networks ,DIGITAL technology ,DEEP learning - Abstract
Word tokenization, a foundational step in natural language processing (NLP), is critical for tasks like part-of-speech tagging, named entity recognition, and parsing, as well as various independent NLP applications. In our tech-driven era, the exponential growth of textual data on the World Wide Web demands sophisticated tools for effective processing. Urdu, spoken widely across the globe, is experiencing a surge in, presents unique challenges due to its distinct writing style, the absence of capitalization features, and the prevalence of compound words. This study introduces a novel knowledge-based word tokenization system tailored for Urdu. Central to this system is a maximum matching model with forward and reverse variants, setting it apart from conventional approaches. The novelty of our system lies in its holistic approach, integrating knowledgebased techniques, dual-variant maximum matching, and heightened adaptability to low-resource language speakers, emphasizing the urgent need for advanced Urdu Language Processing (ULP) systems. However, Urdu, labeled as a low-resource language challenges compared to traditional machine learning (ML) approaches. Significantly, our system eliminates the need for a features file and pre-labelled datasets, streamlining the tokenization process. To evaluate the proposed model's efficacy, a comprehensive analysis was conducted on a dataset comprising 100 sentences with 5,000 Urdu words, yielding an impressive accuracy of 97%. This research makes a substantial contribution to Urdu language processing, providing an innovative solution to the complexities posed by the unique linguistic attributes of Urdu tokenization. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
6. Mobile Deep Learning: Exploring Deep Neural Network for Predicting Context-Aware Smartphone Usage
- Author
-
Sarker, Iqbal H., Abushark, Yoosef B., Khan, Asif Irshad, Alam, Md Mottahir, and Nowrozy, Raza
- Published
- 2021
- Full Text
- View/download PDF
7. An optimal deep belief with buffalo optimization algorithm for fault detection and power loss in grid-connected system.
- Author
-
Alam, Md. Mottahir, Haque, Ahteshamul, Hakami, Jabir, Khan, Asif Irshad, Pasha, Amjad Ali, Kasim, Navin, Islam, Saiful, Khan, Mohammad Amir, Zahmatkesh, Sasan, Hajiaghaei-Keshteli, Mostafa, and Irshad, Kashif
- Subjects
OPTIMIZATION algorithms ,FISHER discriminant analysis ,DEEP learning ,PRINCIPAL components analysis ,DISTRIBUTED power generation ,METAHEURISTIC algorithms ,PHOTOVOLTAIC power systems - Abstract
The recent increase in photovoltaic (PV) power generation and its extensive use worldwide has led to the development of complex distributed generation systems, which has caused an increase in PV faults. These defects lead to considerable power losses, significantly impacting the reliability and performance of the PV system. Several approaches have been implemented, but an accurate solution has not been found. Therefore, an optimal Deep Belief with Buffalo Optimization (DB-BO) algorithm is applied in the grid-connected system for detecting faults and regulating its classes. Moreover, principal component analysis is used to analyze the power loss issues, and linear discriminant analysis is utilized to mitigate the voltage deviation issues. MATLAB or Simulink is used as the implementation process, and simulation outcomes are compared with recent conventional models. It has been revealed that the developed DB-BO algorithm has reduced the power loss to 3.4 mW. Also, total harmonic distortion (THD) is improved compared to the existing security methods. Thus, the efficiency of the model that was built has been proven by getting the best results in accuracy, total harmonic distortion (THD), and power loss. The computation time of the proposed model (0.238 s) is compared with metaheuristic algorithms such as CSE (0.315629 s) and GWA (3.636 s). [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
8. Web-Informed-Augmented Fake News Detection Model Using Stacked Layers of Convolutional Neural Network and Deep Autoencoder.
- Author
-
Ali, Abdullah Marish, Ghaleb, Fuad A., Mohammed, Mohammed Sultan, Alsolami, Fawaz Jaber, and Khan, Asif Irshad
- Subjects
CONVOLUTIONAL neural networks ,FAKE news ,DEEP learning ,COMMUNITIES ,ATTRIBUTION of news - Abstract
Today, fake news is a growing concern due to its devastating impacts on communities. The rise of social media, which many users consider the main source of news, has exacerbated this issue because individuals can easily disseminate fake news more quickly and inexpensive with fewer checks and filters than traditional news media. Numerous approaches have been explored to automate the detection and prevent the spread of fake news. However, achieving accurate detection requires addressing two crucial aspects: obtaining the representative features of effective news and designing an appropriate model. Most of the existing solutions rely solely on content-based features that are insufficient and overlapping. Moreover, most of the models used for classification are constructed with the concept of a dense features vector unsuitable for short news sentences. To address this problem, this study proposed a Web-Informed-Augmented Fake News Detection Model using Stacked Layers of Convolutional Neural Network and Deep Autoencoder called ICNN-AEN-DM. The augmented information is gathered from web searches from trusted sources to either support or reject the claims in the news content. Then staked layers of CNN with a deep autoencoder were constructed to train a probabilistic deep learning-base classifier. The probabilistic outputs of the stacked layers were used to train decision-making by staking multilayer perceptron (MLP) layers to the probabilistic deep learning layers. The results based on extensive experiments challenging datasets show that the proposed model performs better than the related work models. It achieves 26.6% and 8% improvement in detection accuracy and overall detection performance, respectively. Such achievements are promising for reducing the negative impacts of fake news on communities. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
9. IIMFCBM: Intelligent Integrated Model for Feature Extraction and Classification of Brain Tumors Using MRI Clinical Imaging Data in IoT-Healthcare.
- Author
-
Haq, Amin Ul, Li, Jian Ping, Agbley, Bless Lord Y, Khan, Asif, Khan, Inayat, Uddin, M. Irfan, and Khan, Shakir
- Subjects
FEATURE extraction ,BRAIN tumors ,MAGNETIC resonance imaging ,DIAGNOSTIC imaging ,SHORT-term memory ,DEEP learning - Abstract
Accurate classification of brain tumors is vital for detecting brain cancer in the Medical Internet of Things. Detecting brain cancer at its early stages is a tremendous medical problem, and many researchers have proposed various diagnostic systems; however, these systems still do not effectively detect brain cancer. To address this issue, we proposed an automatic diagnosing framework that will assist medical experts in diagnosing brain cancer and ensuring proper treatment. In developing the proposed integrated framework, we first integrated a Convolutional Neural Networks model to extract deep features from Magnetic resonance imaging. The extracted features are forwarded to a Long Short Term Memory model, which performs the final classification. Augmentation techniques were applied to increase the data size, thereby boosting the performance of our model. We used the hold-out Cross-validation technique for training and validating our method. In addition, we used various metrics to evaluate the proposed model. The results obtained from the experiments show that our model achieved higher performance than previous models. The proposed model is strongly recommended to be used to diagnose brain cancer in Medical Internet of Things healthcare systems due to its higher predictive outcomes. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
10. Deep Ensemble Fake News Detection Model Using Sequential Deep Learning Technique.
- Author
-
Ali, Abdullah Marish, Ghaleb, Fuad A., Al-Rimy, Bander Ali Saleh, Alsolami, Fawaz Jaber, and Khan, Asif Irshad
- Subjects
DEEP learning ,SEQUENTIAL learning ,FAKE news ,NATURAL language processing ,FEATURE extraction ,CONVOLUTIONAL neural networks - Abstract
Recently, fake news has been widely spread through the Internet due to the increased use of social media for communication. Fake news has become a significant concern due to its harmful impact on individual attitudes and the community's behavior. Researchers and social media service providers have commonly utilized artificial intelligence techniques in the recent few years to rein in fake news propagation. However, fake news detection is challenging due to the use of political language and the high linguistic similarities between real and fake news. In addition, most news sentences are short, therefore finding valuable representative features that machine learning classifiers can use to distinguish between fake and authentic news is difficult because both false and legitimate news have comparable language traits. Existing fake news solutions suffer from low detection performance due to improper representation and model design. This study aims at improving the detection accuracy by proposing a deep ensemble fake news detection model using the sequential deep learning technique. The proposed model was constructed in three phases. In the first phase, features were extracted from news contents, preprocessed using natural language processing techniques, enriched using n-gram, and represented using the term frequency–inverse term frequency technique. In the second phase, an ensemble model based on deep learning was constructed as follows. Multiple binary classifiers were trained using sequential deep learning networks to extract the representative hidden features that could accurately classify news types. In the third phase, a multi-class classifier was constructed based on multilayer perceptron (MLP) and trained using the features extracted from the aggregated outputs of the deep learning-based binary classifiers for final classification. The two popular and well-known datasets (LIAR and ISOT) were used with different classifiers to benchmark the proposed model. Compared with the state-of-the-art models, which use deep contextualized representation with convolutional neural network (CNN), the proposed model shows significant improvements (2.41%) in the overall performance in terms of the F1score for the LIAR dataset, which is more challenging than other datasets. Meanwhile, the proposed model achieves 100% accuracy with ISOT. The study demonstrates that traditional features extracted from news content with proper model design outperform the existing models that were constructed based on text embedding techniques. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
11. Computational Approach for Detection of Diabetes from Ocular Scans.
- Author
-
Khan, Asif Irshad, Kshirsagar, Pravin R., Manoharan, Hariprasath, Alsolami, Fawaz, Almalawi, Abdulmohsen, Abushark, Yoosef B., Alam, Mottahir, and Chamato, Fekadu Ashine
- Subjects
- *
DEEP learning , *MACHINE learning , *DIABETES , *DIABETIC retinopathy , *EYE examination , *RETINAL imaging - Abstract
The estimated 30 million children and adults are suffering with diabetes across the world. A person with diabetes can recognize several symptoms, and it can also be tested using retina image as diabetes also affects the human eye. The doctor is usually able to detect retinal changes quickly and can help prevent vision loss. Therefore, regular eye examinations are very important. Diabetes is a chronic disease that affects various parts of the human body including the retina. It can also be considered as major cause for blindness in developed countries. This paper deals with classification of retinal image into diabetes or not with the help of deep learning algorithms and architecture. Hence, deep learning is beneficial for classification of medical images specifically such a complex image of human retina. A large number of image data are considered throughout the project on which classification is performed by using binary classifier. On applying certain deep learning algorithms, model results into the training accuracy of 96.68% and validation accuracy of 66.82%. Diabetic retinopathy can be considered as an effective and efficient method for diabetes detection. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
12. Election Prediction on Twitter: A Systematic Mapping Study.
- Author
-
Khan, Asif, Zhang, Huaping, Boudjellal, Nada, Ahmad, Arshad, Shang, Jianyun, Dai, Lin, and Hayat, Bashir
- Subjects
SUPERVISED learning ,ELECTIONS ,SOCIAL media ,SOCIAL network analysis ,SENTIMENT analysis ,DEEP learning ,FORECASTING - Abstract
Context. Social media platforms such as Facebook and Twitter carry a big load of people's opinions about politics and leaders, which makes them a good source of information for researchers to exploit different tasks that include election predictions. Objective. Identify, categorize, and present a comprehensive overview of the approaches, techniques, and tools used in election predictions on Twitter. Method. Conducted a systematic mapping study (SMS) on election predictions on Twitter and provided empirical evidence for the work published between January 2010 and January 2021. Results. This research identified 787 studies related to election predictions on Twitter. 98 primary studies were selected after defining and implementing several inclusion/exclusion criteria. The results show that most of the studies implemented sentiment analysis (SA) followed by volume-based and social network analysis (SNA) approaches. The majority of the studies employed supervised learning techniques, subsequently, lexicon-based approach SA, volume-based, and unsupervised learning. Besides this, 18 types of dictionaries were identified. Elections of 28 countries were analyzed, mainly USA (28%) and Indian (25%) elections. Furthermore, the results revealed that 50% of the primary studies used English tweets. The demographic data showed that academic organizations and conference venues are the most active. Conclusion. The evolution of the work published in the past 11 years shows that most of the studies employed SA. The implementation of SNA techniques is lower as compared to SA. Appropriate political labelled datasets are not available, especially in languages other than English. Deep learning needs to be employed in this domain to get better predictions. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
13. A Medical Multimedia Real-Time Polyp Detection System using Low Computational Resources
- Author
-
Khan, Asif Qayyum
- Subjects
GI tract ,Deep Learning ,Image Classification ,Pill-cam ,Performance ,OpenCV ,Medical Multimedia ,LIRE ,Real-time ,Polyp Detection - Published
- 2017
14. Context pre-modeling: an empirical analysis for classification based user-centric context-aware predictive modeling.
- Author
-
Sarker, Iqbal H., Alqahtani, Hamed, Alsolami, Fawaz, Khan, Asif Irshad, Abushark, Yoosef B., and Siddiqui, Mohammad Khubeb
- Subjects
K-nearest neighbor classification ,PREDICTION models ,SUPPORT vector machines ,DECISION trees ,DEEP learning ,MACHINE learning - Abstract
Nowadays, machine learning classification techniques have been successfully used while building data-driven intelligent predictive systems in various application areas including smartphone apps. For an effective context-aware system, context pre-modeling is considered as a key issue and task, as the representation of contextual data directly influences the predictive models. This paper mainly explores the role of major context pre-modeling tasks, such as context vectorization by defining a good numerical measure through transformation and normalization, context generation and extraction by creating new brand principal components, context selection by taking into account a subset of original contexts according to their correlations, and eventually context evaluation, to build effective context-aware predictive models utilizing multi-dimensional contextual data. For creating models, various popular machine learning classification techniques such as decision tree, random forest, k-nearest neighbor, support vector machines, naive Bayes classifier, and deep learning by constructing a neural network of multiple hidden layers, are used in our study. Based on the context pre-modeling tasks and classification methods, we experimentally analyze user-centric smartphone usage behavioral activities utilizing their contextual datasets. The effectiveness of these machine learning context-aware models is examined by considering prediction accuracy, in terms of precision, recall, f-score, and ROC values, and has been made an empirical discussion in various dimensions within the scope of our study. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF
15. Oral epithelial cell segmentation from fluorescent multichannel cytology images using deep learning.
- Author
-
Sunny, Sumsum P, Khan, Asif Iqbal, Rangarajan, Madhavan, Hariharan, Aditi, N, Praveen Birur, Pandya, Hardik J, Shah, Nameeta, Kuriakose, Moni A, and Suresh, Amritha
- Subjects
- *
DEEP learning , *EPITHELIAL cells , *CYTOLOGY , *BLOOD cells , *CELL nuclei , *IMAGE analysis , *CELL imaging - Abstract
• Automated oral cytology-based assays mandate single epithelial cell segmentation. • Presence of debris, blood cells, and cell clusters form the major challenge. • Two-step method proposed for diagnosis; semantic segmentation and classification. • Multichannel, fluorescent-labeled microscopic cell images were used. • Modified U-Net provided high accuracy for segmentation (IoU:0.79). • New CNN model, artefact-net classified the segmented cells with a high F1 score (0.91). Cytology is a proven, minimally-invasive cancer screening and surveillance strategy. Given the high incidence of oral cancer globally, there is a need to develop a point-of-care, automated, cytology-based screening tool. Oral cytology image analysis has multiple challenges such as, presence of debris, blood cells, artefacts, and clustered cells, which necessitate a skilled expertise for single-cell detection of atypical cells for diagnosis. The main objective of this study is to develop a semantic segmentation model for Single Epithelial Cell (SEC) separation from fluorescent, multichannel, microscopic oral cytology images and classify the segmented images. We have used multi-channel, fluorescent, microscopic images (number of images; n = 2730), which were stained differentially for cytoplasm and nucleus. The cytoplasmic and cell membrane markers used in the study were Mackia Amurensis Agglutinin (MAA; n: 2364) and Sambucus Nigra Agglutinin-1 (SNA-1; n: 366) with a nuclear stain DAPI. The cytology images were labelled for SECs, cluster of cells, artefacts, and blood cells. In this study, we used encoder-decoder models based on the well-established U-Net architecture, modified U-Net and ResNet-34 for multi-class segmentation. The experiments were performed with different class combinations of data to reduce imbalance. The derived MAA dataset (n: 14,706) of SEC, cluster, and artefacts/blood cells were used for developing a classification model. InceptionV3 model and a new custom Convolutional-Neural-Network (CNN) model (Artefact-Net) were trained to classify SNA-1 marker stained segmented images (n:6101). For segmentation models, Intersection Over Union (IoU) and F1 score were used as the evaluation matrices, while the classification models were evaluated using the conventional classification metrics like precision, recall and F1-Score. The U-Net and the modified U-Net models gave the best IoU overall (0.73–0.76) as well as for SEC segmentation (079). The images segmented using the modified U-Net model were classified by Artefact-Net and Inception V3 model with F1 scores of 0.96 and 0.95 respectively. The Artefact-Net, when compared to InceptionV3, provided a better precision and F1 score in classifying clusters (Precision: 0.91 vs 0.80; F1: 0.91 vs 0.86). This study establishes a pipeline for SEC segmentation with the segmented component containing only single cells. The pipline will enable automated, cytology-based early detection with reduced bias. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
16. Recycling waste classification using emperor penguin optimizer with deep learning model for bioenergy production.
- Author
-
Khan, Asif Irshad, Almalaise Alghamdi, Abdullah S., Abushark, Yoosef B., Alsolami, Fawaz, Almalawi, Abdulmohsen, and Marish Ali, Abdullah
- Subjects
- *
WASTE recycling , *DEEP learning , *RENEWABLE energy sources , *WASTE products , *CONVOLUTIONAL neural networks - Abstract
The growth and implementation of biofuels and bioenergy conversion technologies play an important part in the production of sustainable and renewable energy resources in the upcoming years. Recycling sources from waste could efficiently ease the risk of world source strain. The waste classification was a good resolution for separating the waste from the recycled objects. It is inefficient and expensive to rely solely on manual classification of garbage and recycling sources. Convolutional neural networks (CNNs) have lately been used to classify recyclable waste, and this is the primary way for recycling the waste. This study presents a recycling waste classification using emperor penguin optimizer with deep learning (RWC-EPODL) model for bioenergy production. RWC-EPODL model focuses on recycling waste materials recognition and classification. When it comes to detecting and classifying trash, the RWC-EPODL model uses two stages. At the initial stage, the RWC-EPODL model uses AX-RetinaNet model for the recognition of waste objects. In addition, Bayesian optimization (BO) algorithm is applied as hyperparameter optimizer of the AX-RetinaNet model. Following the EPO algorithm with a stacked auto-encoder (SAE) model, the EPO algorithm is used to fine-tune the parameters of the SAE technique for trash classification. The RWC-EPODL model's experimental validation is examined through a number of studies. The RWC-EPODL approach has a 98.96 percent success rate. The comparative result analysis reported the better performance of the RWC-EPODL model over recent approaches. [Display omitted] • Novel recycling waste classification using emperor penguin optimizer with deep learning (RWC-EPODL) for bioenergy production • The presented RWC-EPODL model majorly focuses on the recognition and classification of recycling waste materials. • The proposed RWC-EPODL model uses AX-RetinaNet model for the recognition of waste objects. • The proposed model employs the EPO algorithm with stacked auto-encoder (SAE) model for waste classification. • To demonstrate the improved outcomes of the RWC-EPODL model, a series of experiments has been conducted to test the model. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
17. Modeling of Remora Optimization with Deep Learning Enabled Heavy Metal Sorption Efficiency Prediction onto Biochar.
- Author
-
Almalawi, Abdulmohsen, Khan, Asif Irshad, Alqurashi, Fahad, Abushark, Yoosef B., Alam, Md Mottahir, and Qaiyum, Sana
- Subjects
- *
DEEP learning , *HEAVY metals , *SORPTION , *SORPTION techniques , *PRECIPITATION (Chemistry) , *BIOCHAR , *WATER filtration , *ION-permeable membranes - Abstract
Environmental distresses linked to heavy metal (HM) impurity in the water received significant attention among research communities. Recently, advancements in industrial sectors like paper industries, mining, non-ferrous metallurgy, electroplating, mineral paint production, etc. have resulted in massive heavy metals in wastewater. In contrast to organic pollutants, HMs are not recyclable and can be simply engrossed by living organisms. Recently, different solutions have been employed for removing HMs from water and wastewater, like membrane filtration, chemical precipitation, adsorption, ion-exchange, flotation, flocculation, etc. Sorption can be considered one of the efficient solutions for eradicating HMs from waste water. With this motivation, this article concentrates on the design of Remora Optimization with Deep Learning Enabled Heavy Metal Sorption Efficiency Prediction (RODL-HMSEP) model onto Biochar. The proposed RODL-HMSEP technique intends to determine the sorption performance of HMs of various biochar features. Initially, the density based clustering (DBSCAN) technique is applied to simulating the features of metal adsorption data and splitting them into clusters of identical features. Besides, deep belief network (DBN) model was employed for prediction and the efficiency of the DBN model is optimally adjusted with utilize of RO technique. The experimental validation of the RODL-HMSEP technique ensured the promising performance of the RODL-HMSEP technique on the prediction of sorption efficiency onto biochar over other methods The experimental validation of the RODL-HMSEP technique ensured the promising performance of the RODL-HMSEP technique on the prediction of sorption efficiency onto biochar over other methods. [Display omitted] • Remora Optimization with Deep Learning Enabled Heavy Metal Sorption Efficiency Prediction (RODL-HMSEP) model onto Biochar. • RODL-HMSEP technique aims for predicting the sorption performance of HMs of various biochar features. • The RODL-HMSEP model uses density-based clustering (DBSCAN) technique for simulating the features of metal adsorption data. • Deep belief network (DBN) model performs the next phase of data clustering. • RODL-HMSEP technique ensured promising performance on the prediction of sorption efficiency onto biochar over other methods. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
18. Arithmetic optimization algorithm with deep learning enabled airborne particle-bound metals size prediction model.
- Author
-
Almalawi, Abdulmohsen, Khan, Asif Irshad, Alsolami, Fawaz, Alkhathlan, Ali, Fahad, Adil, Irshad, Kashif, Alfakeeh, Ahmed S., and Qaiyum, Sana
- Subjects
- *
DEEP learning , *MATHEMATICAL optimization , *MACHINE learning , *PREDICTION models , *HEAVY metal toxicology , *ARITHMETIC , *HEAVY metals - Abstract
Recently, heavy metal air pollution has received significant interest in computing the total concentration of every toxic metal. Chemical fractionation of possibly toxic substances in airborne particles becomes a vital element. Among the primary and secondary air pollutants, airborne particulate matter (APM) received considerable internet among research communities owing to the adversative impact on human health. Hence, size distribution details of airborne heavy metals are important in assessing the adverse health effects over the globe. Recently, deep learning models have gained significant interest over the mathematical and statistical prediction models. In this view, this paper presents a novel arithmetic optimization algorithm (AOA) with multi-head attention based bidirectional long short-term memory (MABLSTM) model for predicting the size fractionated airborne particle bound metals. The proposed AOA-MABLSTM technique focuses on the forecasting of the size-fractionated airborne particle bound matter. The presented model intends to examine the concentration of PM and distinct sized-fractionated APM. The proposed model establishes MABLSTM based accurate predictive approaches for atmospheric heavy 83 metals is used for determining temporal trend of heavy metal. The proposed model employs AOA based hyperparameter tuning process to optimally tune the hyperparameters included in the MABLSTM method. To demonstrate the improved outcomes of the AOA-MABLSTM approach, a comparison study is performed with recent models. The stimulation results emphasized the betterment of the presented model over the other methods. Aluminum metal had an RMSE of 73.200 for AOA-MABLSTM. On Cu metal, the AOA-MABLSTM approach had an RMSE of 6.747. On Zn metal, the AOA-MABLSTM system lowered the RMSE by 45.250. [Display omitted] • A novel arithmetic optimization algorithm (AOA) with multi-head attention based bidirectional long short-term memory (MABLSTM) method. • The presented model intends to examine the concentration of PM and distinct sized-fractionated APM. • The proposed model establishes MABLSTM based accurate predictive approaches for atmospheric heavy 83 metals. • The proposed model employs AOA based hyperparameter tuning process to tune the hyperparameter included in the MABLSTM model. • To demonstrate the improved outcomes of the AOA-MABLSTM approach, a comparison study is performed with recent models. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
19. Deep diagnosis: A real-time apple leaf disease detection system based on deep learning.
- Author
-
Khan, Asif Iqbal, Quadri, S.M.K., Banday, Saba, and Latief Shah, Junaid
- Subjects
- *
DEEP learning , *EARLY diagnosis , *APPLE growers , *SYMPTOMS , *DIAGNOSIS , *ORCHARDS - Abstract
• A suitable size expert-annotated apple leaf disease dataset has been prepared. • Presented a two-stage apple disease detection system based on Xception and Faster-RCNN. • Used a transfer learning method to initialize model by weight parameters learned on large-scale datasets. • Achieved an overall 88% of classification accuracy and our best detection model achieved mAP of 42%. • Promising results indicate that this system can be very helpful for farmers and Apple growers. Diseases and pests are one of the major reasons for low productivity of apples which in turn results in huge economic loss to the apple industry every year. Early detection of apple diseases can help in controlling the spread of infections and ensure better productivity. However, early diagnosis and identification of diseases is challenging due to many factors like, presence of multiple symptoms on same leaf, non-homogeneous background, differences in leaf colour due to age of infected cells, varying disease spot sizes etc. In this study, we first constructed an expert-annotated apple disease dataset of suitable size consisting around 9000 high quality RGB images covering all the main foliar diseases and symptoms. Next, we propose a deep learning based apple disease detection system which can efficiently and accurately identify the symptoms. The proposed system works in two stages, first stage is a tailor-made light weight classification model which classifies the input images into diseased, healthy or damaged categories and the second stage (detection stage) processing starts only if any disease is detected in first stage. Detection stage performs the actual detection and localization of each symptom from diseased leaf images. The proposed approach obtained encouraging results, reaching around 88% of classification accuracy and our best detection model achieved mAP of 42%. The preliminary results of this study look promising even on small or tiny spots. The qualitative results validate that the proposed system is effective in detecting various types of apple diseases and can be used as a practical tool by farmers and apple growers to aid them in diagnosis, quantification and follow-up of infections. Furthermore, in future, the work can be extended to other fruits and vegetables as well. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
20. Autonomous assessment of delamination in laminated composites using deep learning and data augmentation.
- Author
-
Khan, Asif, Raouf, Izaz, Noh, Yeong Rim, Lee, Daun, Sohn, Jung Woo, and Kim, Heung Soo
- Subjects
- *
DEEP learning , *LAMINATED materials , *DATA augmentation , *VIBRATION tests , *FAULT diagnosis , *SYSTEM identification - Abstract
• Limited faulty data from different health states hinder the autonomous fault diagnosis via deep learning. • The inverse approach of system identification is employed to synthetically augment limited experimental data without the need for additional experiments. • Synthetic data generation bring out additional information about the system, and deep learning models can learn more robustly from the augmented data. • The comparison of deep learning and transfer learning results on the originally measured and augmented data show that data augmentation resulted in a more robust and rigorous autonomous delamination diagnosis framework for laminated composites. Deep learning models can autonomously learn discriminative features from the data; however, insufficient training data often limit their use. This paper proposes a synthetic data augmentation strategy to alleviate the issue of limited data and employ deep learning models for the autonomous assessment of delamination in laminated composites. Contrary to the existing techniques of image data augmentation (rotation, cropping) and time-series data augmentation (adding noise, windowing), the proposed approach brings out additional information during data augmentation through the variation of loading conditions without the need for further experiments. The approach was thoroughly validated and verified in time and frequency domains using various types of experimental vibration testing. The experimentally measured data of 45-time series was augmented to 4,545-time series, resulting in a more rigorous delamination assessment in laminated composites. The proposed approach is autonomous and does not require human-engineered statistical features while using a small amount of measured data. In addition, the approach would assist in tackling the issue of imbalanced data from the healthy and faulty states of laminated composite. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
21. Damage Detection and Isolation from Limited Experimental Data Using Simple Simulations and Knowledge Transfer.
- Author
-
Khan, Asif, Kim, Jun-Sik, and Kim, Heung Soo
- Subjects
- *
DEEP learning , *FAULT diagnosis , *MACHINE learning , *KNOWLEDGE transfer , *FEATURE extraction , *HEALTH behavior , *LEARNING strategies - Abstract
A simulation model can provide insight into the characteristic behaviors of different health states of an actual system; however, such a simulation cannot account for all complexities in the system. This work proposes a transfer learning strategy that employs simple computer simulations for fault diagnosis in an actual system. A simple shaft-disk system was used to generate a substantial set of source data for three health states of a rotor system, and that data was used to train, validate, and test a customized deep neural network. The deep learning model, pretrained on simulation data, was used as a domain and class invariant generalized feature extractor, and the extracted features were processed with traditional machine learning algorithms. The experimental data sets of an RK4 rotor kit and a machinery fault simulator (MFS) were employed to assess the effectiveness of the proposed approach. The proposed method was also validated by comparing its performance with the pre-existing deep learning models of GoogleNet, VGG16, ResNet18, AlexNet, and SqueezeNet in terms of feature extraction, generalizability, computational cost, and size and parameters of the networks. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
22. Autonomous Assessment of Delamination Using Scarce Raw Structural Vibration and Transfer Learning.
- Author
-
Khan, Asif, Khalid, Salman, Raouf, Izaz, Sohn, Jung-Woo, and Kim, Heung-Soo
- Subjects
- *
STRUCTURAL dynamics , *DEEP learning , *LAMINATED material testing , *LAMINATED materials , *SUPPORT vector machines , *MACHINE learning - Abstract
Deep learning has helped achieve breakthroughs in a variety of applications; however, the lack of data from faulty states hinders the development of effective and robust diagnostic strategies using deep learning models. This work introduces a transfer learning framework for the autonomous detection, isolation, and quantification of delamination in laminated composites based on scarce low-frequency structural vibration data. Limited response data from an electromechanically coupled simulation model and from experimental testing of laminated composite coupons were encoded into high-resolution time-frequency images using SynchroExtracting Transforms (SETs). The simulated and experimental data were processed through different layers of pretrained deep learning models based on AlexNet, GoogleNet, SqueezeNet, ResNet-18, and VGG-16 to extract low- and high-level autonomous features. The support vector machine (SVM) machine learning algorithm was employed to assess how the identified autonomous features were able to assist in the detection, isolation, and quantification of delamination in laminated composites. The results obtained using these autonomous features were also compared with those obtained using handcrafted statistical features. The obtained results are encouraging and provide a new direction that will allow us to progress in the autonomous damage assessment of laminated composites despite being limited to using raw scarce structural vibration data. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
23. Synthetic Data Augmentation and Deep Learning for the Fault Diagnosis of Rotating Machines.
- Author
-
Khan, Asif, Hwang, Hyunho, and Kim, Heung Soo
- Subjects
- *
DATA augmentation , *DEEP learning , *FAULT diagnosis , *MACHINERY , *ELECTRONIC data processing - Abstract
As failures in rotating machines can have serious implications, the timely detection and diagnosis of faults in these machines is imperative for their smooth and safe operation. Although deep learning offers the advantage of autonomously learning the fault characteristics from the data, the data scarcity from different health states often limits its applicability to only binary classification (healthy or faulty). This work proposes synthetic data augmentation through virtual sensors for the deep learning-based fault diagnosis of a rotating machine with 42 different classes. The original and augmented data were processed in a transfer learning framework and through a deep learning model from scratch. The two-dimensional visualization of the feature space from the original and augmented data showed that the latter's data clusters are more distinct than the former's. The proposed data augmentation showed a 6–15% improvement in training accuracy, a 44–49% improvement in validation accuracy, an 86–98% decline in training loss, and a 91–98% decline in validation loss. The improved generalization through data augmentation was verified by a 39–58% improvement in the test accuracy. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
24. CoroNet: A deep neural network for detection and diagnosis of COVID-19 from chest x-ray images.
- Author
-
Khan, Asif Iqbal, Shah, Junaid Latief, and Bhat, Mohammad Mudasir
- Subjects
- *
COVID-19 , *CONVOLUTIONAL neural networks , *X-ray imaging , *SARS-CoV-2 , *COVID-19 pandemic , *PANDEMICS - Abstract
• Classification of Normal, Pneumonia-bacterial, Pneumonia-viral and Covid-19 chest x-ray images. • Presented a deep convolutional neural network model based on Xception architecture. • Used a transfer learning method to initialize model by weight parameters learned on large-scale datasets. • Trained the model on a dataset prepared by collecting x-ray images from publically available databases. • Achieved an overall accuracy of 89.6% and precision and recall rate for Covid-19 cases are 93% and 98.2%. The results obtained by our proposed model are superior compared to other studies in the literature. • Promising results indicate that this model can be very helpful to doctors around the world in their fight against Covid-19 Pandemic. The novel Coronavirus also called COVID-19 originated in Wuhan, China in December 2019 and has now spread across the world. It has so far infected around 1.8 million people and claimed approximately 114,698 lives overall. As the number of cases are rapidly increasing, most of the countries are facing shortage of testing kits and resources. The limited quantity of testing kits and increasing number of daily cases encouraged us to come up with a Deep Learning model that can aid radiologists and clinicians in detecting COVID-19 cases using chest X-rays. In this study, we propose CoroNet, a Deep Convolutional Neural Network model to automatically detect COVID-19 infection from chest X-ray images. The proposed model is based on Xception architecture pre-trained on ImageNet dataset and trained end-to-end on a dataset prepared by collecting COVID-19 and other chest pneumonia X-ray images from two different publically available databases. CoroNet has been trained and tested on the prepared dataset and the experimental results show that our proposed model achieved an overall accuracy of 89.6%, and more importantly the precision and recall rate for COVID-19 cases are 93% and 98.2% for 4-class cases (COVID vs Pneumonia bacterial vs pneumonia viral vs normal). For 3-class classification (COVID vs Pneumonia vs normal), the proposed model produced a classification accuracy of 95%. The preliminary results of this study look promising which can be further improved as more training data becomes available. CoroNet achieved promising results on a small prepared dataset which indicates that given more data, the proposed model can achieve better results with minimum pre-processing of data. Overall, the proposed model substantially advances the current radiology based methodology and during COVID-19 pandemic, it can be very helpful tool for clinical practitioners and radiologists to aid them in diagnosis, quantification and follow-up of COVID-19 cases. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF
25. A Deep Learning Framework for Vibration-Based Assessment of Delamination in Smart Composite Laminates.
- Author
-
Khan, Asif, Shin, Jae Kyoung, Lim, Woo Cheol, Kim, Na Yeon, and Kim, Heung Soo
- Subjects
- *
DELAMINATION of composite materials , *LAMINATED materials , *ARTIFICIAL neural networks , *DEEP learning , *FAST Fourier transforms , *COMPOSITE materials , *MANUFACTURING defects - Abstract
Delamination is one of the detrimental defects in laminated composite materials that often arose due to manufacturing defects or in-service loadings (e.g., low/high velocity impacts). Most of the contemporary research efforts are dedicated to high-frequency guided wave and mode shape-based methods for the assessment (i.e., detection, quantification, localization) of delamination. This paper presents a deep learning framework for structural vibration-based assessment of delamination in smart composite laminates. A number of small-sized (4.5% of total area) inner and edge delaminations are simulated using an electromechanically coupled model of the piezo-bonded laminated composite. Healthy and delaminated structures are stimulated with random loads and the corresponding transient responses are transformed into spectrograms using optimal values of window size, overlapping rate, window type, and fast Fourier transform (FFT) resolution. A convolutional neural network (CNN) is designed to automatically extract discriminative features from the vibration-based spectrograms and use those to distinguish the intact and delaminated cases of the smart composite laminate. The proposed architecture of the convolutional neural network showed a training accuracy of 99.9%, validation accuracy of 97.1%, and test accuracy of 94.5% on an unseen data set. The testing confusion chart of the pre-trained convolutional neural network revealed interesting results regarding the severity and detectability for the in-plane and through the thickness scenarios of delamination. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.