Search

Early identification and accurate diagnosis are crucial for successful therapy and improved patient outcomes of brain tumors. The study looks at how deep learning may help detect brain tumors, including how convolutional neural networks (CNNs) can change the face of diagnostic imaging. This underscores the need of precise and timely identification of brain cancer for efficient therapy and enhanced patient results. The study discusses the challenges associated with tumor segmentation and classification, such as variations in size, shape, and location. To overcome these challenges, deep learning techniques are utilized to analyze brain scans and identify tumor abnormalities. However, the paper underscores the importance of these models serving as tools to assist medical professionals rather than replacing their expertise. Additionally, the paper presents a comparative study that evaluates different techniques, artificial neural networks (ANN) achieve the highest accuracy at 99%, followed by Support Vector Machine (SVM) at 98.9%. vision transformer (ViT), Extreme Gradient Boosting (XG Boost), CNN-based dense Efficient Net, and Deep Neural Network (DNN) also show high accuracies above 98%. However, U-Net, Alex Net, hybrid ensemble method (Random Forest (RF), K-Nearest Neighbour (KNN), Decision Tree (DT), and Region-based convolutional neural networks (R-CNN)) have lower accuracies ranging from 91.66% to 97.305%. Overall, the findings highlight the potential of deep learning in enhancing the efficiency, precision of brain tumor diagnosis, leads to earlier treatment and enhanced patient prognosis. [ABSTRACT FROM AUTHOR]

At present, detection and recognition of animals remain a complicated task and no distinctive technique can solve all situations strongly and effectively. Animal detection in images is challenging because of the complexity of wild environments. Including several different things: The large differences in shapes and color appearances of variations of objects which belong to the same class, and Lighting/Illumination Conditions. This paper presents an effective and efficient animal detection system for Birds detection in images. MobileNet SSD model is a Single Shot Multibox Detection (SSD) suggested in this work, which is capable of handling different shapes and view angles of the objects. This approach allows extracting features of image regions and using deep learning techniques for classifying regions into two categories: (bird and non-animal). The experimental results demonstrated the efficiency of classification and detection of single and multi-animals even in difficult environmental conditions. The accuracy of detection and classification is up to 98.8%. This methodology is more accurate than other similar approaches. This paper exhibits a method for training a convolutional neural network (CNN) based on object detection classifiers. [ABSTRACT FROM AUTHOR]

The rise of cyber-attacks such as Distributed Denial of Service (DDoS) and SQL injection has become a significant concern for organizations and individuals who rely on the internet. Traditional detection methods have become increasingly ineffective in addressing these challenges, necessitating the development of new and innovative solutions. This paper proposes using Convolutional Neural Networks (CNNs) to detect DDoS and SQL injection attacks. Our paper proposes a Convolutional Neural Network model with a multi-layer neural and relu activation function optimizer that reaches a higher degree of precision than previous Deep Learning models. In this study, we tested the relatively new dataset CIC-IDS-2018, which contains different types of attacks. With this dataset, our model achieves an unprecedented accuracy of>96%, minimizing computational time. [ABSTRACT FROM AUTHOR]

Natural disasters cause devastation, chaos, destruction, death, displacement, and much more when they occur. With the advancement of recent technologies especially in artificial intelligence and deep learning, the severity and impact of natural disasters could be reduced by predicting their occurrence. In this research, the flood detection (using images) system is developed using the proposed architecture of the Deep Convolutional Neural Network (CNN). In this paper, the main aim is to propose an automated System for precision disaster detection, in particular flood detection. The intelligent system will monitor vast problematic areas that are dubbed flood risk areas during the season. The intelligent automated system will systematically take images with real-time processing to detect floods. If a flood is detected, the system will automatically communicate to the ground station with the early warning to issue an early warning to all the inhabitants in the path of the flood. Since this paper will prove a concept, the other main contribution of this paper is a new dataset consisting of 9000 images collected from various sources on the Internet, labeled, and preprocessed. The Deep CNN architectures were trained and tested by constructing a new dataset of more than 9000 labeled images with flood and non-flood collected from different sources. Several experiments are performed with changing CNN architectural design parameters in order to get the best recognition rates. Experimental results show that 92.50% accuracy was achieved using GoogleNet. The second highest performance was achieved using AlexNet with an accuracy of 92.20%. [ABSTRACT FROM AUTHOR]

The Dubas bug (Db) is a deadly pest that affects palm and agricultural crops; however, early automatic identification of frond diseases of this type can thus help reduce human effort and reduce economic losses. Traditional methods of detection rely on human vision and hands to spot and categorise the palms affected, while more recent research has begun applying deep learning networks due to their effectiveness in classification tasks. This paper presents a strategy of automatic recognition of Dubas blight based on identification of diseased palms. Data was collected in natural climatic conditions using a drone camera and several pre-processing steps were applied. In particular, pre-sets were created by slicing the images into small parts and using Lifting Wavelet transformations (LWT) to shrink the data in size; this was then used to train a convolutional neural network (CNN) with the assistance of pre-trained Xception, InceptionV3, DenseNet121, and ResNet101 models with different parameters. Dropout and data augmentation was used to avoid overfitting, and the highest classification accuracy was determined to be that offered by the Xception model, with experimental results suggesting that this developed more than 99% accuracy. [ABSTRACT FROM AUTHOR]

This paper investigates the most commonly used Deep Learning (DL) based techniques for estimating the wireless channel at the User Equipment (UE). The generalized Nakagami-m fading distribution is considered for deep learning network. The motive of this work is to provide an experimental investigation on the wireless channels using three different deep-feed forward neural networks, namely Artificial Neural Networks (ANN), Long Short Term Memory (LSTM), and Convolution Neural Networks (CNN). The analysis includes the preprocessing approach for handling complex received signals as one of the inputs and actual channel coefficients as output. Bit Error Rate (BER) performance analysis is performed and is compared with the classical LS estimator. It is demonstrated that DL channel estimation outperforms the Least Square (LS) based estimation, and simulation results support that DL-based channel estimation is very efficient. [ABSTRACT FROM AUTHOR]

Sign language is a crucial mode of communication for individuals who are deaf or hard-of-hearing, and a reliable sign language recognition system can greatly aid in bridging the communication gap. According to statistics provided by the Government of India, there are only around 250 accredited sign language interpreters in India, servicing a deaf population of 1.8 million to 7 million individuals. This paper presents a real-time sign language recognition system for Indian Sign Language (ISL) using YOLOv8 for object detection. The system uses a single convolutional neural network (CNN) architecture to process the entire image in one forward pass and predict the bounding boxes and class probabilities for each sign in the image. The results of the study demonstrate the feasibility and potential of the system in revolutionizing communication for the deaf and hard of hearing community and have applications in gesture-controlled robotics, home automation, game control, human-computer interaction, and sign language interpretation. [ABSTRACT FROM AUTHOR]

Tampered Medical images and scans are a very serious issue in the medical field. The results of tampered scans can range from mild to serious results. For example, a tampered scan or medical image can lead to misdiagnosing a patient with a serious condition or a patient who suffers from a serious condition can be misdiagnosed as healthy leading to a delay in receiving proper treatment. In this paper, we propose a deep learning-based methodology to detect tampered/fake cancers in 3D CT scans of human lungs. We use a publicly available dataset of deepfakes that include both tampered and genuine cancers and propose the use of a modified Convolutional Neural Network (CNN), in particular the AlexNet with Transfer Learning. The model was pre-trained on a large dataset and fine-tuned on the medical images dataset to detect tampering. Experimental results achieve a high level of accuracy in detecting tampering. Using the AlexNet with Transfer learning, we achieved an accuracy of 89.47%, Recall of 89.47%, Precision of 89.47%, and F1 measure of 89.47%. This is higher accuracy than similar methods using the same dataset reported in the extant literature. Achieving this high accuracy for a multiclass complex problem is considered an excellent achievement. Expert radiologists are mostly unable to distinguish between real and tampered cancer images. The results demonstrate the potential for deep learning-based models in improving accuracy and efficiency in tampered medical scan detection. [ABSTRACT FROM AUTHOR]

Due to the fast spread of the new Coronavirus called SARS-CoV-2 (otherwise known as COVID-19 virus) worldwide and its continuous mutations, such large viral outbreaks require early elucidation to determine the genetic sequence of the virus to design an effective system for identifying variants Different known and unknown virus. Identifying specific variables facilitates the comprehension and modelling of viral propagation patterns to treat and manage outbreaks, create efficient reduction techniques, and avoid future outbreaks. In addition, it serves a vital role in assessing the efficiency of known vaccines against each variation and modelling the probability of superinfection. It is known that the genomic sequence carries the vast majority of genetic information pertaining to variations and variants of the Coronavirus. This paper proposes a system that depends on deep learning to predict the mutations of complete COVID-19 virus genomes based on the Convolutional Neural Network (CNN) algorithm as an alignment-free method. The k-mer technology is applied to fragment the DNA of coronavirus mutants to create a unique vocabulary. The proposed approach can correctly predict and characterize other coronavirus strains, such as MERS-CoV, Alpha-CoV, SARS-CoV-2, SARS-CoV, Gamma, Beta, and other strains, regardless of missing information and sequencing errors with an accuracy rate of 99% on the data set. [ABSTRACT FROM AUTHOR]

After a deep questioner among students, faculty members and higher education experts. The demand for qualified engineers in the specific field as understandably gone down. The situation is grimmer for tier-2 and tier-3 colleges in India. The purpose of opting engineering course is not to get expertise in the particular course, instead to get a job in government sector with valid degree. The problem identified in the field of engineering education towards improving the quality in education is addressed with the help of exploratory data analysis. The dataset used in our experiment is collect from UCI machine Learning Repository having 33 variables and 1044 observations. The contribution made in the paper is to identify the vital attributes using single and multi-variant regression techniques. To perform prediction using Decision Tree, Random Forest, Support vector Machine and compare their performance in terms of classification accuracy and F-Score. In addition to that a convolution Neural Network (CNN) model is established in which, the vital attributes identified using regression techniques are provided as inputs and weights at each stage is estimated using Gradient Decent algorithm with step size 0.5. The classification accuracy from 63% is improved to 97% with the help of CNN model in 26664 iterations. The finding of the present research states that student having backlogs are less frequently opting for higher studies. [ABSTRACT FROM AUTHOR]

Aim: The main aim of this paper is to recognize mango leaf disease using convolutional neural networks in google co-laboratory. Materials and Methods: A dataset of 120 photographs of diseased and normal mango leaves was used to distinguish mango leaves using the CNN technique which is based on a deep learning algorithm. Results: The proposed 5D CNN model has a 98.67 % accuracy and 2D CNN has a 89.05% accuracy in leaf disease classification, so the novel 5D Convolution Neural Network algorithm appears to be better than 2D CNN standard deviation is 1. Conclusion: In mango leaf disease detection, the proposed novel 5D Convolution Neural Network based leaf disease recognition model shows less training time and high training accuracy. This demonstrates the adaptability of CNN models in real-time implementations. [ABSTRACT FROM AUTHOR]

The scope of the paper is to leverage the power of Machine Learning and Deep Learning to detect diseases in crops and to provide solutions for the diseases detected. Farmers usually detect diseases in the crops using their naked eyes, eventually leading them to make wrong predictions regarding diseases in the crops. They might use the wrong fertilizers or more than the usual dose, which could damage the plants, soil, and fields. Thus, this paper focuses on providing solutions for detecting diseases in crops and solutions for the diseases identified. Convolutional Neural Networks are used to identify various diseases in crops since it limits the number of parameters and thereby make the model more efficient. The said model is implemented by making a cross-platform code using Flutter with Dart as the programming language. [ABSTRACT FROM AUTHOR]

This paper mostly focuses on real-time detection and classification of biomedical waste objects. Traditional methods for detecting the objects like biomedical waste objects in machine learning are substituted by recent technology of object detection methods in deep learning by building Convolutional Neural Network (CNN) which is nothing but the components of deep learning. This paper proposes a deep learning approach for object detection of biomedical waste material by evaluating the TensorFlow object detection API, which can used for real time application, this biomedical object detection API further we can used for automate the biomedical waste segregation system, this proposed system has been trained using more than 500 images for each type of biomedical waste object. Tensorflow is useful and easy to object detection that can form powerful image recognition software, in this proposed work we are using Faster R-CNN algorithm for developing this object detection process. [ABSTRACT FROM AUTHOR]

The importance of medicinal plants has widely increased throughout the world, especially during the COVID-19 pandemic. It is essential for a layman to identify a medicinal plant and know about its medicinal values. In this view, this paper proposes an approach that helps a person to identify the medicinal values of different plants. The paper focuses on designing a mobile application that can identify the leaf and list its medicinal values with a mere snapshot of it by performing instance segmentation, feature extraction and classification in the backend. The models were trained and tested on a custom dataset generated by collecting around 1500 images spreading over 5 medicinal plant species. The paper uses a deep learning-based segmentation approach for real-time segmentation of the leaf from the complex natural background. The segmented leaf will undergo a feature extraction process and will be given as an input to the traditional Machine Learning algorithms. Manual Feature Extraction and Deep Learning based Feature extraction processes were implemented. Various features including shape, colour and texture were extracted in the manual feature extraction process and a MobileNet pre-trained model was used for deep learning-based feature extraction. The Mask Region-based Convolutional Neural Network (Mask R-CNN) yielded the best performance for real-time segmentation with a Dice score of 0.92 and for the classification MobileNet + Logistic Regression gave the best accuracy of 0.97 and AUC score of 0.99. [ABSTRACT FROM AUTHOR]

The paper proposed an automatic image annotation (AIA) model that is assigned method semantic labels to the new image automatically. It is also proposed a scheme for implementation an AIA-system based on deep learning method by using a Convolutional Neural Network (CNN) model that raw dataset (Corel-5K, ESP Game, IAPR TC-12, NUSWIDE, and MS-COCO). The photos are recorded and accessible for searching, categorization, and retrieval purposes. These photographs must be tagged with appropriate words, phrases, or keywords in order for the required action to be conducted properly. These operations are facing challenges in assigning labels to an image which is in form of keyword tagging or a very short description of the image, that lead to speed up the image's retriever so that the aims of paper are to develop a multilayered tagging model that has common interaction layer by using deep learning method, CNN-RNN model. Although Back Propagation Through Time (BPTT) adjusts the weights of the neural network, and the model is used it to increase the quality of retrieved images that have a high level of relative keywords. In addition, it is a supervised learning algorithm that allows the network to be corrected concerning the errors that have occurred. Finally, the proposed model implemented by Python 3.7 because it has useful models and is change some parts to enhance the results of this paper. [ABSTRACT FROM AUTHOR]

State-of-the-art solutions in the areas of language modelling, generating text, speech recognition, generating image descriptions or video tagging, have been using Recurrent Neural Networks as the foundation for their approaches. Understanding the underlying concepts is therefore of tremendous importance if we want to investigate frontier methods and develop new approaches for building smart digital solutions. This paper proposes a smart city control system architecture based on deep convolutional neural networks. The control system has a multilayer architecture that combines loosely coupled intelligent components. As the main layer, a solution based on deep learning technology is applied, which allows solving several tasks simultaneously: segmentation, detection and classification of images received from surveillance cameras of the smart city system. The data obtained at the output of this layer is used for further analysis and decision-making in the smart city system. The proposed architecture has a high degree of modularity and allows the replacement of individual elements in a loosely coupled architecture. In this paper, deep learning and computer vision technologies are also considered, on the basis of which the image processing layer from video cameras is implemented. A masked recurrent neural network is used for this task. [ABSTRACT FROM AUTHOR]

Chronic liver disease (CLD) is a general term that refers to a number of different hepatic disease processes that consume a significant amount of healthcare and financial resources worldwide. Cirrhosis develops when CLD progresses to permanent end-stage liver fibrosis. For the course and prognosis of liver fibrosis, early detection and intervention are crucial. Ultrasound provides a variety of advantages as one of the most commonly utilized methods for detecting liver fibers, including ease, accuracy, and resilience. However, getting subjective and consistent diagnoses is challenging since ultrasound images are inevitably influenced by device characteristics, ultrasound interactions with body tissues, operation procedures, and other uncontrollable elements. The goal of paper is to develop a new proposed liver fibrosis detection model for ultrasound shear wave elastography (SWE) images using deep learning algorithm to distinguish between normal and fibrosis tissue. This paper provides a convolutional neural network-based deep learning feature extraction algorithm for binary classification and detection of liver fibrosis. The dataset used to develop these models was locally collected from an Iraqi hospital. The results obtained revealed that the final model (CNN) was able to classify normal and abnormal liver tissue from SWE with an accuracy of 97.45%, Sensitivity 98.27%, Specificity 96.66%, Precision 96.61% and F1-score of 97.17%. This is accurate results for assist diagnosis liver fibrosis. [ABSTRACT FROM AUTHOR]

Cancer is one of the most dangerous diseases which is the cause of death of around half a million people every year. Research scientists and doctors are still finding methods to avoid these casualties. Brain tumor and Liver lesions are among the most fatal cancers and early detection of these diseases can help in reducing large human loss every year. Various methods are used for early detection of brain tumor and liver lesion from medical images using computer vision and image processing. This paper provides a detailed analysis on various methods used for detection and segmentation of brain tumor and liver lesion. Due to the large availability of image data and complex computing resources which can process them has made a deep learning approach popular for medical image analysis. Deep learning architectures like Convolutional Neural Network (CNN), Fully Convolutional Network, Auto Encoders and Generative Adversarial Network (GAN) has transformed the research in brain tumor and liver lesion analysis. This paper discusses these deep learning architectures in brief along with the various variations in these architectures for medical image analysis. The datasets used for brain tumor and liver lesion analysis are also listed and compared in the paper. The advantages, limitation and research challenges of using deep learning methods is discussed in detail along with the possible solutions for overcoming these limitations. This paper will explore possible research gaps in deep learning in terms of analyzing the medical image with different modalities, resource computation, ensemble of CNN and optimization of the deep learning model for classification and prediction of medical data. [ABSTRACT FROM AUTHOR]

Arrhythmia is an abnormality in the rhythm of the heartbeat. The detection of cardiac arrhythmia in minimal time is important to prevent sudden deaths. Cardiologists use Electrocardiogram (ECG) to detect such abnormalities in the rhythm of the heartbeat. Deep Learning is one of the emerging technologies in classification. We can use deep learning to detect and classify ECG, which plays an essential role in patient monitoring. This paper gives a detailed review of the recent deep learning methods used in ECG for classification. This paper also discusses various deep learning methods such as Convolutional Neural Network (CNN), Deep Belief Network (DBN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Generative Adversarial Networks (GANs). Among these methods, Convolutional Neural Network is the most suitable method for feature extraction. Classifications based on Deep learning methods are known to be highly accurate. [ABSTRACT FROM AUTHOR]

Medical imaging has seen substantial improvements not only in image procurement but also in terms of interpretational methodologies. The practice of using technologies such as image processing and artificial intelligence has shown remarkable results in the detection, classification, and localization of human bone fractures. Breakage or cracks in the bone occur when an external force is applied to a bone that is significantly larger than the bone's tolerance, which may lead to dislocation requiring extensive treatment. However, manual examination by experts is a complex and arduous process with a high chance of false detection. Many approaches under Artificial Intelligence and its subsets are proposed to facilitate fracture diagnosis and prevent misinterpretation, including Deep Learning and Convolutional Neural Networks (CNN). This paper is a comprehensive study of the various techniques and models designed using image processing approaches and the advances in machine learning and Deep Learning that have demonstrated improved performance in the precise detection of fractures in human bones. [ABSTRACT FROM AUTHOR]

The paper intends to build a drone detection system using machine learning and deep learning algorithms. The system could differentiate between a drone and other flying objects like a different type of bird and recognize it. It also covers the various algorithms implemented for the development of drone detection systems. The research work uses YOLO algorithm as it is very efficient and widely used algorithm. Using the YoloV4 model, 85% of accuracy is obtained by classifying the images of the military drones in the 'aeroplane' category. It is one of the classes 'coco' dataset files. YoloV4 algorithm detects the drones which are based on deep convolutional neural networks. YoloV4 model is one of the most tested and stable versions of the YOLO. Once the drone is identified by the model, it will switch on the alarm to indicate drone detection. [ABSTRACT FROM AUTHOR]

A bigger role in our lives is being played by deep learning (DL). It has already had a significant effect in fields including self-driving cars, speech recognition, cancer diagnosis, precision medicine, and forecasting. Generative adversarial networks, convolutional neural networks, and visual geometry groups employing computer vision are a few of the key facilitators of DL algorithms. Using the defined keywords "deep learning," "image quality," and "computer vision and their application," the current study conducts an exhaustive search of all pertinent research articles on deep learning in image enhancement in three easily accessible databases, namely IEEE, ScienceDirect, ResearchGate, and Kaggle. Two categories are used to separate the final collection of papers on deep learning's application to image improvement. In the first category, you'll find publications that made an effort to build and construct deep learning, especially those that focused on novel architecture, system designs, frameworks, schemes, models, techniques, and algorithms. The second group of studies includes those that made an effort to assess and examine the use of generative adversarial networks in picture improvement. [ABSTRACT FROM AUTHOR]

continuing care is referred to as a chronic disease. The most widespread and expensive medical illnesses worldwide are chronic diseases. Chronic diseases can result in hospitalization, long-term impairment, worse quality of life, and even death. These conditions include cancer, diabetes, hypertension, stroke, heart disease, respiratory conditions, and kidney diseases. In reality, the greatest cause of mortality and disability worldwide is chronic illnesses. In this paper, we present deep-based and machine-based models to diagnose chronic diseases, this system includes several stages, namely the stage of data pre-processing and the stage of disease detection, which is carried out in two ways, the first depending on a deep Convolution Neural Network (CNN) and the second based on five machine learning algorithms: Stochastic Gradient Descent (SGD), Naïve Bayes (NB), K-Nearest Neighbor (KNN), Logistic Regression (LR), and Decision Tree (DT). The proposed model works on three data sets, namely (Pima Indians Diabetes Dataset, Cardiovascular Disease dataset, and UCI Heart Disease Data) to classify heart, diabetes, and kidney diseases. The experimental results proved the capability of the suggested system to classify the aforementioned diseases with an ideal accuracy of 100% using the CNN in the first model, and an accuracy of 94% in the second model using the SGD and LR algorithms. [ABSTRACT FROM AUTHOR]

The paper presents intelligent EU-TIRADS classificator for early detection of thyroid anomalies using a Deep Learning approach. The image data set is consisting of ultrasound images of the Thyroid glance which are classified in five classes: EU-TIRADS – 1, where 1 represents healthy individuals and EU-TIRADS 2-5, where the stage represents the severity of the disease. The Deep learning approach of choice in this experiment is a Deep learning Convolutional Neural Network. This algorithm was selected as it can provide high accuracy without explicit image processing prior to modelling. Finally, the classification performance metrics are presented. [ABSTRACT FROM AUTHOR]

A massive number of sensor nodes are placed in a wireless sensor network to cover a certain region, where their main objective is to monitor and report certain events to the base station. These nodes have relatively restricted memory and processing capabilities due to limited battery power. These nodes are typically used in locations where changing the battery is not accessible, so it's very important for wireless sensor networks to reduce energy usage and extend system lifespan. Because data transmission and reception use the most energy, developing a routing system that tackles the WSN's main issue is crucial. Hierarchical routing is crucial for transferring aggregated data to the sink. The cluster head selection mechanism under examination in this paper alternates the cluster head role between nodes having higher energy values than the cluster as a whole. To extend the system lifetime of the WSN, we applied LEACH with deep learning in this study. Convolutional Neural Networks were used to pick cluster heads in this suggested technique (CNN). In comparison to prior versions of LEACH protocols, the suggested method eliminates random process selection, which causes unexpected failure for some cluster heads in other LEACH versions, and it provides a decent performance in terms of network lifespan and energy usage. [ABSTRACT FROM AUTHOR]

The number of vehicles on the road has grown, producing concerns such as traffic congestion and fatal and injury accidents. To overcome these obstacles, numerous researchers have focused on determining proper vehicle localization, categorization, and tracking using a variety of methodologies. Currently, numerous strategies for detecting vehicles have been proposed. This study gives a detailed overview of deep learning approaches for vehicle detection and classification. The algorithms can be classified into two groups based on the model training approach: among the two-stage detection algorithms are: regional convolutional neural network (R-CNN), fast regional convolutional neural network (Fast R-CNN), faster regional convolutional neural network (Faster R-CNN), mask regional convolutional neural network (Mask R-CNN), and algorithms for single-stage detection include: the single-shot detector (SSD) and you only look once (YOLO). Finally, our paper discusses previous studies for vehicle detection and explains the techniques mentioned above. [ABSTRACT FROM AUTHOR]

Real-time face detection and recognition have become a very important issue in the past two decades. Current security methods based on passwords or fingerprints are risky due to the COVID-19 crisis that can be spread by touch. Face recognition methods are the best choice for security applications. It has proven to be one of the most reliable biometric security systems because frames can be captured from cameras without touching or interacting with them, and these images are automatically recorded and validated using existing databases. CNN's deep network has made it easy to build complex models to extract facial features at a higher resolution than humans can recognize. CNN models are produced to solve complex tasks but with high memory and computational requirements, due to application concerns and as well as the difficulty, this presents to artificial vision algorithms. They must be able to handle the large contrast in aspects of the same faces as well as differences in shooting parameters (position, lighting, haircut, expression, background, etc.). This paper seeks to create a real-time face recognition model to be used as a surveillance camera and works to store images of known and unknown faces instead of watching camera footage, and also for a biometrics system based on convolutional neural networks. It proposes an architecture for a deep learning model which it works to improve the current accuracy and processing time. [ABSTRACT FROM AUTHOR]

The main factor causing blindness in countries like India and others is Diabetic Retinopathy. Millions of people around the world are affected by DR, which causes vision loss and blindness. Detecting diabetes mellitus early plays an essential role in preventing the loss of vision that can result from diabetes mellitus being left untreated for a considerable amount of time. It is becoming increasingly more important to detect diabetic retinopathy early through automated systems instead of manual screening procedures like fluorescein angiography, optical coherence tomography etc., as it can lead to blindness among patients with uncontrolled diabetes. There are several published studies on machine learning and deep learning-based DR detection systems. In this paper, we explore the basics of advanced AI technologies used in DR analysis and early detection. The purpose of this study is to review DR detection methods are examined from a variety of perspectives. It includes fundus datasets, pre-processing of images, methodologies, machine learning and deep learning-based methodologies, and performance metrics. As well as presenting the review findings, it also presents the authors' observations. There were numerous public datasets for DR detection that are readily available. The Artificial Neural Network proved to be the better classifier over other machine learning methods based on shape, texture, and statistical features for DR detection. The purpose of this study is to propose the Convolutional Neural Network (CNN) through GoogLeNet for betterment based on the previous CNN model which was implemented using deep learning. Furthermore, the scientific community dedicated to developing automated DR investigative techniques. This review offers a thorough overview of DR detection methods. [ABSTRACT FROM AUTHOR]

This paper discusses the importance of communication for human interaction, especially for individuals with hearing impairments who rely on sign language. However, learning sign language is not easy, and not many people are familiar with it. To bridge the communication gap between deaf individuals and the general public, this study focuses on developing a deep convolutional neural network (CNN) model to recognize sign language patterns, specifically SIBI Sign Language used for formal activities. The VGG16 architecture is employed, which has been trained on a sign language dataset with 1440 images. The results show an accuracy of over 98.32% in training data. This research demonstrates how technology, particularly deep learning and computer vision, can help solve communication problems and improve accessibility for individuals with hearing impairments. [ABSTRACT FROM AUTHOR]

Ayurvedic medicines plays significant role in maintaining the biological state of human beings. The major components of ayurvedic medicines are plant leaves, roots, stem, bark, leaf stalk, flowers etc. Ayurvedic plants cure several disorders such as lung diseases, gastro-intestinal disease, cardiac disorder, skin disorder, excretory diseases etc. So knowledge about these plants sustained by generations must be conserved. Also appropriate classification and identification of ayurvedic plants is essential for researchers, botanist, cultivator and doctors. Manual identification will be time consuming, imprecise and inaccurate. This paper proposes an automatic recognition system for the identification of different types of ayurvedic plant images using deep Convolutional Neural Network (CNN) and Artificial Neural Network (ANN) based on transfer learning method. For the performance evaluation the dataset is generated by capturing images using mobile device from the environment and from Google network. The dataset consist of 424 plant images of 21 types of ayurvedic plants. A Graphical User Interface (GUI) is also developed to display the informations of the detected ayurvedic plant. [ABSTRACT FROM AUTHOR]

Diseases can have a detrimental effect on plants depreciating their market value. Disease diagnosis is important for improving plant yield. Over the years, farmers are relying on Soft Computing (SC) techniques for the purpose of early diagnosis of various plant diseases. The paper builds an application using a Deep Learning (DL) model for timely disease diagnosis. The research employs pre-trained Convolution Neural Networks (CNN) for identifying crop diseases and insect pests. CNN efficiently tackles the challenges related to image stability and the number of parameters. PlantVillage dataset is used for training and testing the model. The dataset comes with fifteen different classes of infected and healthy leaves. The work applies image pre-processing techniques and data augmentation for enhancing the image recognition rate. The paper implements a crop disease recognition model comprising of Inception-ResNet-v2, Visual Geometry Group 16, DenseNet201 and, Inception_V3 for training. The model and subsequently the application are validated and tested using standard methods. The convolution layer of the networks uses a non-linear activation function-ReLU which has gained popularity in the deep learning domain for its simple activation strategy. Later the name of the crop reporting the highest matching degree is displayed. Lastly, the accuracy of all the networks is compared against the traditional convolution network. It is inferred that the system thus aims to efficiently identify crop diseases and produces better recognition accuracy than the traditional convolution networks. [ABSTRACT FROM AUTHOR]

Driving while drowsy is one of the significant causes of road accidents, and detection of drowsiness of drivers is necessary to minimize such accidents. There are many methods proposed for drowsiness detection. In this paper, we present the details of a drowsiness detection system using deep learning techniques with ECG as its input. Continuous wavelet transforms (CWT) are applied on the input signal, segmented to 1-minute duration, and then it is converted into scalogram images to be fed as input to deep neural networks (DNN). We use pre-trained transfer learning models, AlexNet, ResNet-50, and VGG-19 for this work. The best results were obtained for Reset-50 with an accuracy of 88.31% without dropping the final layers, which is an improvement of 4.5% over the spectrogram-based implementation. This paper evaluates the effectiveness of wavelet-based features, and we note that the time-frequency domain features outperform. To check the robustness of the net-work, a second model is implemented by dropping the final layers, and the validation accuracy of AlexNet is 51.5%, ResNet-50 is 67.2%, and VGG-19 is 81.8%. [ABSTRACT FROM AUTHOR]

Alzheimer's disease (AD) is the most common chronic disease in the elderly, with a high incidence rate.[1] Accurate early-stage Alzheimer's disease identification is essential for successful treatment and recovery. Owing to which a significant research challenge is the precise diagnosis of Alzheimer's disease. Different researchers used various techniques to detect Alzheimer's disease effectively however; these methods still have a lack of prediction accuracy. Deep learning has had significant success and gained popularity in the field of medical imaging in recent years. It has emerged as the method of choice for examining medical images and has drawn considerable interest in the identification of AD. When it comes to detecting AD, the deep model is more precise and effective than ordinary machine learning technologies. In this review paper, we compared various research methodologies focusing on early diagnosis of AD based on convolutional neural networks (ConvNets) with the usage of Positron Emission Tomography (PET) and magnetic resonance imaging (MRI). In comparison to networks trained with single-modal images, the network trained with multi-modal images performs better. The performance of the suggested strategy has been examined using the data set from the Alzheimer's Disease Neuroimaging Initiative. [ABSTRACT FROM AUTHOR]

Yoga aims at development of all-round personality; it is synchronization of mind, body and the spirit. Improper postures / in-correct way of doing Yoga can result in serious damage to one's physique and brain. In ancient times, it used to be performed only under the supervision of an accomplished Guru (teacher). In recent times, people either join Yoga centres or learn through online videos, however self-instruction could be difficult to find incorrect postures can lead to serious injuries. Therefore, it is essential to align proper position for Yoga from the initial stage of learning. Deep Learning models can be trained to detect Yoga postures and be able to provide feedback if corrections are needed. OpenPose is the first real-time multi-person system which brought revolutionary change in the field of pose estimation of a human body. The proposed model estimates and classifies yoga poses into five broad categories with low latency. Using multiple deep learning architectural models, this study provides a comprehensive evaluation of current state-of-the-art Yoga pose detection approaches. Its goal is to serve as a resource for academics and industry to research various Yoga pose detection methods. We investigated the most contemporary and promising deep learning approaches for Yoga pose tracking and detection and divided them into two classes: Convolutional Neural Network (CNN) based systems and Recurrent Neural Network (RNN) based systems. The focus of this research is to offer a contrast of several deep learning-based Yoga pose detection systems like CNN, LSTM, RNN, etc., as well as we illustrated a comprehensive table that gives the overview of the paper published that could be used for further understanding the role and significance of the systems in the Yoga pose detection task. At the closure of the report, obstacles and further development have been mentioned. This survey can assist scholars in better understanding present systems and proposing new techniques by addressing the challenges that have been identified. [ABSTRACT FROM AUTHOR]

Respiratory diseases are one of the main causes of death in the world; an example is COVID-19, which we are facing nowadays. Thus, helping the medical field using new and uprising technologies is a must. One of the ways to help them is by using deep learning technologies and networks to predict and classify diseases. In this paper, radiography lung images, obtained from open-source websites like Kaggle, are used to train different types of networks to classify the patients' lungs into normal, lung opacity, pneumonia, or covid. Comparisons are made to find the model with the best performance. Our research proved that transfer learning achieves better results after using VGG16 and ResNet-50, compared to two Convolutional Neural Networks (CNNs) built from scratch with different pre-processing functions. Several experiments were conducted with different configurations and hyperparameters and it is found that ResNet-50 is the most suitable network for our dataset and these tasks. The results recorded an accuracy equal to 95.77% on training data and 91.83% on testing data for ResNet-50 on the multiple diseases classification tasks. An accuracy equal to 99.48% on training data and 98.25% on testing data for the COVID-19 binary classification task. [ABSTRACT FROM AUTHOR]

Biometric authentication is an absolute way to secure digital belongings. Digital devices empowered with web cameras enabled face recognition as a prominent way to secure these devices and hence the sensitive data from these devices. Face recognition has additional advantage over the other biometric traits used for identification is that unlike fingerprint-based recognition, face scanning is contact free and gives flexibility to be at a distant from camera unlike Iris based recognition. So, we have selected face recognition case study to build classifying model using keras library from Tensorflow framework and studied the basic steps to learn and evaluate model. Deep learning has made it possible to identify images with automatic extraction of features and matching with enough good accuracy in lieu of incurred more time and memory. This paper aims to present comparative study of transfer learning achieved through different Convolutional Neural Network (CNN) architectures which are used to perform face recognition. The CNN architectures Vgg16, Vgg19, InceptionNet need huge amount of training samples to build accurate model. So we have augmented images to have dataset enough large to learn features. With transfer learning, time to train model gets minimized as already updated weights from predefined architectures are used, still inclusion of full connected layers from original architecture and its exclusion affects accuracy as it is matter of appropriateness. Siamese network succeeds in providing equivalent accuracy even though the large dataset is containing few samples within a class. Siamese network following predefined architectures produces favorable accuracy. [ABSTRACT FROM AUTHOR]

In this paper, a video classifier using transfer learning with VGG16 (Convolutional neural network model pre-trained on the ImageNet-1k dataset) base model and hybrid transformers on the UCF Crime Dataset of 100GB is presented. Thisdeep learning approach is presenting a hybrid model for video classification having applications in scene identification, video classification, security, and many. [ABSTRACT FROM AUTHOR]

Age and gender recognition are helpful in various applications, especially in the field of advertising. To replace the traditional advertising method that can only display the same contents to all audiences, a smart advertisement board capable of detecting age and gender of audiences to display relevant contents is required to increase the effectiveness of advertising. This paper will use two image datasets to train and test the Convolutional Neural Network (CNN) based architecture models for age and gender recognition using deep learning. The dataset that produced the best performing model will be implemented on three different devices to observe the performance of the models on each device. A gender recognition model with accuracy of 91.53% and age recognition model with accuracy of 59.62% is produced. The results have also shown the use of Field Programmable Gated Array (FPGA) has greatly boosted the performance of the models in terms of throughput and latency. [ABSTRACT FROM AUTHOR]

Due to the development of technology, it is easy to integrate this into many of applications such as automatic security door lock system. As presented in this paper, we proposed a voice recognition for the user authentication in order to open the door by using the word in Bahasa. In order to recognize the user voice, the convolution neural network (CNN) deep learning algorithm will be utilized as a proposed method. We also provide a simple web based which is allowed to recognize the user voice directly when the user spoke. Some experiments have been carried out to verify the performance of the system by using the work "Buka" and some words which has the similarity in pronunciation. Based on the experiment results, our system was able to recognize the trained voice accurately even the user used another word which was similar to say. [ABSTRACT FROM AUTHOR]

To create, the deep reinforcement learning technique combines deliberative reasoning with visual perception. It does this by using an end-to-end learning approach to merge the reinforcement learning's decision-control abilities with convolution neural networks' perceptual abilities. It's utilized frequently. It has been applied to tackle issues with complex decision control and high-dimensional visual input ever since it was created. MPC works best when I understand what is required of me in terms of authority and responsibility as well as the state constraints that always exist in real-world scenarios, which validates its application in this case. DRL is then used to create the algorithm, which includes observation states. By utilizing the reward function, network structure, and parameter optimization for a 2D environment, the laborious 3D environment effort is avoided. We use the tried-and-true method to obtain the converged network's parameters, such as the deep neural networks (DNN) weights and biases, in a simple 3D environment. This research gives a general overview of how the agent should be represented in technologies employing applied Markov decision processes. This paper presents a proof-of-concept application scenario to illustrate the effect of multichannel Kalman filtering on the reduction of uncorrelated noise in magnetotelluric data. We evaluate our strategy using a variety of maps that depict the kinds, locations, and numbers of obstacles. The experimental findings show strong generalization, the superiority of G2RL over prior technologies, and its capacity to perform almost as well as entirely despite relying on distributed architectures and modern benchmarks at their core. [ABSTRACT FROM AUTHOR]

Now a day there is exponential growth in music files, so the need for automatic music genre classification approach is also increasing. Current classification systems of music genres developed using machine learning algorithms and some of the limitations of existing music genre systems are doesn't work with large database, low accuracy etc. In this paper, presented a large music dataset namely GTZAN with 10 distinct music genres like jazz, rock, hip-hop etc. In order train the classification model of music genre system, a deep learning based technique called CNN (Convolution Neural network) is applied. The proposed method performs the classification of music genre into innumerable genre with the help of feature vector extraction, which plays a vital role in training the model. The feature vector called MFCC (Mel Frequency Cepstral Coefficient) considered in classifying the raw files which are converted to respective music genres or types. The performance of various classification techniques are analyzed compared with respect to evaluation metrics. [ABSTRACT FROM AUTHOR]

Lung cancer is one of the commonest diseases globally and accounts for more deaths from lung cancer than other ones. We did an exact review of the distributed things on the study of disease transmission, conclusion, and treatment of lung cancer and as the dispersion of lung cancer is rapidly going on, it reaches the epidemic range or peak level. Besides, it has beaten the earlier commonest outline of cancer and is presently the commonest harm in men and women. Different modalities for early recognition through screening are being researched and it is observed that the majority of the patients have died due to late detection of this disease so recognition at the premature stage, as well as accurate detection of a lung nodule, is very much necessary so the most challenging thing is to develop a robust method for nodule detection that is why the main objective of this paper is early detection, minimizing the false rate, as well as improving accuracy. In the paper, a new model is proposed based on deep-learning for the pinpointing of region precisely, as we know there is a huge advancement in Deep convolutional neural networks in pre-processing, we adopted Three-dimensional Convolutional Neural Network) for the prognosis of lung cancer from the CT images of the long-sufferer. As one knows about the convolution neural network, it makes things easier to extract significant data by processing the images of the dataset. Gradient-weighted class activation mapping strategies can convey the information by visualization for precise judgment in lung knot by point-up the adversely affected area. [ABSTRACT FROM AUTHOR]

The streaming media services such as over the top (OTT) platforms offer open access to video content to the subscribers irrespective of their age. Different genres of movies suitable for different age groups are available to the viewers on the OTT platforms.Once subscribed; the user has easy access to uncensored content too, as there is no age confirmation during the signup process. Although these platforms allow one to buy subscriptions from credit or debit cards usually owned by adults, yet once the subscription is bought for multiple users, different persons of a household can use the same device and platform to view content of their interest. There is no option to track the kind of content they are viewing on these OTT platforms. The un-censored and adult content easily available on these platforms lead to unguarded exposure of the kids below 18 years of age to audio-visual content that is not suitable for their age. This can hamper the healthy mental and emotional development of the juvenile population. In this paper, we have proposed a deep learning based face detection module that can be integrated with the OTT platforms to verify the age group of the viewer before proceeding for selection of the content. This classification module will not only provide the first layer of security to enforce the age restriction policy for viewing age appropriate content but also can be used for creating a more effective recommendation system. In this paper, we have made a comparative analysis of three main face detection algorithms based on Convolutional Neural Network namely Haar Cascade, HOG and Deep Neural Network (DNN) to estimate an age cut off and range of a new face in real time. The highest accuracy of 92.56 percent was achieved in case of DNN based algorithm for both age cut off and age approximation detection. Precision recorded by DNN for large faces is 90%, which is higher than in case of HOG and OpenCV-Haar. [ABSTRACT FROM AUTHOR]

Social media is in the realms of our daily lives these days. From youngsters to aged and professionals to students – it is hard to find a person who does not have a social media account today. It is to be noted that social media today contains numerous fake accounts as there is no control or check of credentials at the time of opening the account. This uncontrolled expansion of social media has given rise to crimes; both physical and cyber. Criminals create fake account under masquerade and make friends with people to harm them physically, financially and mentally. In order to get rid of this, there should be a system of real time gender and age check before someone could open an account in social media. In this paper we have proposed a deep learning based method of age and gender detection in real time. The proposed method of age and gender detection may be used right at the time of opening an account. This way, it will be difficult for people to pose as someone, who they are not. In this paper we have made a comparative analysis of four main face detection algorithms based on Convolutional Neural Network namely Haar Cascade ,HOG , CNN and Deep Neural Network(DNN) to estimate an age-range and gender of a new face. The highest accuracy i.e 90 percent was achieved in case of DDN based algorithm for both age range approximation and gender detection. [ABSTRACT FROM AUTHOR]

The enormous benefits and applications of Image classification and recognition are umpteen. Machine learning algorithms and Deep Neural Networks are like windfall to fathom the objective proficiently in streamlined manner. The prevalent improvement in this technology is that these networks do not call for any prior blueprints in terms of algorithms as prerequisites. The presented paper is an attempt to create a Convolutional Neural Network from scratch to classify the images from the well-known dataset – Cats and Dogs into their relevant baskets. Manifold open source accessible approaches to amplify the efficiency of the network are no more onerous. Further, data augmentation technique boosts the efficiency tremendously by extending the dataset with reoriented features from the same images. To untangle the same problem, Transfer Learning is also a compelling technique in which all the layers, neurons in each layer, weights of each neuron and all other parameters are predefined and we can amend the output layer as per the classes in the respective problem statement. In the present paper, we have tried to obtain a comparable efficiency with a significant reduction in parameters. [ABSTRACT FROM AUTHOR]

The crime rate has been rising at an unprecedented rate, and security has become a big concern in ATM machines. Face detection is the most common biometric technique due to its non-invasive nature. It's been used in a variety of fields, including camera auto focus, attendance, crowd monitoring, object tracking, security, system, etc. Face detection systems uses image processing techniques that are being learned to operate reliably in a variety of conditions, including changes in posture, lighting, skin color, occlusion, and face spoofing. The face detection system has become increasingly vulnerable to occlusion. Occlusion refers to the deliberate shielding of one's face with a helmet, sunglasses, scarves, or other items in order to avoid being caught. These issues have a significant impact on the development of image processing techniques and system's performance. In this paper the Haar Cascade Classifier (HCC) scheme is projected for face detection where precision as well as minimal processing time are important factors for ATM. The proposed scheme uses deep learning models such as Convolutional Neural Networks to enhance the reliability in feature extraction plus classification of images. Face biometric access control devices are becoming more common in everyday lives, but they remain vulnerable to spoofing attacks. This paper also proposes face spoofing identification using Local Binary Pattern (LBP) that has useful features for face detection. The proposed spoofing attack detection technique has yielded encouraging results. [ABSTRACT FROM AUTHOR]

Detecting driver inattentive is one of interested research area to reduce vehicle accidents. Driver safety can be improved by detecting driver drowsiness and distraction. The increase of in-vehicle information systems induces the biomechanical and cognitive of driver distraction which affects driving performance qualitatively. The impact of digital technology on driving performance is presented in this paper based on the relative influence of the state-of-the-art techniques. The paper presents the finding of Convolution Neural Networks (CNNs) literature review covering the driver distraction detection systems. The results observe that convolutional neural network (CNN) is a powerful deep learning method that fits the needs of researchers in detecting of driver distraction. It can extract the useful attributes from trained data and train the weights by feeding the data on each level then tune the CNN based on specific driver distraction measurements. Also, it can provide a high accuracy results in real-time environment. [ABSTRACT FROM AUTHOR]

In the recent times, deep learning has gained significant importance in various domains. Computer Vision is one the domains in which deep learning has seen vast development and is still gaining a lot of attention. CNNs are deep architectures that are specifically applied for image classification and object detection in computer vision. Image classification has also been successfully applied in the field of agriculture. Using deep learning, various agricultural problems have been addressed and solved. Keeping in view the enormous uses of deep learning in agricultural domain, this paper gives a brief review of the various works proposed by the researchers working in the field of deep learning and agriculture. This paper will put some light on the various agricultural problems, the deep learning models that have been employed to solve the problem, any pre-processing techniques that have been applied on the images to prepare the dataset for the specific model and the results that have been achieved by the model in solving the problem they focus on. It will also provide any research gap found in the specific work. This work will be useful for future researchers to gain an overview of the work done so far and the deep learning techniques used in agriculture. [ABSTRACT FROM AUTHOR]

Nowadays social media plays a significant role in all sorts of our activities ranging from analysing the attitude of a person for the job, getting opinions towards buying a product, acting as a forum for exchanging thoughts about the current events of various domains, creating awareness to the public about the natural calamities, educating the public about the fraudulent news spread by the fakers, initiating the young aspirant to protest against any societal issues, etc. Grasping the opinions shared by the experienced people towards a product, film, event, news, or politics like any subject of matter is one among the worth noting applications for a common man. It extends its application to making decisions about our day-to-day activities. The text reviews consist of enormous, sparse, non-uniform distribution of words represented as features. Text mining is the backend process for those applications. It includes techniques such as feature representation, sentiment classification, feature optimization, etc. Analysing the opinions suggested by the experienced people as positive and negative reviews is a challenging process and it is the baseline of our work. This paper contributes to the related processes involved in analysing the sentiments from the text reviews and accurately classifying them based on their polarity. In the proposed work, we particularly focus on feature representation techniques that have a major effect on enhancing the performance of sentiment classification. We explore different feature representation models such as TF-IDF vectorizer, word2vec vectorizer, and glove vectorizer as these word embedding models are interpreting the words and their syntactic and semantic relationships differently from the corpus. Also, we employ machine learning algorithms and a deep convolution neural network to perform comparative studies in classifying the sentiments. The word2vec in combination with Deep Convolution Neural Network provides the accuracy of 85.7%, precision of 84.4%, recall of 87%, and F-measure of 85.7% compared to other models. [ABSTRACT FROM AUTHOR]

The degree of Guyabano fruit is decided commercially by human assessment of color and texture to confirmthat the fruits are of good quality. Manual grading of Guyabano fruit using human vision is both time-consuming andharmful. Guyabano is graded for ripeness using vision and touch to assess color and texture. Farmers and consumers who are ready to harvest and eat Guyabano fruit but are having trouble determining maturity will be able to do utilizingCNN techniques. In today's world, the most widely utilized class of image identification and classification models is the Convolutional Neural Network (CNN). The application of strategies for grading the quality of Guyabano fruit is discussed in this paper. From hand grading, an automatic gradation is done to ensure that the fruits are of the greatest possible quality. Based on the results, the study looked at various CNN designs to determine the best prediction classifier. The goal of this study is to develop a non-destructive way for the significant maturity of Guyabano fruits. We employed a MobileNetV2 network that had been pre-trained by the ImageNet dataset as a base network and then substitute the top layer of the base network with a normal convolution layer. The test results were reviewed using generated accuracy and loss evaluation to establish the model's overall effectiveness. The average grading accuracy for Guyabano fruit is 99%. [ABSTRACT FROM AUTHOR]