Search

Pashtu is one of the most widely spoken languages in south-east Asia. Pashtu Numerics recognition poses challenges due to its cursive nature. Despite this, employing a machine learning-based optical character recognition (OCR) model can be an effective way to tackle this issue. The main aim of the study is to propose an optimized machine learning model which can efficiently identify Pashtu numerics from 0–9. The methodology includes data organizing into different directories each representing labels. After that, the data is preprocessed i.e., images are resized to 32 × 32 images, then they are normalized by dividing their pixel value by 255, and the data is reshaped for model input. The dataset was split in the ratio of 80:20. After this, optimized hyperparameters were selected for LSTM and CNN models with the help of trial-and-error technique. Models were evaluated by accuracy and loss graphs, classification report, and confusion matrix. The results indicate that the proposed LSTM model slightly outperforms the proposed CNN model with a macro-average of precision: 0.9877, recall: 0.9876, F1 score: 0.9876. Both models demonstrate remarkable performance in accurately recognizing Pashtu numerics, achieving an accuracy level of nearly 98%. Notably, the LSTM model exhibits a marginal advantage over the CNN model in this regard. [ABSTRACT FROM AUTHOR]

Sentiment analysis, a crucial task in discerning emotional tones within the text, plays a pivotal role in understanding public opinion and user sentiment across diverse languages. While numerous scholars conduct sentiment analysis in widely spoken languages such as English, Chinese, Arabic, Roman Arabic, and more, we come to grappling with resource-poor languages like Urdu literature which becomes a challenge. Urdu is a uniquely crafted language, characterized by a script that amalgamates elements from diverse languages, including Arabic, Parsi, Pashtu, Turkish, Punjabi, Saraiki, and more. As Urdu literature, characterized by distinct character sets and linguistic features, presents an additional hurdle due to the lack of accessible datasets, rendering sentiment analysis a formidable undertaking. The limited availability of resources has fueled increased interest among researchers, prompting a deeper exploration into Urdu sentiment analysis. This research is dedicated to Urdu language sentiment analysis, employing sophisticated deep learning models on an extensive dataset categorized into five labels: Positive, Negative, Neutral, Mixed, and Ambiguous. The primary objective is to discern sentiments and emotions within the Urdu language, despite the absence of well-curated datasets. To tackle this challenge, the initial step involves the creation of a comprehensive Urdu dataset by aggregating data from various sources such as newspapers, articles, and socialmedia comments. Subsequent to this data collection, a thorough process of cleaning and preprocessing is implemented to ensure the quality of the data. The study leverages two well-known deep learningmodels, namely Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN), for both training and evaluating sentiment analysis performance. Additionally, the study explores hyperparameter tuning to optimize the models' efficacy. Evaluation metrics such as precision, recall, and the F1-score are employed to assess the effectiveness of the models. The research findings reveal that RNN surpasses CNN in Urdu sentiment analysis, gaining a significantly higher accuracy rate of 91%. This result accentuates the exceptional performance of RNN, solidifying its status as a compelling option for conducting sentiment analysis tasks in the Urdu language. [ABSTRACT FROM AUTHOR]

This study explores the area of Author Profiling (AP) and its importance in several industries, including forensics, security, marketing, and education. A key component of AP is the extraction of useful information from text, with an emphasis on the writers' ages and genders. To improve the accuracy of AP tasks, the study develops an ensemble model dubbed ABMRF that combines AdaBoostM1 (ABM1) and Random Forest (RF). The work uses an extensive technique that involves textmessage dataset pretreatment, model training, and assessment. To evaluate the effectiveness of several machine learning (ML) algorithms in classifying age and gender, including Composite Hypercube on Random Projection (CHIRP), Decision Trees (J48), Naïve Bayes (NB), K Nearest Neighbor, AdaboostM1, NB-Updatable, RF, andABMRF, they are compared. The findings demonstrate thatABMRFregularly beats the competition, with a gender classification accuracy of 71.14% and an age classification accuracy of 54.29%, respectively. Additional metrics like precision, recall, F-measure, Matthews Correlation Coefficient (MCC), and accuracy support ABMRF's outstanding performance in age and gender profiling tasks. This study demonstrates the usefulness of ABMRF as an ensemble model for author profiling and highlights its possible uses in marketing, law enforcement, and education. The results emphasize the effectiveness of ensemble approaches in enhancing author profiling task accuracy, particularly when it comes to age and gender identification. [ABSTRACT FROM AUTHOR]

This paper investigates the performance enhancement of base classifiers within the AdaBoost framework applied to medical datasets. Adaptive boosting (AdaBoost), being an instance of boosting, combines other classifiers to enhance their performance. We conducted a comprehensive experiment to assess the efficacy of twelve base classifiers with the AdaBoost framework, namely, Bayes network, decision stump, ZeroR, decision tree, Naïve Bayes, J-48, voted perceptron, random forest, bagging, random tree, stacking, and AdaBoost itself. The experiments are carried out on five datasets from the medical domain based on various types of cancers, i.e., global cancer map (GCM), lymphoma-I, lymphoma-II, leukaemia, and embryonal tumours. The evaluation focuses on the accuracy, precision, and efficiency of the base classifiers in the AdaBoost framework. The results show that the performance of Naïve Bayes, Bayes network, and voted perceptron is highly improved compared to the rest of the base classifiers, attaining accuracies as high as 94.74%, 97.78%, and 97.78%, respectively. The results also show that in most cases, the base classifiers perform better with AdaBoost compared to their performance, i.e., for voted perceptron, the accuracy is improved up to 13.34%.For bagging, it is improved by up to 7%. This research aims to identify such base classifiers with optimal boosting capabilities within the AdaBoost framework for medical datasets. The significance of these results is that they provide insight into the performance of the base classifiers when used in the boosting framework to enhance the classification performance of classifiers in scenarios where individual classifiers do not perform up to the mark. [ABSTRACT FROM AUTHOR]

Dental caries is one of the most prevalent and chronic diseases worldwide. Dental X-ray radiography is considered a standard tool and a valuable resource for radiologists to identify dental diseases and problems that are hard to recognize by visual inspection alone. However, the available dental panoramic image datasets are extremely limited and only include a small number of images. U-Net is one of the deep learning networks that are showing promising performance in medical image segmentation. In this work, different U-Net models are applied to dental panoramic X-ray images to detect caries lesions. The Detection, Numbering, and Segmentation Panoramic Images (DNS) dataset, which includes 1500 panoramic X-ray images obtained from Ivisionlab, is used in this experiment. The major objective of this work is to extend the DNS Panoramic Images dataset by detecting the cavities in the panoramic image and generating the binary ground truth of this image to use as the ground truth for the evaluation of models. These ground truths are revised by experts to ensure their robustness and correctness. Firstly, we expand the Panoramic Images (DNS) dataset by detecting the cavities in the panoramic images and generating the images' binary ground truth. Secondly, we apply U-Net, U-Net++ and U-Net3+ to the expanded DNS dataset to learn the hierarchical features and to enhance the cavity boundary. The results show that U-Net3+ outperforms the other versions of U-Net with 95% in testing accuracy. [ABSTRACT FROM AUTHOR]

The recent outbreak of monkeypox has raised significant concerns in the field of public health, primarily because it has quickly spread to over 40 countries outside of Africa. Detecting monkeypox in its early stages can be quite challenging because its symptoms can resemble those of chickenpox and measles. However, there is hope that potential use of computer-assisted tools may be used to identify monkeypox cases rapidly and efficiently. A promising approach involves the use of technology, specifically deep learning methods, which have proven effective in automatically detecting skin lesions when sufficient training examples are available. To improve monkeypox diagnosis through mobile applications, we have employed a particular neural network called MobileNetV2, which falls under the category of Fully Connected Convolutional Neural Networks (FCCNN). It enables us to identify suspected monkeypox cases accurately compared to classical machine learning approaches. The proposed approach was evaluated using the recall, precision, F score, and accuracy. The experimental results show that our architecture achieves an accuracy of 0.99%, a Recall of 1.0%, an F-score of 0.98%, and a Precision of 0.95%. We believe that such experimental evaluation will contribute to the medical domain and many use cases. [ABSTRACT FROM AUTHOR]

Bloom filters are a type of data structure that is used to test whether or not an element is a member of a set. They are known for being space-efficient and are commonly employed in various applications, such as network routers, web browsers, and databases. These filters work by allowing a fixed probability of incorrectly identifying an element as being a member of the set, known as the false positive rate (FPR). However, traditional bloom filters suffer from a high FPR and extensive memory usage, which can lead to incorrect query results and a slow performance. Thus, this study indicates that a content-based strategy could be a practical solution for these challenges. Specifically, our approach requires less bloom filter storage, consequently decreasing the probability of false positives. The effectiveness of several hash functions on our strategy's performance was also evaluated. Experimental evaluations demonstrated that the proposed strategy could potentially decrease false positives by a substantial margin of up to 79.83%. The use of size-based content bits significantly contributes to the decrease in the number of false positives as well. However, as the volume of content bits rises, the impact on time is not considerably noticeable. Moreover, the evidence suggests that the application of a singular approach leads to a more than 50% decrease in false positives. [ABSTRACT FROM AUTHOR]

Skin conditions influence people of all ages and genders and impose an enormous strain on worldwide public health. For efficient management and medical treatment, skin disorders must be accurately categorized. However, the conventional method of classifying skin conditions can be arbitrary and time-consuming, delaying diagnosis and treatment. In this research, we examine the application of traditional machine learning models and conventional image characteristics for the classification of skin cancer based on picture features. Specifically, we employ six feature extraction approaches, which we model using six classical classifiers. To evaluate our approach, we address skin cancer detection as both a seven-class problem and a two-class problem comprising 21 permutations of skin cancer instances. Our experimental results demonstrate that Random Forest achieves the highest performance, followed by Support Vector Machines. Additionally, our analysis reveals that the Edge Histogram and Fuzzy Opponent Histogram feature sets perform best in learning the skin cancer model. Our comprehensive evaluation of various models provides practitioners with valuable insights when selecting appropriate models for similar problems. Our findings demonstrate that acceptable detection performance can be achieved even with simple feature extraction and non-deep classifiers. We argue that classical features are not only easier and faster to extract than deep features but can also be combined with classical machine learning models to save time and valuable resources. [ABSTRACT FROM AUTHOR]

In the machine learning (ML) paradigm, data augmentation serves as a regularization approach for creating ML models. The increase in the diversification of training samples increases the generalization capabilities, which enhances the prediction performance of classifiers when tested on unseen examples. Deep learning (DL) models have a lot of parameters, and they frequently overfit. Effectively, to avoid overfitting, data plays a major role to augment the latest improvements in DL. Nevertheless, reliable data collection is a major limiting factor. Frequently, this problem is undertaken by combining augmentation of data, transfer learning, dropout, and methods of normalization in batches. In this paper, we introduce the application of data augmentation in the field of image classification using Random Multi-model Deep Learning (RMDL) which uses the association approaches of multi-DL to yield random models for classification. We present a methodology for using Generative Adversarial Networks (GANs) to generate images for data augmenting. Through experiments, we discover that samples generated by GANs when fed into RMDL improve both accuracy and model efficiency. Experimenting across both MNIST and CIAFAR-10 datasets show that, error rate with proposed approach has been decreased with different random models. [ABSTRACT FROM AUTHOR]

The rapid rise of data value, such as social media and mobile applications, results in large volumes of data, which is what the term "big data" refers to. The increased rate of data growth makes handling big data very challenging. Despite a Bloom filter (BF) technique having previously been proposed as a space-and-time efficient probabilistic method, this proposal has not yet been evaluated in terms of big data. This study, thus, evaluates the BF technique by conducting an experimental study with a large amount of data. The results revealed that BF overcomes the efficiency not present in the space-and-time of indexing and examining big data. Moreover, to address the increase of false-positive rate in using BF with big data, a novel false-positive rate reduction approach is proposed in this paper. The initial experimental results of evaluating this method are very promising. The novel approach helped to reduce the false-positive rate by more than 70%. [ABSTRACT FROM AUTHOR]

Bloom filter (BF) is a space-and-time efficient probabilistic technique that helps answermembership queries. However, BF faces several issues. The problems with traditional BF are generally two. Firstly, a large number of false positives can return wrong content when the data is queried. Secondly, the large size of BF is a bottleneck in the speed of querying and thus uses large memory. In order to solve the above two issues, in this article, we propose the check bits concept. From the implementation perspective, in the check bits approach, before saving the content value in the BF, we obtain the binary representation of the content value. Then, we take some bits of the content value, we call these the check bits. These bits are stored in a separate array such that they point to the same location as the BF. Finally, the content value (data) is stored in the BF based on the hash function values. Before retrieval of data from BF, the reverse process of the steps ensures that even if the same hash functions output has been generated for the content, the check bits make sure that the retrieval does not depend on the hash output alone. This thus helps in the reduction of false positives. In the experimental evaluation, we are able to reduce more than 50% of false positives. In our proposed approach, the false positives can still occur, however, false positives can only occur if the hash functions and check bits generate the same value for a particular content. The chances of such scenarios are less, therefore, we get a reduction of approximately more than 50% false positives in all cases. We believe that the proposed approach adds to the state of the art and opens new directions as such. [ABSTRACT FROM AUTHOR]

Depression is a mental psychological disorder that may cause a physical disorder or lead to death. It is highly impactful on the socialeconomical life of a person; therefore, its effective and timely detection is needful. Despite speech and gait, facial expressions have valuable clues to depression. This study proposes a depression detection system based on facial expression analysis. Facial features have been used for depression detection using Support Vector Machine (SVM) and Convolutional Neural Network (CNN). We extracted micro-expressions using Facial Action Coding System (FACS) as Action Units (AUs) correlated with the sad, disgust, and contempt features for depression detection. A CNN-based model is also proposed in this study to auto classify depressed subjects from images or videos in real-time. Experiments have been performed on the dataset obtained from Bahawal Victoria Hospital, Bahawalpur, Pakistan, as per the patient health questionnaire depression scale (PHQ-8); for inferring the mental condition of a patient. The experiments revealed 99.9% validation accuracy on the proposed CNN model, while extracted features obtained 100% accuracy on SVM. Moreover, the results proved the superiority of the reported approach over state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Big data applications have tremendously increased due to technological developments. However, processing such a large amount of data is challenging for machine learning algorithms and computing resources. This study aims to analyze a large amount of data with classical machine learning. The influence of different random sampling techniques on the model performance is investigated by combining the feature selection techniques and machine learning classifiers. The experiments used two feature selection techniques: random subset and random projection. Two machine learning classifiers were also used: Naïve Bayes and Bayesian Network. This study aims to maximize the model performance by reducing the data dimensionality. In the experiments, 400 runs were performed by reducing the data dimensionality of a video dataset that was more than 40 GB. The results show that the overall performance fluctuates between 70% accuracy to 74% for using sampled and non-sample (all the data), a slight difference in performance compared to the non-sampled dataset. With the overall view of the results, the best performance among all combinations of experiments is recorded for combination 3, where the random subset technique and the Bayesian network classifier were used. Except for the round where 10% of the dataset was used, combination 1 has the best performance among all combinations. [ABSTRACT FROM AUTHOR]

The advent of the COVID-19 pandemic has adversely affected the entire world and has put forth high demand for techniques that remotely manage crowd-related tasks. Video surveillance and crowd management using video analysis techniques have significantly impacted today’s research, and numerous applications have been developed in this domain. This research proposed an anomaly detection technique applied to Umrah videos in Kaaba during the COVID-19 pandemic through sparse crowd analysis. Managing the Kaaba rituals is crucial since the crowd gathers from around the world and requires proper analysis during these days of the pandemic. The Umrah videos are analyzed, and a system is devised that can track and monitor the crowd flow in Kaaba. The crowd in these videos is sparse due to the pandemic, and we have developed a technique to track the maximum crowd flow and detect any object (person) moving in the direction unlikely of the major flow. We have detected abnormal movement by creating the histograms for the vertical and horizontal flows and applying thresholds to identify the non-majority flow. Our algorithm aims to analyze the crowd through video surveillance and timely detect any abnormal activity to maintain a smooth crowd flow in Kaaba during the pandemic. [ABSTRACT FROM AUTHOR]

Pernicious insects and plant diseases threaten the food science and agriculture sector. Therefore, diagnosis and detection of such diseases are essential. Plant disease detection and classification is a much-developed research area due to enormous development in machine learning (ML). Over the last ten years, computer vision researchers proposed different algorithms for plant disease identification using ML. This paper proposes an end-to-end semantic leaf segmentation model for plant disease identification. Our model uses a deep convolutional neural network based on semantic segmentation (SS). The proposed algorithm highlights diseased and healthy parts and allows the classification of ten different diseases affecting a specific plant leaf. The model successfully highlights the foreground (leaf) and background (nonleaf) regions through SS, identifying regions as healthy and diseased parts. As the semantic label is provided by the proposed method for each pixel, the information about how much area of a specific leaf is affected due to a disease is also estimated. We use tomato plant leaves as a test case in our work. We test the proposed CNN-based model on the publicly available database, PlantVillage. Along with PlantVillage, we also collected a dataset of twenty thousand images and tested our framework on it. Our proposed model obtained an average accuracy of 97.6%, which shows substantial improvement in performance on the same dataset compared to previous results. [ABSTRACT FROM AUTHOR]

Human face image analysis using machine learning is an important element in computer vision. The human face image conveys information such as age, gender, identity, emotion, race, and attractiveness to both human and computer systems. Over the last ten years, face analysis methods using machine learning have received immense attention due to their diverse applications in various tasks. Although several methods have been reported in the last ten years, face image analysis still represents a complicated challenge, particularly for images obtained from 'in the wild' conditions. This survey paper presents a comprehensive review focusing on methods in both controlled and uncontrolled conditions. Our work illustrates both merits and demerits of each method previously proposed, starting from seminal works on face image analysis and ending with the latest ideas exploiting deep learning frameworks. We show a comparison of the performance of the previous methods on standard datasets and also present some promising future directions on the topic. [ABSTRACT FROM AUTHOR]

Time series forecasting plays a significant role in numerous applications, including but not limited to, industrial planning, water consumption, medical domains, exchange rates and consumer price index. The main problem is insufficient forecasting accuracy. The present study proposes a hybrid forecasting methods to address this need. The proposed method includes three models. The first model is based on the autoregressive integrated moving average (ARIMA) statistical model; the second model is a back propagation neural network (BPNN) with adaptive slope and momentum parameters; and the third model is a hybridization between ARIMA and BPNN (ARIMA/BPNN) and artificial neural networks and ARIMA (ARIMA/ANN) to gain the benefits of linear and nonlinear modeling. The forecasting models proposed in this study are used to predict the indices of the consumer price index (CPI), and predict the expected number of cancer patients in the Ibb Province in Yemen. Statistical standard measures used to evaluate the proposed method include (i) mean square error, (ii) mean absolute error, (iii) root mean square error, and (iv) mean absolute percentage error. Based on the computational results, the improvement rate of forecasting the CPI dataset was 5%, 71%, and 4% for ARIMA/BPNN model, ARIMA/ANN model, and BPNN model respectively; while the result for cancer patients’ dataset was 7%, 200%, and 19% for ARIMA/BPNN model, ARIMA/ANN model, and BPNN model respectively. Therefore, it is obvious that the proposed method reduced the randomness degree, and the alterations affected the time series with data non-linearity. The ARIMA/ANN model outperformed each of its components when it was applied separately in terms of increasing the accuracy of forecasting and decreasing the overall errors of forecasting. [ABSTRACT FROM AUTHOR]

Coronavirus disease, which resulted from the SARS-CoV-2 virus, has spread worldwide since early 2020 and has been declared a pandemic by the World Health Organization (WHO). Coronavirus disease is also termed COVID-19. It affects the human respiratory system and thus can be traced and tracked from the Chest X-Ray images. Therefore, Chest X-Ray alone may play a vital role in identifying COVID-19 cases. In this paper, we propose a Machine Learning (ML) approach that utilizes the X-Ray images to classify the healthy and affected patients based on the patterns found in these images. The article also explores traditional, and Deep Learning (DL) approaches for COVID-19 patterns from Chest X-Ray images to predict, analyze, and further understand this virus. The experimental evaluation of the proposed approach achieves 97.5% detection performance using the DL model for COVID-19 versus normal cases. In contrast, for COVID-19 versus Pneumonia Virus scenario, we achieve 94.5% accurate detections. Our extensive evaluation in the experimental section guides and helps in the selection of an appropriate model for similar tasks. Thus, the approach can be used for medical usages and is particularly pertinent in detecting COVID-19 positive patients using X-Ray images alone. [ABSTRACT FROM AUTHOR]

A Smart Community (SC) is an essential part of the Internet of Energy (IoE), which helps to integrate Electric Vehicles (EVs) and distributed renewable energy sources in a smart grid. As a result of the potential privacy and security challenges in the distributed energy system, it is becoming a great problem to optimally schedule EVs' charging with different energy consumption patterns and perform reliable energy trading in the SC. In this paper, a blockchain-based privacy-preserving energy trading system for 5G-deployed SC is proposed. The proposed system is divided into two components: EVs and residential prosumers. In this system, a reputation-based distributed matching algorithm for EVs and a Reward-based Starvation Free Energy Allocation Policy (RSFEAP) for residential homes are presented. A short-term load forecasting model for EVs' charging using multiple linear regression is proposed to plan and manage the intermittent charging behavior of EVs. In the proposed system, identity-based encryption and homomorphic encryption techniques are integrated to protect the privacy of transactions and users, respectively. The performance of the proposed system for EVs' component is evaluated using convergence duration, forecasting accuracy, and executional and transactional costs as performance metrics. For the residential prosumers' component, the performance is evaluated using reward index, type of transactions, energy contributed, average convergence time, and the number of iterations as performance metrics. The simulation results for EVs' charging forecasting gives an accuracy of 99.25%. For the EVs matching algorithm, the proposed privacy-preserving algorithm converges faster than the bichromatic mutual nearest neighbor algorithm. For RSFEAP, the number of iterations for 50 prosumers is 8, which is smaller than the benchmark. Its convergence duration is also 10 times less than the benchmark scheme. Moreover, security and privacy analyses are presented. Finally, we carry out security vulnerability analysis of smart contracts to ensure that the proposed smart contracts are secure and bug-free against the common vulnerabilities' attacks. The results show that the smart contracts are secure against both internal and external attacks. [ABSTRACT FROM AUTHOR]

There are over 200 different varieties of dates fruit in the world. Interestingly, every single type has some very specific features that differ from the others. In recent years, sorting, separating, and arranging in automated industries, in fruits businesses, and more specifically in dates businesses have inspired many research dimensions. In this regard, this paper focuses on the detection and recognition of dates using computer vision and machine learning. Our experimental setup is based on the classical machine learning approach and the deep learning approach for nine classes of dates fruit. Classical machine learning includes the Bayesian network, Support Vector Machine, Random Forest, and Multi-Layer Perceptron (MLP), while the Convolutional Neural Network is used for the deep learning set. The feature set includes Color Layout features, Fuzzy Color and Texture Histogram, Gabor filtering, and the Pyramid Histogram of the Oriented Gradients. The fusion of various features is also extensively explored in this paper. The MLP achieves the highest detection performance with an F-measure of 0.938. Moreover, deep learning shows better accuracy than the classical machine learning algorithms. In fact, deep learning got 2% more accurate results as compared to the MLP and the Random forest. We also show that classical machine learning could give increased classification performance which could get close to that provided by deep learning through the use of optimized tuning and a good feature set. [ABSTRACT FROM AUTHOR]

COVID-19 was declared a pandemic by World Health Organization in March 2020. Since then, it has attracted the enormous attention of researchers from around the world. The world has gone through previous instances of corona-viruses such as Severe Acute Respiratory Syndrome and Middle Eastern Respiratory Syndrome. Nevertheless, none was of these were of this serious nature as COVID-19. In this research, we carry out a bibliometric analysis of coronavirus research using the Scopus database. However, we restricted ourselves to the Gulf Cooperation Council countries, comprising Bahrain, Kuwait, Oman, Qatar, Saudi Arabia, and the United Arab Emirates. The analysis was performed using Biblioshiny software. We analyzed 4288 articles written by 24226 researchers from 1994 till 2021, published in 1429 sources. The number of authors per publication is 5.65. A bulk of the research (more than 68%) appeared in the form of articles. More than 43% of the publications appeared in 2020 and more than 44% in 2021. Saudi Arabia appears the most-cited country, followed by Qatar. Journal of Infection and Public Health published the most number of papers, whereas New England Journal of Medicine is the most-cited one. Memish, Z.A. wrote the maximum number of papers. The top source, according to the H-index, is the Journal of Virology. Furthermore, the two most prolific universities are King Saud University and King Abdulaziz University, both from Saudi Arabia. The research uncovered deep learning as a niche theme used in recent publications. The research landscape continues to alter as the pandemic keeps on evolving. [ABSTRACT FROM AUTHOR]

A tremendous amount of vendor invoices is generated in the corporate sector. To automate the manual data entry in payable documents, highly accurate Optical Character Recognition (OCR) is required. This paper proposes an end-to-end OCR system that does both localization and recognition and serves as a single unit to automate payable document processing such as cheques and cash disbursement. For text localization, the maximally stable extremal region is used, which extracts a word or digit chunk from an invoice. This chunk is later passed to the deep learning model, which performs text recognition. The deep learning model utilizes both convolution neural networks and long short-termmemory (LSTM). The convolution layer is used for extracting features, which are fed to the LSTM. The model integrates feature extraction, modeling sequence, and transcription into a unified network. It handles the sequences of unconstrained lengths, independent of the character segmentation or horizontal scale normalization. Furthermore, it applies to both the lexicon-free and lexicon-based text recognition, and finally, it produces a comparatively smaller model, which can be implemented in practical applications. The overall superior performance in the experimental evaluation demonstrates the usefulness of the proposed model. The model is thus generic and can be used for other similar recognition scenarios. [ABSTRACT FROM AUTHOR]

Race classification is a long-standing challenge in the field of face image analysis. The investigation of salient facial features is an important task to avoid processing all face parts. Face segmentation strongly benefits several face analysis tasks, including ethnicity and race classification. We propose a race-classification algorithm using a prior face segmentation framework. A deep convolutional neural network (DCNN) was used to construct a face segmentation model. For training the DCNN, we label face images according to seven different classes, that is, nose, skin, hair, eyes, brows, back, andmouth. The DCNN model developed in the first phase was used to create segmentation results. The probabilistic classification method is used, and probability maps (PMs) are created for each semantic class. We investigated five salient facial features from among seven that help in race classification. Features are extracted from the PMs of five classes, and a new model is trained based on the DCNN. We assessed the performance of the proposed race classification method on four standard face datasets, reporting superior results compared with previous studies. [ABSTRACT FROM AUTHOR]

Hierarchical architecture, in combination with static structure, is a productive approach to Wireless Sensor Networks (WSNs) scalability as well as efficiency. Sensor nodes, a dual-layer framework, are extensively explored for several scenarios. This paper demonstrates the proposed novel clustering methodology representing it as the Minimum Weight Low Energy Adaptive Clustering Hierarchy (MW-LEACH). The Cluster Heads (CHs) are selected in MW-LEACH depending upon the surplus energy and the distances among them. With the proposed scheme, from the initial set, the nodes are chosen through surplus energy around the centre of the density, thus leading to the composition of the primary set of CH candidates. These candidates further accumulate data from their members by travelling in multiple directions forwarding that particular data to the BS. This specific methodology has lesser complications when it comes to message and time and is speedy and guarantees an appropriate fault tolerance level. In Matlab simulations and evaluations during the experimental phase, the proposed approach exceeds the advanced trendy protocols in reliance on performance metrics of throughput, packet delivery, energy intake, network lifespan (duration), and delays. [ABSTRACT FROM AUTHOR]

Neural networks have several useful applications in machine learning. However, benefiting from the neural-network architecture can be tricky in some instances due to the large number of parameters that can influence performance. In general, given a particular dataset, a data scientist cannot do much to improve the efficiency of the model. However, by tuning certain hyperparameters, the model's accuracy and time of execution can be improved. Hence, it is of utmost importance to select the optimal values of hyperparameters. Choosing the optimal values of hyperparameters requires experience and mastery of the machine learning paradigm. In this paper, neural network-based architectures are tested based on altering the values of hyperparameters for handwritten-based digit recognition. Various neural network-based models are used to analyze different aspects of the same, primarily accuracy based on hyperparameter values. The extensive experimentation setup in this article should, therefore, provide the most accurate and time-efficient solution models. Such an evaluation will help in selecting the optimized values of hyperparameters for similar tasks. [ABSTRACT FROM AUTHOR]

In this paper we introduce a real Pashtu handwritten numerals dataset (PHND) having 50,000 scanned images and make publicly available for research and scientific use. Although more than fifty million people in the world use this language for written and oral communication, no significant efforts are devoted to the Pashtu Optical Character Recognition (POCR). We present a new approach for Pahstu handwritten numerals recognition (PHNR) based on deep neural networks. We train Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) on high-frequency numerals for feature extraction and classification. We evaluated the performance of the proposed algorithm on the newly introduced Pashtu handwritten numerals database PHND and Bangla language number database CMATERDB 3.1.1. We obtained best recognition rate of 98.00% and 98.64% on PHND and CMATERDB 3.1.1. respectively. [ABSTRACT FROM AUTHOR]

Processing big data requires serious computing resources. Because of this challenge, big data processing is an issue not only for algorithms but also for computing resources. This article analyzes a large amount of data from different points of view. One perspective is the processing of reduced collections of big data with less computing resources. Therefore, the study analyzed 40 GB data to test various strategies to reduce data processing. Thus, the goal is to reduce this data, but not to compromise on the detection and model learning in machine learning. Several alternatives were analyzed, and it is found that in many cases and types of settings, data can be reduced to some extent without compromising detection efficiency. Tests of 200 attributes showed that with a performance loss of only 4%, more than 80% of the data could be ignored. The results found in the study, thus provide useful insights into large data analytics. [ABSTRACT FROM AUTHOR]

The authors propose a novel multiple weight low energy adaptive clustering hierarchy (MW‐LEACH) protocol for wireless sensor networks. In MW‐LEACH, they select the cluster heads (CHs) based on the residual energy, the distances between the CHs, and an optimal number of member nodes. The nodes are selected from the initial set based on the high residual energy closer to the centre of the density, thus forming an initial set of CH candidates. The candidates then move in different directions to collect data from their members sending it to the base station. The proposed approach has lower complexity in terms of time and message. It is also fast and offers a longer lifetime for the network. It also provides a proper level of fault tolerance. In the experimental simulation evaluation, their approach outperforms state‐of‐the‐art protocols based on performance metrics of throughput, energy consumption, packet delivery, network lifetime, and latency. [ABSTRACT FROM AUTHOR]

: Human face image analysis is an active research area within computer vision. In this paper we propose a framework for face image analysis, addressing three challenging problems of race, age, and gender recognition through face parsing. We manually labeled face images for training an end-to-end face parsing model through Deep Convolutional Neural Networks. The deep learning-based segmentation model parses a face image into seven dense classes. We use the probabilistic classification method and created probability maps for each face class. The probability maps are used as feature descriptors. We trained another Convolutional Neural Network model by extracting features from probability maps of the corresponding class for each demographic task (race, age, and gender). We perform extensive experiments on state-of-the-art datasets and obtained much better results as compared to previous results. [ABSTRACT FROM AUTHOR]

Background and motivation: Every year, millions of Muslims worldwide come to Mecca to perform the Hajj. In order to maintain the security of the pilgrims, the Saudi government has installed about 5000 closed circuit television (CCTV) cameras to monitor crowd activity efficiently. Problem: As a result, these cameras generate an enormous amount of visual data through manual or offline monitoring, requiring numerous human resources for efficient tracking. Therefore, there is an urgent need to develop an intelligent and automatic system in order to efficiently monitor crowds and identify abnormal activity. Method: The existing method is incapable of extracting discriminative features from surveillance videos as pre-trained weights of different architectures were used. This paper develops a lightweight approach for accurately identifying violent activity in surveillance environments. As the first step of the proposed framework, a lightweight CNN model is trained on our own pilgrim's dataset to detect pilgrims from the surveillance cameras. These preprocessed salient frames are passed to a lightweight CNN model for spatial features extraction in the second step. In the third step, a Long Short Term Memory network (LSTM) is developed to extract temporal features. Finally, in the last step, in the case of violent activity or accidents, the proposed system will generate an alarm in real time to inform law enforcement agencies to take appropriate action, thus helping to avoid accidents and stampedes. Results: We have conducted multiple experiments on two publicly available violent activity datasets, such as Surveillance Fight and Hockey Fight datasets; our proposed model achieved accuracies of 81.05 and 98.00, respectively. [ABSTRACT FROM AUTHOR]

Crowd counting is an active research area within scene analysis. Over the last 20 years, researchers proposed various algorithms for crowd counting in real-time scenarios due to many applications in disaster management systems, public events, safety monitoring, and so on. In our paper, we proposed an end-to-end semantic segmentation framework for crowd counting in a dense crowded image. Our proposed framework was based on semantic scene segmentation using an optimized convolutional neural network. The framework successfully highlighted the foreground and suppressed the background part. The framework encoded the high-density maps through a guided attention mechanism system. We obtained crowd counting through integrating the density maps. Our proposed algorithm classified the crowd counting in each image into groups to adapt the variations occurring in crowd counting. Our algorithm overcame the scale variations of a crowded image through multi-scale features extracted from the images. We conducted experiments with four standard crowd-counting datasets, reporting better results as compared to previous results. [ABSTRACT FROM AUTHOR]

Real time crowd analysis represents an active area of research within the computer vision community in general and scene analysis in particular. Over the last 10 years, various methods for crowd management in real time scenario have received immense attention due to large scale applications in people counting, public events management, disaster management, safety monitoring an so on. Although many sophisticated algorithms have been developed to address the task; crowd management in real time conditions is still a challenging problem being completely solved, particularly in wild and unconstrained conditions. In the proposed paper, we present a detailed review of crowd analysis and management, focusing on state-of-the-art methods for both controlled and unconstrained conditions. The paper illustrates both the advantages and disadvantages of state-of-the-art methods. The methods presented comprise the seminal research works on crowd management, and monitoring and then culminating state-of-the-art methods of the newly introduced deep learning methods. Comparison of the previous methods is presented, with a detailed discussion of the direction for future research work. We believe this review article will contribute to various application domains and will also augment the knowledge of the crowd analysis within the research community. [ABSTRACT FROM AUTHOR]

This work presents a double asymmetric data hiding technique. The first asymmetry is created by hiding secret data in the complex region of the cover image and keep the smooth region unaffected. Then another asymmetry is developed by hiding a different number of secret bits in the various pixels of the complex region. The proposed technique uses the ant colony optimization (ACO) based technique for the classification of complex and smooth region pixels. Then, the variable least significant bits (VLSB) data hiding framework is used to hide secret bits in the complex region of the cover image. A distance-based substitution technique, namely increasing distance increasing bits substitution algorithm, is used to ensure the asymmetry in the number of hidden bits. The double asymmetric framework enhances the security of the hidden secret data and makes the retrieval of hidden information difficult for unauthorized users. The algorithm results in high-quality stego images, and the hidden information does not attract the human visual system (HVS). [ABSTRACT FROM AUTHOR]

The increase in the internal temperature of high voltage electrical instruments is due to a variety of factors, particularly, contact problems; environmental factors; unbalanced loads; and cracks in the high voltage current transformers, voltage transformers, insulators, or terminal junctions. This increase in the internal temperature can cause unusual disturbances and damage to high voltage electrical equipment. Therefore, early prevention measures of thermal anomalies in equipment are necessary to prevent high voltage equipment failure that might shut down the whole grid system. In this article, we propose a novel non-destructive approach to defect analysis in high voltage equipment by taking advantage of the infrared thermography and the deep learning (DL) approach from the machine learning paradigm. The infrared images of the components were captured using the FLIR T630 without disturbing the operations of the power grid. In the first stage, rich features maps from the convolutional layers of the AlexNet pretrained model were extracted. After feature extraction, the random forest (RF) and support vector machines (SVM) were trained for learning of the defective and non-defective high voltage electrical equipment. In an experimental analysis, the RF optimally learned the separation between defective and non-defective equipment with greater than 96% accuracy, outperforming all the other comparative approaches for deep and nondeep features. The proposed approach based on the RF is reliable and shows its efficacy for fault detection in high voltage electrical equipment. [ABSTRACT FROM AUTHOR]

Accurate face segmentation strongly benefits the human face image analysis problem. In this paper we propose a unified framework for face image analysis through end-to-end semantic face segmentation. The proposed framework contains a set of stack components for face understanding, which includes head pose estimation, age classification, and gender recognition. A manually labeled face data-set is used for training the Conditional Random Fields (CRFs) based segmentation model. A multi-class face segmentation framework developed through CRFs segments a facial image into six parts. The probabilistic classification strategy is used, and probability maps are generated for each class. The probability maps are used as features descriptors and a Random Decision Forest (RDF) classifier is modeled for each task (head pose, age, and gender). We assess the performance of the proposed framework on several data-sets and report better results as compared to the previously reported results. [ABSTRACT FROM AUTHOR]