ABSTRACT A face‐swapping framework is designed to generate an image or video that merges the pose and characteristics of the input image with the identity from the source image. It has found significant applications in entertainment, privacy protection and digital content creation. However, this process is inherently complex, involving challenges like identity preservation, expression consistency and photorealism. Despite the rapid advancements in face‐swapping technology, there has been a noticeable lack of in‐depth analysis of the intricate mechanisms and recent developments in this field. This work attempts to bridge that gap by providing an extensive overview of face‐swapping methods based on deep learning. Researchers, developers and practitioners interested in learning about the state of face‐swapping technology and its possible uses may find this survey to be an invaluable resource. It will provide insights that can inform future research and innovation in this fast‐evolving area.

In the modern digital world, social media has become essential for interpersonal interaction by promoting the interchange of ideas and points of view. But there are difficulties in this digital environment, especially concerning rude behavior and offensive remarks. To address both problems at once, the research focuses on sentiment analysis and abusive comment detection in social media interactions. The dataset contains Hate Speech and Offensive Content Identification (HASOC) data from 2019 to 2021 to identify hate speech in Hindi on various social media platforms. To categorize comments into abusive and non-abusive groups, several BERT models, including mBERT, DistilBERT, RoBERTa, HateBERT, and IndicBERT, have been utilized. Additionally, a comprehensive sentiment analysis of the derogatory comments has been performed. The research presents a stacked ensemble framework for binary (abusive and non-abusive) and multiclass (hate, offensive, and profane) classification that integrates predictions from mBERT, HateBERT, and IndicBERT models. Further, the study provides an integrated approach for providing abusive comment detection and sentiment analysis using a multi-output model. The proposed ensemble model achieves 94% accuracy in binary classification, with precision, recall, and F1 scores all approaching 94%. Multiclass ensemble models yield an accuracy of 93% and associated precision, recall, and F1 scores of 91%, 92%, and 92%, respectively. A comparative analysis using several state-of-the-art techniques has been generated to verify the efficacy of the suggested methodology.

Abstract Among the sectors that deep learning has transformed, deepfake, a novel method of manipulating multimedia, deserves particular attention. The long‐term objective of many researchers is to seamlessly mimic human facial movement or whole‐body activity, referred to as reenactment. Deepfake progress has made this goal much more feasible in recent years. Yet, achieving more realistic facial and body reenactment remains a challenging task. The primary focus of this study is to explore the current capability of the reenactment techniques and expand them further to attain greater results. The analysis offers a thorough overview of the various techniques involved, the challenges addressed, the datasets utilized, and the metrics employed by the underlying methods of reenactment technologies. The study also addresses the potential risks and their mitigating strategies to ensure responsible reenactment techniques. To the best of the authors' knowledge, this is the first survey paper that delves deeper into the topic of deepfake reenactment.

Summary The recent advancements in computer vision and deep learning have led to promising progress in various motion detection and gesture recognition methods. Thriving efforts in the field of sign language recognition (SLR) during recent years led to interaction between humans and computer systems. Contributing a real‐time automated Sign Language recognition system will be a remarkable treasure for hearing and speech‐impaired people that will break the barriers of interaction with the real world. Albeit several research works are accomplished in sign language recognition, there is still a demand for developing a real‐time automated sign language recognition system. Compared to other methodologies, the techniques adopted may have advantages and disadvantages, and they vary from researcher to researcher. There are still some issues with employing these SLR models and procedures regularly, even though numerous research studies have been conducted to determine the most acceptable methods and models for sign language recognition. It gets more expensive and difficult in terms of resources when the developed automated SLR system becomes available as a product. Hence, for the welfare of the hearing and speech‐impaired community, the researchers are still endeavoring way to find a cost‐effective method. This work brings forth the challenges faced by scientists in developing a cost‐effective commercial prototype for the hearing and speech‐impaired community. This paper also explores and analyses various deep learning techniques and methods used in developing a sign language recognition system. The objective behind this work is to identify the best method which produces high accuracy in developing a cost‐effective sign language recognition system aiding communication between signers and non‐signers so that they can be a part of growing technology.

Abstract Breast cancer is possibly the deadliest illness in the world and the risks are gradually increasing. One out of eight women has the chance to be detected with breast cancer in their lifetime. The utmost cause for the higher fatality rates is the prolonged prognosis for the detection of breast cancer. The focus of this study is therefore to develop a better fuzzy expert system for the detection of breast cancer using decision tree analysis for deriving the rule base. For this classification problem, the input features of the dataset are converted into human‐understandable terms‐linguistic variables. The Mamdani Fuzzy Rule‐Based system is deployed as the main inference engine and the centroid method for the defuzzification process to convert the final fuzzy score into class labels‐ benign (not cancerous) or malignant (cancerous). A decision tree algorithm is applied the creating a novel set of 27 fuzzy rules which are fed into FRBS. The investigation is performed on the publicly available Wisconsin Breast Cancer Dataset. The accuracy obtained by the proposed system is about 97%, recall is 99.58% and precision is about 93%. The experiments on this dataset yield higher performance as compared to the state‐of‐the‐art dataset.

Abstract Breast carcinoma is a sort of malignancy that begins in the breast. Breast malignancy cells generally structure a tumour that can routinely be seen on an x‐ray or felt like a lump. Despite advances in screening, treatment, and observation that have improved patient endurance rates, breast carcinoma is the most regularly analyzed malignant growth and the subsequent driving reason for malignancy mortality among ladies. Invasive ductal carcinoma is the most boundless breast malignant growth with about 80% of all analyzed cases. It has been found from numerous types of research that artificial intelligence has tremendous capabilities, which is why it is used in various sectors, especially in the healthcare domain. In the initial phase of the medical field, mammography is used for diagnosis, and finding cancer in the case of a dense breast is challenging. The evolution of deep learning and applying the same in the findings are helpful for earlier tracking and medication. The authors have tried to utilize the deep learning concepts for grading breast invasive ductal carcinoma using Transfer Learning in the present work. The authors have used five transfer learning approaches here, namely VGG16, VGG19, InceptionReNetV2, DenseNet121, and DenseNet201 with 50 epochs in the Google Colab platform which has a single 12GB NVIDIA Tesla K80 graphical processing unit (GPU) support that can be used up to 12 h continuously. The dataset used for this work can be openly accessed from http://databiox.com . The experimental results that the authors have received regarding the algorithm's accuracy are as follows: VGG16 with 92.5%, VGG19 with 89.77%, InceptionReNetV2 with 84.46%, DenseNet121 with 92.64%, DenseNet201 with 85.22%. From the experimental results, it is clear that the DenseNet121 gives the maximum accuracy in terms of cancer grading, whereas the InceptionReNetV2 has minimal accuracy.

The papers in this special section focus on federal learning applications for the Internet of Medical Things. Due to to the advancements in Internet of Medical Things (IoMT), wearable devices, remote monitoring of patients is possible like never before. Machine learning and deep learning techniques help the doctors immensely in remotely diagnosing the patients by learning the patterns from the data generated through these devices [1]. The main problem with traditional machine learning (ML)/deep learning (DL) models is that the data from the individual devices, sensors, wearables of patients have to be transferred to the central servers to train the data using the ML/DL models. Due to the sensitive nature of the healthcare data, the aforementioned approach of transferring the patients’ data to the central servers may create serious security and privacy issues.

The papers in this special issue focus on advanced wearable sensor technologies for monitoring and disease prediction. The seamless integration of sensor technologies with the smart healthcare infrastructure has leveraged the sensing and communication capabilities to monitor patient’s health parameters remotely through various wearable/medical sensors. Advanced sensor technologies enable various types of smart healthcare applications, including diagnosing the symptomatic/ asymptomatic patients’ health condition, health symptoms forecasting, disease prediction and analysis, and ontologybased recommendation. Advancements in wearable sensors and communication technologies (6G/5G and-beyond) enable the design of smart healthcare frameworks and efficiently analyzing the sensing parameters. Besides that, advanced AI-enabled technologies, including machine learning and deep learning algorithms, come into play to analyze the sensed data at remote computing devices for disease prediction and diagnosis. This special issue focus on discussions and insights into the latest advancements and technologies pertaining to these technologies.

Atrial fibrillation (AF) is one of the clinic's most common arrhythmias with high morbidity and mortality. Developing an intelligent auxiliary diagnostic model of AF based on a body surface electrocardiogram (ECG) is necessary. Convolutional neural network (CNN) is one of the most commonly used models for AF recognition. However, typical CNN is not compatible with variable-duration ECG, so it is hard to demonstrate its universality and generalization in practical applications. Hence, this paper proposes a novel Time-adaptive densely network named MP-DLNet-F. The MP-DLNet module solves the problem of incompatibility between variable-duration ECG and 1D-CNN. In addition, the feature enhancement module and data imbalance processing module are respectively used to enhance the perception of temporal-quality information and decrease the sensitivity to data imbalance. The experimental results indicate that the proposed MP-DLNet-F achieved 87.98% classification accuracy, and F1-score of 0.847 on the CinC2017 database for 10-second cropped/padded single-lead ECG fragments. Furthermore, we deploy transfer learning techniques to test heterogeneous datasets, and in the CPSC2018 12-lead dataset, the method improved the average accuracy and F1-score by 21.81% and 16.14%, respectively. Experimental results indicate that our method can update the constructed model's parameters and precisely forecast AF with different duration distributions and lead distributions. Combining these advantages, MP-DLNet-F can exemplify all kinds of varied-duration or imbalance medical signal processing problems such as Electroencephalogram (EEG) and Photoplethysmography (PPG).

Abstract World Health Organization recognized COVID‐19 as a pandemic on March 11, 2020. A total of 213 countries and territories around the world have reported a total of 27,948,441 confirmed cases as on September 9, 2020. This article adopted two non‐linear growth models (Gompertz, Verhulst) and exponential model (SIR) to analyse the coronavirus pandemic across the world. All the models have been used for active COVID‐19 patients predictions based on the data collected from John Hopkins University repository in the time period of January 30, 2020 to June 4, 2020. Outbreak of COVID‐19 disease has been analysed for India, Pakistan, Myanmar (Burma), Brazil, Italy and Germany till June 4, 2020 and predictions have been made for the number of positive cases for the next 28 days. Verhulst model fitting effect is better than Gompertz and SIR model with R‐score 0.9973. The proposed model perform better as compare to other three existing models with R‐score 0.9981.These above models can be adapted to forecast in long term intervals, based on the predictions for a short interval as of June 5, 2020 and June 30, 2020, active COVID‐19 patients for India, Pakistan, Italy, Germany, Brazil and Myanmar predicted as (236,170, 88,998, 234,066, 184,922, 645,057 and 235) and (486,357, 218,864, 240,545, 193,727, 1,211,567 and 309).

Abstract In the field of cytogenetics, chromosome image analysis or karyotyping from metaphase images plays an imperative role in the diagnosis, prognosis and treatment assessment of different genetic disorders and cancers. This paper is a comprehensive review on different traditional and deep‐based techniques, which are utilized in the design of automated karyotyping systems (AKSs). By this review, a detailed methodology is suggested for the design of end‐to‐end automated karyotyping system (EEAKS) which portrays a sequential multi stage approach. Methods related to all the stages in EEAKS are systematically surveyed by exploring the state of the art literature. Datasets and performance measures incorporated in the past studies are explored. Even though numerous methods were proposed throughout the past three decades, a completely automated framework has not yet been acknowledged. Inferences from this study show that, while various traditional image processing strategies are utilized for pre‐processing and segmentation, machine learning techniques are used only for the classification purpose. In conventional classifiers, artificial neural networks are generally utilized even when the peak performance is given by support vector machines. However, owing to the recent prodigious breakthrough in computer vision, deep neural networks are progressively utilized for developing automated systems. It is seen that deep neural networks are not yet explored in the realm of pre‐processing stage of EEAKS. However, limited number of methods based on convolutional neural networks (CNN) are utilized in all other stages. This review recommends a hybrid CNN for the design of EEAKS, in which all the stages can be automated by sub CNNs. Methodology for generating sufficient datasets is also discussed here which is, indeed, required for further research in this area. This paper concludes with future research directions for the development of a fully automated end‐to‐end karyotyping system.

In this paper problem of offline signature verification has been discussed with a novel high-performance convolution Siamese network. The paper proposes modifications in the already existing convolution Siamese network. The proposed method makes use of the Batch Normalization technique instead of Local Response Normalization to achieve better accuracy. The regularization factor has been added in the fully connected layers of the convolution neural network to deal with the problem of overfitting. Apart from this, a wide range of learning rates are provided during the training of the model and optimal one having the least validation loss is used. To evaluate the proposed changes and compare the results with the existing solution, our model is validated on three benchmarks datasets viz. CEDAR, BHSig260, and GPDS Synthetic Signature Corpus. The evaluation is done via two methods firstly by Test-Train validation and then by K-fold cross-validation (K = 5), to test the skill of our model. We show that the proposed modified Siamese network outperforms all the prior results for offline signature verification. One of the major advantages of our system is its capability of handling an unlimited number of new users which is the drawback of many research works done in the past.

In the present times, artificial-intelligence based techniques are considered as one of the prominent ways to classify images which can be conveniently leveraged in the real-world scenarios. This technology can be extremely beneficial to the lepidopterists, to assist them in classification of the diverse species of Rhopalocera, commonly called as butterflies. In this article, image classification is performed on a dataset of various butterfly species, facilitated via the feature extraction process of the Convolutional Neural Network (CNN) along with leveraging the additional features calculated independently to train the model. The classification models deployed for this purpose predominantly include K-Nearest Neighbors (KNN), Random Forest and Support Vector Machine (SVM). However, each of these methods tend to focus on one specific class of features. Therefore, an ensemble of multiple classes of features used for classification of images is implemented. This research paper discusses the results achieved from the classification performed on basis of two different classes of features i.e., structure and texture. The amalgamation of the two specified classes of features forms a combined data set, which has further been used to train the Growing Convolutional Neural Network (GCNN), resulting in higher accuracy of the classification model. The experiment performed resulted in promising outcomes with TP rate, FP rate, Precision, recall and F-measure values as 0.9690, 0.0034, 0.9889, 0.9692 and 0.9686 respectively. Furthermore, an accuracy of 96.98% was observed by the proposed methodology.

Covid-19 is a rapidly spreading viral disease that infects not only humans, but animals are also infected because of this disease. The daily life of human beings, their health, and the economy of a country are affected due to this deadly viral disease. Covid-19 is a common spreading disease, and till now, not a single country can prepare a vaccine for COVID-19. A clinical study of COVID-19 infected patients has shown that these types of patients are mostly infected from a lung infection after coming in contact with this disease. Chest x-ray (i.e., radiography) and chest CT are a more effective imaging technique for diagnosing lunge related problems. Still, a substantial chest x-ray is a lower cost process in comparison to chest CT. Deep learning is the most successful technique of machine learning, which provides useful analysis to study a large amount of chest x-ray images that can critically impact on screening of Covid-19. In this work, we have taken the PA view of chest x-ray scans for covid-19 affected patients as well as healthy patients. After cleaning up the images and applying data augmentation, we have used deep learning-based CNN models and compared their performance. We have compared Inception V3, Xception, and ResNeXt models and examined their accuracy. To analyze the model performance, 6432 chest x-ray scans samples have been collected from the Kaggle repository, out of which 5467 were used for training and 965 for validation. In result analysis, the Xception model gives the highest accuracy (i.e., 97.97%) for detecting Chest X-rays images as compared to other models. This work only focuses on possible methods of classifying covid-19 infected patients and does not claim any medical accuracy.

Abstract Biometric systems are widely used in applications such as forensics and military. Biometric authentication is a challenging and complex task. These biometric systems must be accurate for practical applications. In this era of artificial intelligence, artificial neural network‐based classifiers are widely used in biometric‐based systems. However, most of the artificial neural network‐based classifiers are less accurate and computationally complex. In this work, two modified self‐organising map (SOM) networks are proposed for iris image classification to improve the performance measures. Particle swarm optimization technique is used in the training process of conventional SOM. The experiments are carried out with conventional and modified classifiers. The proposed modified classifiers provide better performance than the conventional SOM classifier.

The statistics highlights that physical rehabilitation are required nowadays by increased number of people that are affected by motor impairments caused by accidents or aging. Among the most common causes of disability in adults are strokes or cerebral palsy. To reduce the costs preserving the quality of services new solutions based on current technologies in the area of physiotherapy are emerging. The remote monitoring of physical training sessions could facilitate for physicians and physical therapists' information about training outcome that may be useful to personalize the exercises helping the patients to achieve better rehabilitation results in short period of time process. This research work aims to apply physical rehabilitation monitoring combining Virtual Reality serious games and Wearable Sensor Network to improve the patient engagement during physical rehabilitation and evaluate their evolution. Serious games based on different scenarios of Virtual Reality, allows a patient with motor difficulties to perform exercises in a highly interactive and non-intrusive way, using a set of wearable devices, contributing to their motivational process of rehabilitation. The system implementation, system validation and experimental results are included in the paper.

Abstract The role of gesture recognition is significant in areas like human‐computer interaction, sign language, virtual reality, machine vision, etc. Among various gestures of the human body, hand gestures play a major role to communicate nonverbally with the computer. As the hand gesture is a continuous pattern with respect to time, the hidden Markov model (HMM) is found to be the most suitable pattern recognition tool, which can be modeled using the hand gesture parameters. The HMM considers the speeded up robust feature features of hand gesture and uses them to train and test the system. Conventionally, the Viterbi algorithm has been used for training process in HMM by discovering the shortest decoded path in the state diagram. The recursiveness of the Viterbi algorithm leads to computational complexity during the execution process. In order to reduce the complexity, the state sequence analysis approach is proposed for training the hand gesture model, which provides a better recognition rate and accuracy than that of the Viterbi algorithm. The performance of the proposed approach is explored in the context of pattern recognition with the Cambridge hand gesture data set.

Abstract Artificial neural network (ANN) is one of the commonly used tools for computational applications. The specific advantages of ANN are high accuracy, less convergence time, less computational complexity, and so forth. However, all these merits are not available in the same ANN. Even though back propagation neural (BPN) networks are accurate, their computational complexity is significantly high. BPN networks are also not stable. On the other hand, Hopfield neural network (HNN) is better than BPN in terms of computational efficiency. But the accuracy of HNN is low. In this work, a modified ANN is proposed to overcome this specific problem. The modified ANN is a fusion of BPN and HNN. The technical concepts of BPN and HNN are mixed in the training algorithm of the proposed back propagation‐Hopfield network (BPHN). The objective of this fusion is to improve the performance of conventional ANN. Magnetic resonance brain image classification experiments are used to analyse the proposed BPHN. Experimental results have suggested improvement in the learning process of the proposed BPHN. A comparative analysis with the conventional networks is performed to validate the performance of the proposed approach.