Epilepsy is a common brain disorder that causes patients to face multiple seizures in a single day. Around 65 million people are affected by epilepsy worldwide. Patients with focal epilepsy can be treated with surgery, whereas generalized epileptic seizures can be managed with medications. It has been noted that in more than 30% of cases, these medications fail to control epileptic seizures, resulting in accidents and limiting the patient’s life. Predicting epileptic seizures in such patients prior to the commencement of an oncoming seizure is critical so that the seizure can be treated with preventive medicines before it occurs. Electroencephalogram (EEG) signals of patients recorded to observe brain electrical activity during a seizure can be quite helpful in predicting seizures. Researchers have proposed methods that use machine and/or deep learning techniques to predict epileptic seizures using scalp EEG signals; however, prediction of seizures with increased accuracy is still a challenge. Therefore, we propose a three-step approach. It includes preprocessing of scalp EEG signals with PREP pipeline, which is a more sophisticated alternative to basic notch filtering. This method uses a regression-based technique to further enhance the SNR, with a combination of handcrafted, i.e., statistical features such as temporal mean, variance, and skewness, and automated features using CNN, followed by classification of interictal state and preictal state segments using LSTM to predict seizures. We train and validate our proposed technique on the CHB-MIT scalp EEG dataset and achieve accuracy of 94%, sensitivity of 93.8%, and 91.2% specificity. The proposed technique achieves better sensitivity and specificity than existing methods.

Internet of Things (IoT) devices usage is increasing exponentially with the spread of the internet. With the increasing capacity of data on IoT devices, these devices are becoming venerable to malware attacks; therefore, malware detection becomes an important issue in IoT devices. An effective, reliable, and time-efficient mechanism is required for the identification of sophisticated malware. Researchers have proposed multiple methods for malware detection in recent years, however, accurate detection remains a challenge. We propose a deep learning-based ensemble classification method for the detection of malware in IoT devices. It uses a three steps approach; in the first step, data is preprocessed using scaling, normalization, and de-noising, whereas in the second step, features are selected and one hot encoding is applied followed by the ensemble classifier based on CNN and LSTM outputs for detection of malware. We have compared results with the state-of-the-art methods and our proposed method outperforms the existing methods on standard datasets with an average accuracy of 99.5%.

Multimodal hateful social media meme detection is an important and challenging problem in the vision-language domain. Recent studies show high accuracy for such multimodal tasks due to datasets that provide better joint multimodal embedding to narrow the semantic gap. Religiously hateful meme detection is not extensively explored among published datasets. While there is a need for higher accuracy on religiously hateful memes, deep learning–based models often suffer from inductive bias. This issue is addressed in this work with the following contributions. First, a religiously hateful memes dataset is created and published publicly to advance hateful religious memes detection research. Over 2000 meme images are collected with their corresponding text. The proposed approach compares and fine-tunes VisualBERT pre-trained on the Conceptual Caption (CC) dataset for the downstream classification task. We also extend the dataset with the Facebook hateful memes dataset. We extract visual features using ResNeXT-152 Aggregated Residual Transformations–based Masked Regions with Convolutional Neural Networks (R-CNN) and Bidirectional Encoder Representations from Transformers (BERT) uncased for textual encoding for the early fusion model. We use the primary evaluation metric of an Area Under the Operator Characters Curve (AUROC) to measure model separability. Results show that the proposed approach has a higher AUROC score of 78%, proving the model’s higher separability performance and an accuracy of 70%. It shows comparatively superior performance considering dataset size and against ensemble-based machine learning approaches.

Alzheimer's disease (AD) affects millions of individuals worldwide and is considered a serious global health issue due to its gradual neuro-degenerative effects on cognitive abilities such as memory, thinking, and behavior. There is no cure for this disease but early detection along with a supportive care plan may aid in improving the quality of life for patients. Automated detection of AD is challenging because its symptoms vary in patients due to genetic, environmental, or other co-existing health conditions. In recent years, multiple researchers have proposed automated detection methods for AD using MRI and fMRI. These approaches are expensive, have poor temporal resolution, do not offer real-time insights, and have not proven to be very accurate. In contrast, only a limited number of studies have explored the potential of Electroencephalogram (EEG) signals for AD detection. In contrast, Electroencephalogram (EEG) signals present a cost-effective, non-invasive, and high-temporal-resolution alternative for AD detection. Despite their potential, the application of EEG signals in AD research remains under-explored. This study reviews publicly available EEG datasets, the variety of machine learning models developed for automated AD detection, and the performance metrics achieved by these methods. It provides a critical analysis of existing approaches, highlights challenges, and identifies key areas requiring further investigation. Key findings include a detailed evaluation of current methodologies, prevailing trends, and potential gaps in the field. What sets this work apart is its in-depth analysis of EEG signals for Alzheimer's Disease detection, providing a stronger and more reliable foundation for understanding the potential role of EEG in this area.

The present era is facing the industrial revolution. Machine-to-Machine (M2M) communication paradigm is becoming prevalent. Resultantly, the computational capabilities are being embedded in everyday objects called things. When connected to the internet, these things create an Internet of Things (IoT). However, the things are resource-constrained devices that have limited computational power. The connectivity of the things with the internet raises the challenges of the security. The user sensitive information processed by the things is also susceptible to the trusability issues. Therefore, the proliferation of cybersecurity risks and malware threat increases the need for enhanced security integration. This demands augmenting the things with state-of-the-art deep learning models for enhanced detection and protection of the user data. Existingly, the deep learning solutions are overly complex, and often overfitted for the given problem. In this research, our primary objective is to investigate a lightweight deep-learning approach maximizes the accuracy scores with lower computational costs to ensure the applicability of real-time malware monitoring in constrained IoT devices. We used state-of-the-art Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), and Bi-directional LSTM deep learning algorithm on a vanilla configuration trained on a standard malware dataset. The results of the proposed approach show that the simple deep neural models having single dense layer and a few hundred trainable parameters can eliminate the model overfitting and achieve up to 99.45% accuracy, outperforming the overly complex deep learning models.

Human activity recognition (HAR) is pivotal in advancing applications ranging from healthcare monitoring to interactive gaming. Traditional HAR systems, primarily relying on single data sources, face limitations in capturing the full spectrum of human activities. This study introduces a comprehensive approach to HAR by integrating two critical modalities: RGB imaging and advanced pose estimation features. Our methodology leverages the strengths of each modality to overcome the drawbacks of unimodal systems, providing a richer and more accurate representation of activities. We propose a two-stream network that processes skeletal and RGB data in parallel, enhanced by pose estimation techniques for refined feature extraction. The integration of these modalities is facilitated through advanced fusion algorithms, significantly improving recognition accuracy. Extensive experiments conducted on the UTD multimodal human action dataset (UTD MHAD) demonstrate that the proposed approach exceeds the performance of existing state-of-the-art algorithms, yielding improved outcomes. This study not only sets a new benchmark for HAR systems but also highlights the importance of feature engineering in capturing the complexity of human movements and the integration of optimal features. Our findings pave the way for more sophisticated, reliable, and applicable HAR systems in real-world scenarios.