Ransomware attacks on cloud-encrypted data pose a significant risk to the security and privacy of cloud-based businesses and their consumers. We present RANSOMNET+, a state-of-the-art hybrid model that combines Convolutional Neural Networks (CNNs) with pre-trained transformers, to efficiently take on the challenging issue of ransomware attack classification. RANSOMNET+ excels over other models because it combines the greatest features of both architectures, allowing it to capture hierarchical features and local patterns. Our findings demonstrate the exceptional capabilities of RANSOMNET+. The model had a fantastic precision of 99.5%, recall of 98.5%, and F1 score of 97.64%, and attained a training accuracy of 99.6% and a testing accuracy of 99.1%. The loss values for RANSOMNET+ were impressively low, ranging from 0.0003 to 0.0035 throughout training and testing. We tested our model against the industry standard, ResNet 50, as well as the state-of-the-art, VGG 16. RANSOMNET+ excelled over the other two models in terms of F1 score, accuracy, precision, and recall. The algorithm’s decision-making process was also illuminated by RANSOMNET+’s interpretability analysis and graphical representations. The model’s openness and usefulness were improved by the incorporation of feature distributions, outlier detection, and feature importance analysis. Finally, RANSOMNET+ is a huge improvement in cloud safety and ransomware research. As a result of its unrivaled accuracy and resilience, it provides a formidable line of defense against ransomware attacks on cloud-encrypted data, keeping sensitive information secure and ensuring the reliability of cloud-stored data. Cybersecurity professionals and cloud service providers now have a reliable tool to combat ransomware threats thanks to this research.

Autism spectrum disorder (ASD) is a complex neurodevelopmental disorder characterized by difficulties in social communication and repetitive behaviors. The exact causes of ASD remain elusive and likely involve a combination of genetic, environmental, and neurobiological factors. Doctors often face challenges in accurately identifying ASD early due to its complex and diverse presentation. Early detection and intervention are crucial for improving outcomes for individuals with ASD. Early diagnosis allows for timely access to appropriate interventions, leading to better social and communication skills development. Artificial intelligence techniques, particularly facial feature extraction using machine learning algorithms, display promise in aiding the early detection of ASD. By analyzing facial expressions and subtle cues, AI models identify patterns associated with ASD features. This study developed various hybrid systems to diagnose facial feature images for an ASD dataset by combining convolutional neural network (CNN) features. The first approach utilized pre-trained VGG16, ResNet101, and MobileNet models. The second approach employed a hybrid technique that combined CNN models (VGG16, ResNet101, and MobileNet) with XGBoost and RF algorithms. The third strategy involved diagnosing ASD using XGBoost and an RF based on features of VGG-16-ResNet101, ResNet101-MobileNet, and VGG16-MobileNet models. Notably, the hybrid RF algorithm that utilized features from the VGG16-MobileNet models demonstrated superior performance, reached an AUC of 99.25%, an accuracy of 98.8%, a precision of 98.9%, a sensitivity of 99%, and a specificity of 99.1%.

Anomalous driving behavior detection is becoming more popular since it is vital in ensuring the safety of drivers and passengers in vehicles. Road accidents happen for various reasons, including health, mental stress, and fatigue. It is critical to monitor abnormal driving behaviors in real time to improve driving safety, raise driver awareness of their driving patterns, and minimize future road accidents. Many symptoms appear to show this condition in the driver, such as facial expressions or abnormal actions. The abnormal activity was among the most common causes of road accidents, accounting for nearly 20% of all accidents, according to international data on accident causes. To avoid serious consequences, abnormal driving behaviors must be identified and avoided. As it is difficult to monitor anyone continuously, automated detection of this condition is more effective and quicker. To increase drivers’ recognition of their driving behaviors and prevent potential accidents, a precise monitoring approach that detects abnormal driving behaviors and identifies abnormal driving behaviors is required. The most common activities performed by the driver while driving is drinking, eating, smoking, and calling. These types of driver activities are considered in this work, along with normal driving. This study proposed deep learning-based detection models for recognizing abnormal driver actions. This system is trained and tested using a newly created dataset, including five classes. The main classes include Driver-smoking, Driver-eating, Driver-drinking, Driver-calling, and Driver-normal. For the analysis of results, pre-trained and fine-tuned CNN models are considered. The proposed CNN-based model and pre-trained models ResNet101, VGG-16, VGG-19, and Inception-v3 are used. The results are compared by using the performance measures. The results are obtained 89%, 93%, 93%, 94% for pre-trained models and 95% by using the proposed CNN-based model. Our analysis and results revealed that our proposed CNN base model performed well and could effectively classify the driver’s abnormal behavior.

The research study provides a comprehensive bibliometric assessment in the field of Software Testing (ST). The dynamic evolution in the field of ST is evident from the publication rate over the last six years. The research study is carried out to provide insight into the field of ST from various research bibliometric aspects. Our methodological approach includes dividing the six-year time frame into the set of two symmetric but different periods (2016–2018) and (2019–2021) comprising a total of 75,098 records. VOSViewer is used to perform analysis with respect to collaboration network of countries and co-word assessment. Bibliometrix (Studio R) analysis tool is used to evaluate research themes/topics. The year 2019 leads the publication rate whereas a decrement in publication frequency is observed for the years 2020 and 2021. Our research study shows the influence of ST in other research domains as depicted in different research areas. Especially the impact of ST in the Electrical and Electronics Domain is quite notable. Most of the research publications are from the USA and China as they are among the most resourceful countries. On the whole, the majority of the publications are from Asian countries. Collaboration networks amongst countries demonstrate the fact that the higher the collaboration network, the greater would be the research output. Co-word analysis presents the relatedness of documents based on the keywords. The topic dendrogram is generated based on the identified research themes. Although English is the leading language, prominent studies are present in other languages also. This research study provides a comprehensive analysis based on 12 informative research questions

Sustainability incorporation within the field of Software Engineering is an emerging research area. Sustainability, from an academic perspective, has been addressed to a large extent. However, when it comes to the software industry, the topic has not received much-needed attention. Software, being designed and developed in the industry, can benefit society at large, if sustainability is taken into account by the software professionals during the software design and development process. To develop a sustainable software application, knowledge and awareness about sustainability by professional software developers is one of the key elements. This study is an attempt to examine sustainability knowledge, importance, and support from the perspective of South Asian software professionals. Additionally, this study also proposes sustainability guidelines for certain software applications and also a catalog for the identification of sustainability requirements for different software applications. The queries such as ‘What does sustainability mean to a professional software developer?’, ‘How does the software industry identify sustainability requirements?’, ‘How do software developers incorporate the sustainability parameters within software during software development?’, and many other such queries are addressed in this study. To achieve this goal, a survey was carried out among 221 industry practitioners involved in software projects in various application domains such as banking, finance, and management applications. The results pinpoint that even though sustainability is deemed important by 91% of practitioners, still there is a lack of understanding regarding sustainability incorporation in software development. A total of 48% of professionals often misunderstand “Green software” as “sustainable software”. The technical aspect of sustainability is considered most important by professionals (67%) as well as companies (77%). One of the key findings of this study is that 92% of software practitioners are not able to identify sustainability requirements for software applications. The outcomes of the study may be regarded as an initial attempt towards how sustainability is comprehended in software by the South Asian software industry.

The proliferation of Internet of Things (IoT) devices has revolutionized various sectors by enabling real-time monitoring, data collection, and intelligent decision-making. However, the massive volume of data generated by these devices presents significant challenges for data processing and analysis. Intrusion Detection Systems (IDS) for IoT require efficient and accurate identification of malicious activities amidst vast amounts of data. Feature selection is a critical step in this process, aiming to identify the most relevant features that contribute to accurate intrusion detection, thus reducing computational complexity and improving model performance. Traditional Mutual Information-based Feature Selection (MIFS) methods face challenges when applied to IoT data due to their inherent noise, uncertainty, and imprecision. This study introduces a novel Fuzzy Mutual Information-based Feature Selection (Fuzzy-MIFS) method that integrates fuzzy logic with Gaussian membership functions to address these challenges. The proposed method enhances the robustness and effectiveness of the feature selection process, resulting in improved accuracy and efficiency of IDSs in IoT environments. Experimental results demonstrate that the Fuzzy-MIFS method consistently outperformed existing feature selection techniques across various neural network models, such as CNN, LSTM, and DBN, showcasing its superior performance in handling the complexities of IoT data. The results show that Fuzzy-MIFS increased the accuracy from 0.962 to 0.986 for CNN, from 0.96 to 0.968 for LSTM, and from 0.96 to 0.97 for DBN.