Search

This research presents a novel framework for distinguishing between actual and non-suicidal ideation in social media interactions using an ensemble technique. The prompt identification of sentiments on social networking platforms is crucial for timely intervention serving as a key tactic in suicide prevention efforts. However, conventional AI models often mask their decision-making processes primarily designed for classification purposes. Our methodology, along with an updated ensemble method, bridges the gap between Explainable AI and leverages a variety of machine learning algorithms to improve predictive accuracy. By leveraging Explainable AI's interpretability to analyze the features, the model elucidates the reasoning behind its classifications leading to a comprehension of hidden patterns associated with suicidal ideations. Our system is compared to cutting-edge methods on several social media datasets using experimental evaluations, demonstrating that it is superior, since it detects suicidal content more accurately than others. Consequently, this study presents a more reliable and interpretable strategy (F1-score for suicidal = 95.5% and Non-Suicidal = 99%), for monitoring and intervening in suicide-related online discussions., Competing Interests: Declarations. Competing interests: The authors declare no competing interests. Informed consent: All procedures followed were in accordance with the ethical standards of the responsible committee on human experimentation (institutional and national) and with the Helsinki Declaration of 1975, as revised in 2008 (5). Additional informed consent was obtained from all patients for whom identifying information is included in this article. Human and animal rights: This study did not involve any experimental research on humans or animals; hence, an approval from an ethics committee was not applicable in this regard. The data collected from the online forums are publicly available data, and no personally identifiable information of the forum users were collected or used for this study., (© 2025. The Author(s).)

Advancements in wireless communication and automation have revolutionized mobility systems, notably through autonomous vehicles and unmanned aerial vehicles (UAVs). UAV spatial coordinates, determined via Global Positioning System (GPS) signals, are susceptible to cyberattacks due to unencrypted and unauthenticated transmissions with GPS spoofing being a significant threat. To mitigate these vulnerabilities, intrusion detection systems (IDSs) for UAVs have been developed and enhanced using machine learning (ML) algorithms. However, Adversarial Machine Learning (AML) has introduced new risks by exploiting ML models. This study presents a UAV-IDS employing AML methodology to enhance the detection and classification of GPS spoofing attacks. The key contribution is the development of an AML detection model that significantly improves UAV system robustness and security. Our findings indicate that the model achieves a detection accuracy of 98%, demonstrating its effectiveness in managing large-scale datasets and complex tasks. This study emphasizes the importance of physical layer security for enhancing IDSs in UAVs by introducing a novel detection model centered on an adversarial training defense method and advanced deep learning techniques.

Wireless physical layer authentication has emerged as a promising approach to wireless security. The topic of wireless node classification and recognition has experienced significant advancements due to the rapid development of deep learning techniques. The potential of using deep learning to address wireless security issues should not be overlooked due to its considerable capabilities. Nevertheless, the utilization of this approach in the classification of wireless nodes is impeded by the lack of available datasets. In this study, we provide two models based on a data-driven approach. First, we used generative adversarial networks to design an automated model for data augmentation. Second, we applied a convolutional neural network to classify wireless nodes for a wireless physical layer authentication model. To verify the effectiveness of the proposed model, we assessed our results using an original dataset as a baseline and a generated synthetic dataset. The findings indicate an improvement of approximately 19% in classification accuracy rate.

The physical layer security of wireless networks is becoming increasingly important because of the rapid development of wireless communications and the increasing security threats. In addition, because of the open nature of the wireless channel, authentication is a critical issue in wireless communications. Physical layer authentication (PLA) is based on distinctive features to provide information-theory security and low complexity. However, although many researchers are interested in the PLA and how it might be used to improve wireless security, there is surprisingly little literature on the subject, with no systematic overview of the current state-of-the-art PLA and the main foundations involved. Therefore, this paper aims to determine and systematically compare existing studies in the physical layer authentication. This study showed whether machine learning approaches in physical layer authentication models increased wireless network security performance and demonstrated the latest techniques used in PLA. Moreover, it identified issues and suggested directions for future research. This study is valuable for researchers and security model developers interested in using machine learning (ML) and deep learning (DL) approaches for PLA in wireless communication systems in future research and designs.

Adversarial machine learning is a recent area of study that explores both adversarial attack strategy and detection systems of adversarial attacks, which are inputs specially crafted to outwit the classification of detection systems or disrupt the training process of detection systems. In this research, we performed two adversarial attack scenarios, we used a Generative Adversarial Network (GAN) to generate synthetic intrusion traffic to test the influence of these attacks on the accuracy of machine learning-based Intrusion Detection Systems(IDSs). We conducted two experiments on adversarial attacks including poisoning and evasion attacks on two different types of machine learning models: Decision Tree and Logistic Regression. The performance of implemented adversarial attack scenarios was evaluated using the CICIDS2017 dataset. Also, it was based on a comparison of the accuracy of machine learning-based IDS before and after attacks. The results show that the proposed evasion attacks reduced the testing accuracy of both network intrusion detection systems models (NIDS). That illustrates our evasion attack scenario negatively affected the accuracy of machine learning-based network intrusion detection systems, whereas the decision tree model was more affected than logistic regression. Furthermore, our poisoning attack scenario disrupted the training process of machine learning-based NIDS, whereas the logistic regression model was more affected than the decision tree.

Epilepsy is a nervous system disorder. Encephalography (EEG) is a generally utilized clinical approach for recording electrical activity in the brain. Although there are a number of datasets available, most of them are imbalanced due to the presence of fewer epileptic EEG signals compared with non-epileptic EEG signals. This research aims to study the possibility of integrating local EEG signals from an epilepsy center in King Abdulaziz University hospital into the CHB-MIT dataset by applying a new compatibility framework for data integration. The framework comprises multiple functions, which include dominant channel selection followed by the implementation of a novel algorithm for reading XLtek EEG data. The resulting integrated datasets, which contain selective channels, are tested and evaluated using a deep-learning model of 1D-CNN, Bi-LSTM, and attention. The results achieved up to 96.87% accuracy, 96.98% precision, and 96.85% sensitivity, outperforming the other latest systems that have a larger number of EEG channels.

In recent years, the advent of cloud computing has transformed the field of computing and information technology. It has been enabling customers to rent virtual resources and take advantage of various on-demand services with the lowest costs. Despite the advantages of cloud computing, it faces several threats; an example is a distributed denial of service (DDoS) attack, which is considered among the most serious. This article presents real-time monitoring and detection of DDoS attacks on the cloud using a machine learning approach. Naïve Bayes, K-nearest neighbor, decision tree, and random forest machine learning classifiers have been selected to build a predictive model named "Real-Time DDoS flood Attack Monitoring and Detection RT-AMD." The DDoS-2020 dataset was constructed with 70,020 records to evaluate RT-AMD's accuracy. The DDoS-2020 contains three protocols for network/transport-level, which are TCP, DNS, and ICMP. This article evaluates the proposed model by comparing its accuracy with related works. Our model has shown improvement in the results and reached real-time attack detection using incremental learning. The model achieved 99.38% accuracy for the random forest in real-time on the cloud environment and 99.39% on local testing. The RT-AMD was evaluated on the NSL-KDD dataset as well, in which it achieved 99.30% accuracy in real-time in a cloud environment., Competing Interests: The authors declare that they have no competing interests., (© 2022 Bamasag et al.)

Rapid advancements in the internet of things (IoT) are driving massive transformations of health care, which is one of the largest and critical global industries. Recent pandemics, such as coronavirus 2019 (COVID-19), include increasing demands for ubiquitous, preventive, and personalized health care to be provided to the public at reduced risks and costs with rapid care. Mobile crowdsourcing could potentially meet the future massive health care IoT (mH-IoT) demands by enabling anytime, anywhere sense and analyses of health-related data to tackle such a pandemic situation. However, data reliability and availability are among the many challenges for the realization of next-generation mH-IoT, especially in COVID-19 epidemics. Therefore, more intelligent and robust health care frameworks are required to tackle such pandemics. Recently, reinforcement learning (RL) has proven its strengths to provide intelligent data reliability and availability. The action-state learning procedure of RL-based frameworks enables the learning system to enhance the optimal use of the information as the time passes and data increases. In this article, we propose an RL-based crowd-to-machine (RLC2M) framework for mH-IoT, which leverages crowdsourcing and an RL model (Q-learning) to address the health care information processing challenges. The simulation results show that the proposed framework rapidly converges with accumulated rewards to reveal the sensing environment situation.

Background and Objective: According to the WHO, diabetes mellitus is a long-term condition marked by high blood sugar levels. The consequences might be far-reaching. According to current increases in mortality, diabetes has risen to number 10 among the leading causes of mortality worldwide. When used to predict diabetes using unbalanced datasets from testing, machine learning (ML) classifiers and established approaches for encoding categorical data have exhibited a broad variety of surprising outcomes. Early studies also made use of an artificial neural network to extract features without obtaining a grasp of the sequence information., Methods: This study offers a deep learning-based decision support system (DSS), utilizing bidirectional long/short-term memory (BiLSTM), to accurately predict diabetic illness from patient data. In order to predict diabetes, the BiLSTM hybrid model was used after balancing the data set., Results: Unlike earlier studies, this proposed model's trial findings were promising, with an accuracy of 93.07%, 93% precision, 92% recall, and a 92% F1-score., Conclusions: Using a BILSTM model for classification outperforms current approaches in the diabetes detection domain., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2022 Rabie, Alghazzawi, Asghar, Saddozai and Asghar.)

The development of the Internet of Things (IoT) expands to an ultra-large-scale, which provides numerous services across different domains and environments. The use of middleware eases application development by providing the necessary functional capability. This paper presents a new form of middleware for controlling smart devices installed in an intelligent environment. This new form of middleware functioned seamlessly with any manufacturer API or bespoke controller program. It acts as an all-encompassing top layer of middleware in an intelligent environment control system capable of handling numerous different types of devices simultaneously. This protected de-synchronization of data stored in clone devices. It showed that in this middleware, the clone devices were regularly synchronized with their original master such as locally stored representations were continuously updated with the known true state values., Competing Interests: Daniyal Alghazzawi, James Dooley, Dr. Ghadah Aldabagh & Dr. Abdullah Alghamdi declare no conflict of interest., (© 2021 Alghazzawi et al.)

Upon the working principles of the human neocortex, the Hierarchical Temporal Memory model has been developed which is a proposed theoretical framework for sequence learning. Both categorical and numerical types of data are handled by HTM. Semantic Folding Theory (SFT) is based on HTM to represent a data stream for processing in the form of sparse distributed representation (SDR). For natural language perception and production, SFT delivers a solid structural background for semantic evidence description to the fundamentals of the semantic foundation during the phase of language learning. Anomalies are the patterns from data streams that do not follow the expected behavior. Any stream of data patterns could have a number of anomaly types. In a data stream, a single pattern or combination of closely related patterns that diverges and deviates from standard, normal, or expected is called a static (spatial) anomaly. A temporal anomaly is a set of unexpected changes between patterns. When a change first appears, this is recorded as an anomaly. If this change looks a number of times, then it is set to a "new normal" and terminated as an anomaly. An HTM system detects the anomaly, and due to continuous learning nature, it quickly learns when they become the new normal. A robust anomalous behavior detection framework using HTM-based SFT for improving decision-making (SDR-ABDF/P2) is a proposed framework or model in this research. The researcher claims that the proposed model would be able to learn the order of several variables continuously in temporal sequences by using an unsupervised learning rule., Competing Interests: The authors declare that they have no conflicts of interest., (Copyright © 2021 Hamid Masood Khan et al.)

Competing Interests: None declared.

In recent years, accumulating evidences have shown that microRNA (miRNA) plays an important role in the exploration and treatment of diseases, so detection of the associations between miRNA and disease has been drawn more and more attentions. However, traditional experimental methods have the limitations of high cost and time- consuming, a computational method can help us more systematically and effectively predict the potential miRNA-disease associations. In this work, we proposed a novel network embedding-based heterogeneous information integration method to predict miRNA-disease associations. More specifically, a heterogeneous information network is constructed by combining the known associations among lncRNA, drug, protein, disease, and miRNA. After that, the network embedding method Learning Graph Representations with Global Structural Information (GraRep) is employed to learn embeddings of nodes in heterogeneous information network. In this way, the embedding representations of miRNA and disease are integrated with the attribute information of miRNA and disease (e.g. miRNA sequence information and disease semantic similarity) to represent miRNA-disease association pairs. Finally, the Random Forest (RF) classifier is used for predicting potential miRNA-disease associations. Under the 5-fold cross validation, our method obtained 85.11% prediction accuracy with 80.41% sensitivity at the AUC of 91.25%. In addition, in case studies of three major Human diseases, 45 (Colon Neoplasms), 42 (Breast Neoplasms) and 44 (Esophageal Neoplasms) of top-50 predicted miRNAs are respectively verified by other miRNA-disease association databases. In conclusion, the experimental results suggest that our method can be a powerful and useful tool for predicting potential miRNA-disease associations.

We consider a demand response program in which a block of apartments receive a discount from their electricity supplier if they ensure that their aggregate load from air conditioning does not exceed a predetermined threshold. The goal of the participants is to obtain the discount, while ensuring that their individual temperature preferences are also satisfied. As such, the apartments need to collectively optimise their use of air conditioning so as to satisfy these constraints and minimise their costs. Given an optimal cooling profile that secures the discount, the problem that the apartments face then is to divide the total discounted cost in a fair way. To achieve this, we take a coalitional game approach and propose the use of the Shapley value from cooperative game theory, which is the normative payoff division mechanism that offers a unique set of desirable fairness properties. However, applying the Shapley value in this setting presents a novel computational challenge. This is because its calculation requires, as input, the cost of every subset of apartments, which means solving an exponential number of collective optimisations, each of which is a computationally intensive problem. To address this, we propose solving the optimisation problem of each subset suboptimally, to allow for acceptable solutions that require less computation. We show that, due to the linearity property of the Shapley value, if suboptimal costs are used rather than optimal ones, the division of the discount will be fair in the following sense: each apartment is fairly "rewarded" for its contribution to the optimal cost and, at the same time, is fairly "penalised" for its contribution to the discrepancy between the suboptimal and the optimal costs. Importantly, this is achieved without requiring the optimal solutions., Competing Interests: The authors have declared that no competing interests exist.

Self-interacting proteins (SIPs) is of paramount importance in current molecular biology. There have been developed a number of traditional biological experiment methods for predicting SIPs in the past few years. However, these methods are costly, time-consuming and inefficient, and often limit their usage for predicting SIPs. Therefore, the development of computational method emerges at the times require. In this paper, we for the first time proposed a novel deep learning model which combined natural language processing (NLP) method for potential SIPs prediction from the protein sequence information. More specifically, the protein sequence is de novo assembled by k- mers . Then, we obtained the global vectors representation for each protein sequences by using natural language processing (NLP) technique. Finally, based on the knowledge of known self-interacting and non-interacting proteins, a multi-grained cascade forest model is trained to predict SIPs. Comprehensive experiments were performed on yeast and human datasets, which obtained an accuracy rate of 91.45% and 93.12%, respectively. From our evaluations, the experimental results show that the use of amino acid semantics information is very helpful for addressing the problem of sequences containing both self-interacting and non-interacting pairs of proteins. This work would have potential applications for various biological classification problems., Competing Interests: The authors declare no conflict of interest.

This investigation sought to understand whether performance in naturalistic virtual reality tasks for cognitive assessment relates to the cognitive domains that are supposed to be measured. The Shoe Closet Test (SCT) was developed based on a simple visual search task involving attention skills, in which participants have to match each pair of shoes with the colors of the compartments in a virtual shoe closet. The interaction within the virtual environment was made using the Microsoft Kinect. The measures consisted of concurrent paper-and-pencil neurocognitive tests for global cognitive functioning, executive functions, attention, psychomotor ability, and the outcomes of the SCT. The results showed that the SCT correlated with global cognitive performance as measured with the Montreal Cognitive Assessment (MoCA). The SCT explained one third of the total variance of this test and revealed good sensitivity and specificity in discriminating scores below one standard deviation in this screening tool. These findings suggest that performance of such functional tasks involves a broad range of cognitive processes that are associated with global cognitive functioning and that may be difficult to isolate through paper-and-pencil neurocognitive tests.

Information and Communication Technologies (ICTs) have grown exponentially in the education context and the use of digital products by children is increasing. As a result, teachers are taking advantage of ICTs to include mobile devices such as Tablets or Smartphones inside the classroom as playful support material to motivate children during their learning. Designing an interactive experience for a child with a special need such as a hearing impairment is a great challenge. In this article, two interactive systems are depicted, using a non-traditional interaction, by the following stages: analysis, design and implementation, with the participation of children with cochlear implant in the Institute of Blind and Deaf Children of Valle del Cauca, Colombia and the ASPAS Institute, Mallorca, Spain, who evaluated both interactive systems, PHONOMAGIC and CASETO. Positive results were obtained, showing that the use of real objects can greatly influence the environment in which children interact with the game, allowing them to explore and manipulate the objects supporting their teaching-learning processes.

Ecological validity should be the cornerstone of any assessment of cognitive functioning. For this purpose, we have developed a preliminary study to test the Art Gallery Test (AGT) as an alternative to traditional neuropsychological testing. The AGT involves three visual search subtests displayed in a virtual reality (VR) art gallery, designed to assess visual attention within an ecologically valid setting. To evaluate the relation between AGT and standard neuropsychological assessment scales, data were collected on a normative sample of healthy adults ( n = 30). The measures consisted of concurrent paper-and-pencil neuropsychological measures [Montreal Cognitive Assessment (MoCA), Frontal Assessment Battery (FAB), and Color Trails Test (CTT)] along with the outcomes from the three subtests of the AGT. The results showed significant correlations between the AGT subtests describing different visual search exercises strategies with global and specific cognitive measures. Comparative visual search was associated with attention and cognitive flexibility (CTT); whereas visual searches involving pictograms correlated with global cognitive function (MoCA).

Background: Despite the multisensory nature of perception, previous research on emotions has been focused on unimodal emotional cues with visual stimuli. To the best of our knowledge, there is no evidence on the extent to which incongruent emotional cues from visual and auditory sensory channels affect pupil size., Aims: To investigate the effects of audiovisual emotional information perception on the physiological and affective response, but also to determine the impact of mismatched cues in emotional perception on these physiological indexes., Method: Pupil size, electrodermal activity and affective subjective responses were recorded while 30 participants were exposed to visual and auditory stimuli with varied emotional content in three different experimental conditions: pictures and sounds presented alone (unimodal), emotionally matched audio-visual stimuli (bimodal congruent) and emotionally mismatched audio-visual stimuli (bimodal incongruent)., Results: The data revealed no effect of emotional incongruence on physiological and affective responses. On the other hand, pupil size covaried with skin conductance response (SCR), but the subjective experience was partially dissociated from autonomic responses., Conclusion: Emotional stimuli are able to trigger physiological responses regardless of valence, sensory modality or level of emotional congruence.