ABSTRACT Zero‐day exploits remain challenging to detect because they often appear in unknown distributions of signatures and rules. The article entails a systematic review and cross‐sectional synthesis of four fundamental model families for identifying zero‐day intrusions, namely, convolutional neural networks (CNN), deep neural networks (DNN), Bayesian networks (BN), and reinforcement learning (RL). A PRISMA‐style protocol is used to extract evidence, test across popular corpora, and test models in zero‐day faithful regimes, time‐split, and cross‐dataset transfer. In addition to aggregate accuracy and F1, we also highlight operating‐point reporting the true‐positive rate at a fixed false‐positive rate, ranking measures in the presence of class imbalance, and calibration of probability predictions as a measure of expected error probabilistic calibration, which may include syntactic measures such as time‐to‐alert, throughput, and memory compute footprint. Reported results suggest that DNNs demonstrate the aggregate performance on richly feature inputs (nearly 99.56% accuracy on CICDDoS2019), CNNs on tensorized flows/bytes with advantageous latency at the edge 92.17% on Bot‐IOT), BN provides interpretable uncertainty with acceptable accuracy (99.74% on NSL‐KDD), and RL shows promise as an adaptive detection‐response when there are rewards and safe training environments (96.18% on CSE‐CIC‐IDS2018). We unify the heterogeneity of our datasets and suggest a coherent, leakage‐wary evaluation environment to facilitate comparability and reproducibility. Language or code models of logs and transformer traffic encoders, along with lightweight backbones of edge IDS, become available as subjects of future head‐to‐head studies under equal protocol conditions. The review provides tactical advice on model‐data fit, operating points, calibration, and latency budgets, the precursor to deployment ready, adaptive defence against unknown attacks.

Deep learning-based automated systems have emerged as powerful tools for medical image analysis. However, existing models often face limitations when applied to gastrointestinal (GI) tract imaging and segmentation because the irregular organ shapes, varying sizes, overlapping regions, and low-contrast boundaries significantly affect the performance and generalizability of current segmentation techniques. To address this challenge, we propose PTransNet, a novel transformer-based segmentation network for GI images. Here, we introduce a novel technique, Contextual Relative Positional Encoding (CRPE), that explicitly embeds relative spatial relationships among features, thereby improving the network’s spatial reasoning in anatomical scenes. We proposed the PTransNet architecture, which combines UNet and a transformer with a novel CRPE for optimized segmentation. The encoder-decoder architecture of UNet enhances model efficiency by capturing contextual features through downsampling and precisely localizing them via symmetric upsampling with skip connections. Using the UW-Madison GI Tract dataset (16,590 images), PTransNet is trained, validated, and tested (80%-10%-10% split) to target the segmentation of the three major GI components (small, large, and stomach), which achieved substantially higher testing performances with a Dice score of 93.49%, an IoU (Intersection-over-Union) of 90.51%, and a specificity of 99.87%. Moreover, PTransNet achieved 10.64% and 13.4% gains in dice and IoU scores, respectively, when using the novel CRPE component, highlighting its contribution to precision diagnosis. The model also outperformed state-of-the-art methods across higher MCC, BM, HD95, NSD, MASD, precision, recall, and F1 scores, demonstrating robust segmentation quality. These advances highlight PTransNet’s strength in handling the challenges of spatial scenarios. Thus, PTransNet has substantial practical implications for the reliable delineation of GI organs in clinical workflows (e.g., radiotherapy planning), thereby contributing to improved healthcare outcomes in the management of GI disease.

The complicated process of neuronal development is initiated early in life, with the genetic mechanisms governing this process yet to be fully elucidated. Single-cell RNA sequencing (scRNA-seq) is a potent instrument for pinpointing biomarkers that exhibit differential expression across various cell types and developmental stages. By employing scRNA-seq on human embryonic stem cells, we aim to identify differentially expressed genes (DEGs) crucial for early-stage neuronal development. Our focus extends beyond simply identifying DEGs. We strive to investigate the functional roles of these genes through enrichment analysis and construct gene regulatory networks to understand their interactions. Ultimately, this comprehensive approach aspires to illuminate the molecular mechanisms and transcriptional dynamics governing early human brain development. By uncovering potential links between these DEGs and intelligence, mental disorders, and neurodevelopmental disorders, we hope to shed light on human neurological health and disease. In this study, we have used scRNA-seq to identify DEGs involved in early-stage neuronal development in hESCs. The scRNA-seq data, collected on days 26 (D26) and 54 (D54), of the in vitro differentiation of hESCs to neurons were analyzed. Our analysis identified 539 DEGs between D26 and D54. Functional enrichment of those DEG biomarkers indicated that the up-regulated DEGs participated in neurogenesis, while the down-regulated DEGs were linked to synapse regulation. The Reactome pathway analysis revealed that down-regulated DEGs were involved in the interactions between proteins located in synapse pathways. We also discovered interactions between DEGs and miRNA, transcriptional factors (TFs) and DEGs, and between TF and miRNA. Our study identified 20 significant transcription factors, shedding light on early brain development genetics. The identified DEGs and gene regulatory networks are valuable resources for future research into human brain development and neurodevelopmental disorders.

Abstract Autism Spectrum Disorder (ASD) is a chronic condition characterised by impairments in social interaction and communication. Early detection of ASD is desired, and there exists a demand for the development of diagnostic aids to facilitate this. A lightweight Involutional Neural Network (INN) architecture has been developed to diagnose ASD. The model follows a simpler architectural design and has less number of parameters than the state‐of‐the‐art (SOTA) image classification models, requiring lower computational resources. The proposed model is trained to detect ASD from eye‐tracking scanpath (SP), heatmap (HM), and fixation map (FM) images. Monte Carlo Dropout has been applied to the model to perform an uncertainty analysis and ensure the effectiveness of the output provided by the proposed INN model. The model has been trained and evaluated using two publicly accessible datasets. From the experiment, it is seen that the model has achieved 98.12% accuracy, 96.83% accuracy, and 97.61% accuracy on SP, FM, and HM, respectively, which outperforms the current SOTA image classification models and other existing works conducted on this topic.

Abstract Quick and accurate diagnosis of COVID‐19 is crucial in preventing its transmission. Chest X‐ray (CXR) imaging is often used for diagnosis, however, even experienced radiologists may misinterpret the results, necessitating computer‐aided diagnosis. Deep learning has yielded favourable results previously, but overfitting, excessive variance, and generalization errors may occur due to noise and limited datasets. Ensemble learning can improve predictions by using robust techniques. Therefore, this study, proposes two‐fold strategy that combines advanced and robust algorithms, including DenseNet201, EfficientNetB7, and Xception, to achieve faster and more accurate COVID‐19 detection. Segmented lung images were generated from CXR images using the residual U‐Net model, and two attention‐based ensemble neural networks were used for classification. The COVID‐19 radiography dataset was used to evaluate the proposed approach, which achieved an accuracy of 98.21%, 93.4%, and 89.06% for two, three, and four classes respectively which outperformed previous studies by a significant margin considering COVID, viral pneumonia, and lung opacity simultaneously. Despite the similarity in CXR images of COVID, pneumonia, and lung opacity, the proposed approach achieved 89.06% accuracy, demonstrating its ability to recognize distinguishable features. The developed algorithm is expected to have applications in clinics for diagnosing different diseases using X‐ray images.

In this paper, an Electro-Hydraulic Servo System (EHSS) actuating an active suspension system by employing finite frequency robust control method is presented. EHSS is popularly used in various industrial applications. However, parametric uncertainties are responsible for the response of such system to be unstable. In addition to that, the performance of such system is highly sensitive to external load disturbances. This paper thus, presents the identification of parametric uncertainties posed by unmodeled dynamics through a comprehensive mathematical model of EHSS. The modeling constraints are also investigated to propose a Finite Frequency Robust Control Strategy to actuate an active suspension system subjected to road disturbances. Simulation results are able to determine the trade-off between robust control and rejecting road disturbances at higher deflection frequencies using different performance criteria. As a consequence, these investigations show that the proposed controller could overcome the model uncertainties of EHSS for Robust Active Suspension.

Signalling transduction pathways (STPs) are commonly hijacked by many cancers for their growth and malignancy, but demystifying their underlying mechanisms is difficult. Here, we developed methodologies with a fully Bayesian approach in discovering novel driver bio-markers in aberrant STPs given high-throughput gene expression (GE) data. This project, namely 'PathTurbEr' (Pathway Perturbation Driver) uses the GE dataset derived from the lapatinib (an EGFR/HER dual inhibitor) sensitive and resistant samples from breast cancer cell lines (SKBR3). Differential expression analysis revealed 512 differentially expressed genes (DEGs) and their pathway enrichment revealed 13 highly perturbed singalling pathways in lapatinib resistance, including PI3K-AKT, Chemokine, Hippo and TGF-$\beta $ singalling pathways. Next, the aberration in TGF-$\beta $ STP was modelled as a causal Bayesian network (BN) using three MCMC sampling methods, i.e. Neighbourhood sampler (NS) and Hit-and-Run (HAR) sampler that potentially yield robust inference with lower chances of getting stuck at local optima and faster convergence compared to other state-of-art methods. Next, we examined the structural features of the optimal BN as a statistical process that generates the global structure using $p_1$-model, a special class of Exponential Random Graph Models (ERGMs), and MCMC methods for their hyper-parameter sampling. This step enabled key drivers identification that drive the aberration within the perturbed BN structure of STP, and yielded 34, 34 and 23 perturbation driver genes out of 80 constituent genes of three perturbed STP models of TGF-$\beta $ signalling inferred by NS, HAR and MH sampling methods, respectively. Functional-relevance and disease-relevance analyses suggested their significant associations with breast cancer progression/resistance.

Drug similarity studies are driven by the hypothesis that similar drugs should display similar therapeutic actions and thus can potentially treat a similar constellation of diseases. Drug-drug similarity has been derived by variety of direct and indirect sources of evidence and frequently shown high predictive power in discovering validated repositioning candidates as well as other in-silico drug development applications. Yet, existing resources either have limited coverage or rely on an individual source of evidence, overlooking the wealth and diversity of drug-related data sources. Hence, there has been an unmet need for a comprehensive resource integrating diverse drug-related information to derive multi-evidenced drug-drug similarities. We addressed this resource gap by compiling heterogenous information for an exhaustive set of small-molecule drugs (total of 10 367 in the current version) and systematically integrated multiple sources of evidence to derive a multi-modal drug-drug similarity network. The resulting database, 'DrugSimDB' currently includes 238 635 drug pairs with significant aggregated similarity, complemented with an interactive user-friendly web interface (http://vafaeelab.com/drugSimDB.html), which not only enables database ease of access, search, filtration and export, but also provides a variety of complementary information on queried drugs and interactions. The integration approach can flexibly incorporate further drug information into the similarity network, providing an easily extendable platform. The database compilation and construction source-code has been well-documented and semi-automated for any-time upgrade to account for new drugs and up-to-date drug information.

Coronavirus Disease 2019 (COVID-19), although most commonly demonstrates respiratory symptoms, but there is a growing set of evidence reporting its correlation with the digestive tract and faeces. Interestingly, recent studies have shown the association of Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) infection with gastrointestinal symptoms in infected patients but any sign of respiratory issues. Moreover, some studies have also shown that the presence of live SARS-CoV-2 virus in the faeces of patients with COVID-19. Therefore, the pathophysiology of digestive symptoms associated with COVID-19 has raised a critical need for comprehensive investigative efforts. To address this issue we have developed a bioinformatics pipeline involving a system biological framework to identify the effects of SARS-CoV-2 messenger RNA expression on deciphering its association with digestive symptoms in COVID-19 positive patients. Using two RNA-seq datasets derived from COVID-19 positive patients with celiac (CEL), Crohn's (CRO) and ulcerative colitis (ULC) as digestive disorders, we have found a significant overlap between the sets of differentially expressed genes from SARS-CoV-2 exposed tissue and digestive tract disordered tissues, reporting 7, 22 and 13 such overlapping genes, respectively. Moreover, gene set enrichment analysis, comprehensive analyses of protein-protein interaction network, gene regulatory network, protein-chemical agent interaction network revealed some critical association between SARS-CoV-2 infection and the presence of digestive disorders. The infectome, diseasome and comorbidity analyses also discover the influences of the identified signature genes in other risk factors of SARS-CoV-2 infection to human health. We hope the findings from this pathogenetic analysis may reveal important insights in deciphering the complex interplay between COVID-19 and digestive disorders and underpins its significance in therapeutic development strategy to combat against COVID-19 pandemic.

Existing in-network query processing techniques are categorized as approximation and aggregation based approaches, where the former achieves lower network traffic at the expense of query response accuracy, whereas the later reduces query response inaccuracy by executing queries at the actual sensor nodes which necessitates the overhead of query specific sensor selection mechanism. In this paper, we propose a hybrid query processing framework that combines the advantages of both the approximation and aggregation based techniques and avoids their limitations. In our approach, we construct a hierarchical probabilistic data model representing the overall sensor data characteristics across the network, which is query independent and is later used for selecting sensor nodes to process user queries. Experimental results illustrate the efficacy of the proposed framework compared to contemporary approximation and aggregation based query processing techniques.

Transmission policy, in addition to topology control, routing, and MAC protocols, can play a vital role in extending network lifetime. Existing transmission policies, however, cause an extremely unbalanced energy usage that contributes to early demise of some sensors reducing overall network's lifetime drastically. Considering cocentric rings around the sink, we decompose the transmission distance of traditional multihop scheme into two parts: ring thickness and hop size, analyze the traffic and energy usage distribution among sensors and determine how energy usage varies and critical ring shifts with hop size. Based on above observations, we propose a transmission scheme and determine the optimal ring thickness and hop size by formulating network lifetime as an optimization problem. Numerical results show substantial improvements in terms of network lifetime and energy usage distribution over existing policies. Two other variations of this policy are also presented by redefining the optimization problem considering: 1) concomitant hop size variation by sensors over lifetime along with optimal duty cycles, and 2) a distinct set of hop sizes for sensors in each ring. Both variations bring increasingly uniform energy usage with lower critical energy and further improves lifetime. A heuristic for distributed implementation of each policy is also presented.

Most existing data models and transmission policies for sensor network assume uniform periodic data generation and unconstrained transmission range for sensor nodes, both assumptions being too restrictive to capture and analyze real- world operation for practical deployment. In this paper, we consider these two practical aspects and present a new transmission policy formulated after (i) stochastic data model where a set of events occur with certain probabilities and rate of data generation by a sensor varies based on sensed event and (ii) limited transmission range of sensors. Assuming co-centric rings around the base station, located at a generic location (internal or external to the network area), ring thickness and hope sizes over lifetime is determined by formatting an optimization problem where nodes in each ring may transmit data at different hop sizes at a given instant and also vary hop sizes over lifetime. Performance analysis shows significant improvement in network lifetime and better uniformity in energy usage distribution in the proposed policy irrespective of network size and maximum allowable transmission range of nodes.

For many applications, simultaneous sensing of a number of parameters is crucial that leads to the deployment of multiple classes of sensors having different initial energy, data generation rate and deployment density within the vicinity of a cluster as opposed to identical sensors assumed in the existing heterogeneous sensor networks. For data transmission to cluster head, such networks use single hop, multi hop and their hybrid as intra-cluster transmission policy which suffer highly from non-uniform energy usage among sensors, thereby reducing the lifetime drastically leaving considerable amount of energy in many nodes. In this paper, we propose a framework for multi-class heterogeneous sensor networks where incoming traffic is relayed towards cluster head in collaboration among multiple classes of sensors considering their heterogeneity. We also propose two transmission policies for this framework considering generic polygonal cluster and limited transmission range for individual sensors. Performance analysis shows substantial improvement of overall lifetime by the collaborative framework of multi-class sensors. Our proposed transmission policies further improve the lifetime over existing multi hop and hybrid communications through better distribution of energy usage among sensors.

Although transmission policy is crucial in extending lifetime of sensor networks, most existing policies make simplified assumptions which include: i) circular cluster with cluster head (CH) at the center, ii) uniform periodic data generation model and iii) unrestricted transmission range for nodes. But, in practice, these assumptions are too restrictive for real-world deployment of heterogeneous sensor networks where clusters are usually polygonal. Moreover, in multi hop transmission energy consumption by sensors varies greatly with their distance from CH and even among sensors in the critical ring due to non-uniform relay traffic caused by asymmetric polygonal structure of cluster. In this paper, we propose a new transmission policy where sensors transmit at optimally determined hop sizes that varies over lifetime and a distributed hop selection algorithm that regulates each packet's arrival to CH within a given hop limit. Our formulation considers generic polygonal cluster, stochastic data generation model where data generation rate by sensors vary with events and limited transmission range for sensors. Performance analysis shows significant improvement in lifetime and better uniformity in energy usage among sensors in the proposed policy irrespective of cluster size, hop limit and maximum allowable transmission range of nodes.

Non-uniform energy usage among sensors due to varying distances from the base station makes some nodes to die early, thereby reducing the network's lifetime drastically leaving considerable amount of residual energy in others. Performance optimization techniques that have recently been proposed include optimal transmission policies and dynamic relocation of the base station within the network area. Here we propose two transmission policies, namely, fixed hop size (FHS) and synchronous variable hop size (SVHS) transmissions considering generic location for the base station. We decompose the transmission distance of traditional multi hop protocol into two parts: ring thickness and hop size, and determine the optimal values of these parameters by formulating network lifetime as an optimization problem. Numerical results show that each of our policies perform substantially better in terms of network lifetime and energy usage distribution than the single hop and multi hop transmission policies irrespective of network size and distance of the base station from the network centre.