Search Results (254)

Classification is an important task in the field of machine learning. Decision tree algorithms are a popular choice for handling classification tasks due to their high accuracy, simple algorithmic process, and good interpretability. Traditional decision tree algorithms, such as ID3, C4.5, and CART, differ primarily in their criteria for splitting trees. Shannon entropy, Gini index, and mean squared error are all examples of measures that can be used as splitting criteria. However, their performance varies on different datasets, making it difficult to determine the optimal splitting criterion. As a result, the algorithms lack flexibility. In this paper, we introduce the concept of generalized entropy from information theory, which unifies many splitting criteria under one free parameter, as the split criterion for decision trees. We propose a new decision tree algorithm called RSE (RS-Entropy decision tree). Additionally, we improve upon a two-term information measure method by incorporating penalty terms and coefficients into the split criterion, leading to a new decision tree algorithm called RSEIM (RS-Entropy Information Method). In theory, the improved algorithms RSE and RSEIM are more flexible due to the presence of multiple free parameters. In experiments conducted on several datasets, using genetic algorithms to optimize the parameters, our proposed RSE and RSEIM methods significantly outperform traditional decision tree methods in terms of classification accuracy without increasing the complexity of the resulting trees. Full article

Personal identification (ID) is a prerequisite to many financial and social services; however, many vulnerable residents do not have ID and lack the resources to acquire it. To assess the impact of ID inaccessibility in a local context, a study was conducted throughout New Brunswick, Canada. The study objective was to understand the implications of ID requirements and the barriers to acquiring it through the lens of consumers. This mixed-methods, observational study included surveys and interviews. The survey collected demographics, socioeconomic status (SES), financial behaviors and experiences, and barriers to accessing ID. The semi-structured interviews explored individual experiences. In order to address disparities in health and social outcomes, ID requirements and barriers to access need to be acknowledged and mitigated. A total of 142 surveys were completed. Many respondents reported difficulty obtaining or replacing a driver’s license (30.8%), a provincial photo ID (47.7%), or their birth certificate (39.4%), identifying cost (34.4%) and required documentation (28.1%) as the main barriers. Thematic analysis identified three main themes: the difficulty of living without ID, barriers to obtaining or replacing an ID, and an exploration of solutions. Current ID policies restrict access to community services such as banking, housing, and employment, which are intended to support individuals to improve their situation and gain autonomy. Policies and services are required to address this urgent issue. Full article

Background: Hepatopancreatobiliary (HPB) surgery is among the most complex domains in oncologic care, where decisions entail significant risk–benefit considerations. Artificial intelligence (AI) has emerged as a promising tool for improving individualized decision-making through enhanced risk stratification, complication prediction, and survival modeling. However, its role in HPB oncologic surgery has not been comprehensively assessed. Methods: This systematic review was conducted in accordance with PRISMA guidelines and registered with PROSPERO ID: CRD420251114173. A comprehensive search across six databases was performed through 30 May 2025. Eligible studies evaluated AI applications in risk–benefit assessment in HPB cancer surgery. Inclusion criteria encompassed peer-reviewed, English-language studies involving human s ubjects. Two independent reviewers conducted study selection, data extraction, and quality appraisal. Results: Thirteen studies published between 2020 and 2024 met the inclusion criteria. Most studies employed retrospective designs with sample sizes ranging from small institutional cohorts to large national databases. AI models were developed for cancer risk prediction (n = 9), postoperative complication modeling (n = 4), and survival prediction (n = 3). Common algorithms included Random Forest, XGBoost, Decision Trees, Artificial Neural Networks, and Transformer-based models. While internal performance metrics were generally favorable, external validation was reported in only five studies, and calibration metrics were often lacking. Integration into clinical workflows was described in just two studies. No study addressed cost-effectiveness or patient perspectives. Overall risk of bias was moderate to high, primarily due to retrospective designs and incomplete reporting. Conclusions: AI demonstrates early promise in augmenting risk–benefit assessment for HPB oncologic surgery, particularly in predictive modeling. However, its clinical utility remains limited by methodological weaknesses and a lack of real-world integration. Future research should focus on prospective, multicenter validation, standardized reporting, clinical implementation, cost-effectiveness analysis, and the incorporation of patient-centered outcomes. Full article

Background/Objectives: Sleep state misperception (SSM) is a common phenomenon in insomnia disorder (ID), characterized by a discrepancy between subjective and objective sleep metrics. Recent studies have revealed microstructural EEG alterations specifically in misperceiving ID patients, yet clinically accessible SSM markers remain limited. This study aimed to characterize SSM within ID by integrating standard polysomnography (PSG) features and cognitive-affective traits, focusing on accessible clinical tools. Methods: Twenty patients with ID and twenty healthy controls (HC) underwent a night of PSG recording and completed both sleep diaries and a comprehensive psychological assessment. SSM was quantified using the Total Sleep Time misperception index (TSTm), analyzed both dimensionally and categorically Results: IDs reported significantly altered sleep parameters compared to HCs, both subjectively and objectively. Within the ID sample, although underestimators and normoestimators had similar objective TST, underestimators showed significantly more cortical arousal density (CAd), a higher percentage of sleep stage 1 and higher non-acceptance of emotions. Notably, none of the HC reached the threshold for being classified as underestimators. Regression analyses identified CAd, latency to sleep stage 3 and to REM, percentage of REM sleep and lack of emotional clarity, as key predictors of TSTm. Conclusions: SSM in insomnia reflects a dimensional vulnerability grounded in subtle sleep fragmentation and emotional dysregulation. Recognizing SSM as a clinically meaningful phenomenon may guide more targeted, emotion-focused, interventions for insomnia. Full article

The increasing adoption of electric vehicles (EVs) within intelligent transportation systems (ITSs) has elevated the importance of cybersecurity, especially with the rise in Vehicle-to-Everything (V2X) communications. Traditional intrusion detection systems (IDSs) struggle to address the evolving and complex nature of cyberattacks in such dynamic environments. To address these challenges, this study introduces a novel deep learning-based IDS designed specifically for EV communication networks. We present a hybrid model that integrates convolutional neural networks (CNNs), long short-term memory (LSTM) layers, and adaptive learning strategies. The model was trained and validated using the VeReMi dataset, which simulates a wide range of attack scenarios in V2X networks. Additionally, an ablation study was conducted to isolate the contribution of each of its modules. The model demonstrated strong performance with 98.73% accuracy, 97.88% precision, 98.91% sensitivity, and 98.55% specificity, as well as an F1-score of 98.39%, an MCC of 0.964, a false-positive rate of 1.45%, and a false-negative rate of 1.09%, with a detection latency of 28 ms and an AUC-ROC of 0.994. Specifically, this work fills a clear gap in the existing V2X intrusion detection literature—namely, the lack of scalable, adaptive, and low-latency IDS solutions for hardware-constrained EV platforms—by proposing a hybrid CNN–LSTM architecture coupled with an elastic weight consolidation (EWC)-based adaptive learning module that enables online updates without full retraining. The proposed model provides a real-time, adaptive, and high-precision IDS for EV networks, supporting safer and more resilient ITS infrastructures. Full article

The diverse usage of Unmanned Aerial Vehicles (UAVs) across commercial, military, and civil domains has significantly heightened the need for robust cybersecurity mechanisms. Given their reliance on wireless communications, real-time control systems, and sensor integration, UAVs are highly susceptible to cyber intrusions that can disrupt missions, compromise data integrity, or cause physical harm. This paper presents a comprehensive literature review of Intrusion Detection Systems (IDSs) that leverage artificial intelligence (AI) to enhance the security of UAV and UAV swarm environments. Through rigorous analysis of recent peer-reviewed publications, we have examined the studies in terms of AI model algorithm, dataset origin, deployment mode: centralized, distributed or federated. The classification also includes the detection strategy: online versus offline. Results show a dominant preference for centralized, supervised learning using standard datasets such as CICIDS2017, NSL-KDD, and KDDCup99, limiting applicability to real UAV operations. Deep learning (DL) methods, particularly Convolutional Neural Networks (CNNs), Long Short-term Memory (LSTM), and Autoencoders (AEs), demonstrate strong detection accuracy, but often under ideal conditions, lacking resilience to zero-day attacks and real-time constraints. Notably, emerging trends point to lightweight IDS models and federated learning frameworks for scalable, privacy-preserving solutions in UAV swarms. This review underscores key research gaps, including the scarcity of real UAV datasets, the absence of standardized benchmarks, and minimal exploration of lightweight detection schemes, offering a foundation for advancing secure UAV systems. Full article

Field-Programmable Gate Arrays (FPGAs) are increasingly shaping the future of network security, thanks to their flexibility, parallel processing capabilities, and energy efficiency. In this survey, we examine 50 peer-reviewed studies published between 2020 and 2025, selected from an initial pool of 210 articles based on relevance, hardware implementation, and the presence of empirical performance data. These studies encompass a broad range of topics, including cryptographic acceleration, intrusion detection and prevention systems (IDS/IPS), hardware firewalls, and emerging strategies that incorporate artificial intelligence (AI) and post-quantum cryptography (PQC). Our review focuses on five major application areas: cryptographic acceleration, intrusion detection and prevention systems (IDS/IPS), hardware firewalls, and emerging strategies involving artificial intelligence (AI) and post-quantum cryptography (PQC). We propose a structured taxonomy that organises the field by technical domain and challenge, and compare solutions in terms of scalability, resource usage, and real-world performance. Beyond summarising current advances, we explore ongoing limitations—such as hardware constraints, integration complexity, and the lack of standard benchmarking. We also outline future research directions, including low-power cryptographic designs, FPGA–AI collaboration for detecting zero-day attacks, and efficient PQC implementations. This survey aims to offer both a clear overview of recent progress and a valuable roadmap for researchers and engineers working toward secure, high-performance FPGA-based systems. Full article

Inertial Measurement Units (IMUs) offer promising alternatives to traditional motion capture systems, especially in real-world sports scenarios. Accurate foot contact detection (FCD) is crucial for biomechanical analysis, and since on-the-field force plates are unsuitable, IMU-based FCD algorithms have been extensively investigated. However, sports activities leading to musculoskeletal injuries are multidirectional and high-dynamics in nature and FCD algorithms, which have mostly been studied in gait analysis, might sensibly worsen performance. This systematic review (PROSPERO, ID: CRD420251010584) aimed to evaluate IMU-based FCD algorithms applied to high-dynamics sports tasks, identifying strengths, limitations, and areas for improvement. A multi-database search was conducted until May 2025. Studies were included if they applied IMU-based FCD algorithms in high-dynamic movements. In total, 37 studies evaluating 71 FCD algorithms were included. Most papers focused on running, with only 3 on cut manoeuvres. Almost all studies involved healthy individuals only, and foot linear acceleration was the most inspected FCD metric. FCD algorithms demonstrated high accuracy, though speed variation impacted performance in 23/37 studies. This review highlights the lack of validated IMU-based FCD algorithms for high-dynamic sports movements and emphasizes the need for improved methods to advance sports biomechanics testing in injury prevention. Full article

Understanding escape behavior in cryptic and venomous reef fishes is critical for both ecological theory and public safety in coastal environments. We quantified the Flight Initiation Distance (FID) of 65 individual stonefish (Synanceia spp.) across four public beaches in Eilat, Israel, between March and May 2025. Initial Identification Distance (Initial ID) ranged from 0.5 to 3.5 m, whereas FID was consistently short (0.0–0.6 m), with 62% of individuals (n = 40) showing no flight response. Logistic regression revealed that the probability of fleeing was positively predicted by Alert behavior (p = 0.005), while Initial ID and site were not significant. Among individuals that did flee (n = 25), FID remained short and showed no significant spatial variation. A linear model confirmed Alert as the only positive predictor of FID (p = 0.045), while other variables were non-significant. These findings demonstrate that stonefish predominantly rely on crypsis and venom rather than active escape, resulting in minimal or absent flight responses. This lack of FID highlights their unique defensive strategy among reef fishes but also increases the risk of accidental human envenomation in areas of high recreational activity. Monitoring FID patterns may serve as a behavioral indicator of anthropogenic disturbance, while also informing conservation and public safety strategies in urban reef environments. Full article

Background: HIV drug resistance (DR) mutations can compromise antiretroviral therapy (ART) success among children living with HIV (CLHIV). We conducted a secondary analysis using data from a randomized control trial for ART monitoring among CLHIV in Kisumu County, Kenya from 2019 to 2023, to assess clinical, psychosocial, and structural factors associated with HIV DR. Methods: 704 CLHIV were followed for 12+ months, with characteristics captured at enrollment and follow-up visits in the “parent” randomized-controlled-trial (of point-of-care plasma viral load testing and for viremias ≥ 1000 copies/mL HIV genotyping for DR vs. standard-of-care) and an observational “extension” substudy (of participants on a dolutegravir-containing ART with genotyping performed on viremic specimens ≥ 200 copies/mL). A multivariate modified Poisson regression model was used to analyze factors associated with sequences yielding a Stanford HIVDR database DR penalty score (DR-PS) ≥ 30 to a nucleos(t)ides and/or non-nucleoside reverse transcriptase inhibitor, protease inhibitor (PI), and/or integrase inhibitor (INSTI). Results: Among 113 (16.1%) participants who underwent genotyping, 93 (82.3%) had a DR-PS ≥ 30. DR-PS ≥ 30 were associated with age 1–5 years (adjusted risk ratio (ARR) = 1.84; 95% confidence interval (CI): 1.07, 3.14), history of viremia ≥ 1000 copies/mL (ARR = 4.18; 95% CI: 2.77, 6.31), prescription of a PI- (ARR = 6.05; 95% CI: 3.43, 10.68) or INSTI-containing regimen (ARR = 1.83; 95% CI: 1.08, 3.11), poor adherence to ART (ARR = 1.91; 95% CI: 1.32, 2.76), lack of caregiver confidence in ART administration (ARR = 1.89; 95% CI: 1.11, 3.22), and mid-sized clinic populations (ARR = 0.55; 95% CI: 0.33, 0.92). Conclusion: Addressing social factors associated with DR-PS ≥ 30 may improve ART success among CLHIV. Full article

Low-power microcontrollers, wireless sensors, and embedded gateways form the backbone of many Internet of Things (IoT) deployments. However, their limited memory, constrained energy budgets, and lack of standardized firmware make them attractive targets for diverse attacks, including bootloader backdoors, hardcoded keys, unpatched CVE exploits, and code-reuse attacks, while traditional single-layer defenses are insufficient as they often assume abundant resources. This paper presents a Systematic Literature Review (SLR) conducted according to the PRISMA 2020 guidelines, covering 196 peer-reviewed studies on cross-layer security for resource-constrained IoT and Industrial IoT environments, and introduces a four-axis taxonomy—system level, algorithmic paradigm, data granularity, and hardware budget—to structure and compare prior work. At the firmware level, we analyze static analysis, symbolic execution, and machine learning-based binary similarity detection that operate without requiring source code or a full runtime; at the network and behavioral levels, we review lightweight and graph-based intrusion detection systems (IDS), including single-packet authorization, unsupervised anomaly detection, RF spectrum monitoring, and sensor–actuator anomaly analysis bridging cyber-physical security; and at the policy level, we survey identity management, micro-segmentation, and zero-trust enforcement mechanisms supported by blockchain-based authentication and programmable policy enforcement points (PEPs). Our review identifies current strengths, limitations, and open challenges—including scalable firmware reverse engineering, efficient cross-ISA symbolic learning, and practical spectrum anomaly detection under constrained computing environments—and by integrating diverse security layers within a unified taxonomy, this SLR highlights both the state-of-the-art and promising research directions for advancing IoT security. Full article

Background/Objectives: Maxillary defects, whether congenital or acquired, can compromise chewing, speech, and aesthetics. This systematic review aimed to evaluate the application and characteristics of definitive palatal obturators in the rehabilitation of such defects, analyzing techniques of fabrication, materials, outcomes of the fabrication, and limitations reported in the literature. Methods: The review was conducted in accordance with PRISMA 2020 guidelines and was registered in PROSPERO (ID: 1011648). A comprehensive search was performed in PubMed, Scopus, Lilacs, and Google Scholar for studies published from 1 January 2014 to 1 January 2025. Inclusion criteria comprised adult patients treated with definitive palatal obturators and with reported follow-up. Exclusion criteria included studies on children, animals, or lacking patient data. Two reviewers independently screened studies and assessed eligibility. Bias was evaluated qualitatively across five domains. No meta-analysis was conducted; data were synthesized descriptively using charts and tables. The study was funded by the Italian Ministry of Health—Current Research IRCCS. Results: A total of 59 studies involving 83 patients (46 males, 37 females; mean age 54.6 ± 13.8 years) were included. Mucormycosis and squamous cell carcinoma were the primary causes of defects. Conventional impressions using alginate and silicone were most common, while digital techniques were reported in only 6.6% of cases. All definitive obturators were fabricated using acrylic resin, with some featuring hollow bulbs, velopharyngeal extensions, or magnetic retention. Multiple sources of bias were observed. Conclusions: Definitive palatal obturators provide effective functional and aesthetic rehabilitation for maxillary defects. However, evidence is limited by methodological weaknesses, lack of standardization, and underutilization of digital technologies. Future studies should focus on improving reporting quality, adopting innovative fabrication protocols, and generating higher-level clinical evidence to support best practices. Full article

With the recent proliferation of the Internet and the ever-evolving threat landscape, developing a reliable and effective intrusion detection system (IDS) has become an urgent need. However, one of the key challenges hindering the success of IDS development is class imbalance, which often leads to biased models and poor detection rates. To address this challenge, this paper proposes a GAN-AHR algorithm which adaptively balances the dataset by augmenting minority classes using CGAN or BSMOTE, based on class-specific characteristics such as compactness and density. By leveraging BSMOTE to oversample classes with high compactness and high density, we can exploit its simplicity and effectiveness. However, the quality of BSMOTE-generated data is significantly lower when the classes are sparse and lacking clear boundaries. In such cases, CGAN is better suited in this scenario given its ability to capture complex data distributions. We present empirical results on the NF-UNSW-NB15 dataset using a Random Forest (RF) classifier, reporting a significant improvement in the precision, recall, and F1-score of several minority classes. Specifically, a remarkable increase in the F1-score for the Shellcode and DoS classes was reported, reaching 0.90 and 0.51, respectively. Full article

Background: Simple renal cysts (SRCs) are the most common incidentally found cystic lesions in the kidney. While their association with hypertension (HT) has been explored in various studies, the findings remain inconclusive. Thus, our meta-analysis aimed to systematically evaluate the relationship between SRCs and HT (PROSPERO ID: CRD42025580609). Methods: We conducted searches in PubMed, Web of Science Core Collection, and Scopus to identify observational studies that examined the association between SRCs and HT. All articles containing animal or pediatric (<18 years old) study populations or having <10 patients in total and/or lacking a control group that did not develop HT were excluded. Two reviewers independently screened the studies and extracted the data, and the quality of each included study was assessed using the Newcastle–Ottawa Scale. Statistical analyses were performed using Review Manager 5.4. Results: In total, 12 studies with 147,310 participants were included in this meta-analysis. Presence of SRCs was associated with a 2.04-fold higher likelihood of having HT (OR 2.04, 95%CI 1.70–2.45, p < 0.0001). Multivariate analysis further revealed that SRCs were independently associated with HT (aOR 1.36, 95%CI 1.24–1.49, p < 0.0001), with multiple SRCs (aOR 1.36, 95%CI 1.26–2.42, p = 0.0008) and bilateral SRCs (aOR 2.26, 95%CI 1.12–4.59, p = 0.02) showing a stronger association. Conclusions: This study provides the first in-depth review on the topic, showing an established link between SRCs and HT even after adjustment for major confounding factors such as age, sex, renal function, and other metabolic factors. Full article

This study aims to critically assesses the application and limitations of Universal Design (UD) and Inclusive Design (ID) in Bangkok’s public parks and proposes a context-sensitive framework to enhance urban inclusivity. While UD has contributed significantly to improving physical accessibility—through standardized features such as ramps, tactile paving, and clear circulation paths—it often fails to address emotional comfort, cultural representation, and participatory engagement. In contrast, ID emphasizes co-creation, contextual adaptability, and symbolic inclusion, offering a more holistic and equity-driven approach. Using a five-dimensional comparative framework—philosophy, function, spatial logic, user engagement, and evaluation—this research analyzes three major public parks: Benjakitti Forest Park, Chatuchak (Railway) Park, and Chulalongkorn Centenary Park. Each site was evaluated through narrative critique, dimension scoring, and radar diagram visualizations. The findings reveal that while all three parks exhibit strong UD characteristics, they lack alignment with ID principles, particularly in the areas of community engagement and emotional resonance. These typologies highlight a broader trend in Thai public space planning, wherein accessibility is interpreted narrowly as compliance rather than inclusion. The study concludes by proposing policy and design recommendations for embedding ID into future park development, positioning ID not only as a design approach but as a paradigm for spatial justice, belonging, and cultural sustainability. Full article