Search Results (27,132)

In lung cytology, screeners and pathologists examine many cells in cytological specimens and describe their corresponding imaging findings. To support this process, our previous study proposed an image-finding generation model based on convolutional neural networks and a transformer architecture. However, further improvements are required to enhance the accuracy of these findings. In this study, we developed a cytology-specific image-finding generation model using a vision transformer and open-source large language models. In the proposed method, a vision transformer pretrained on large-scale image datasets and multiple open-source large language models was introduced and connected through an original projection layer. Experimental validation using 1059 cytological images demonstrated that the proposed model achieved favorable scores on language-based evaluation metrics and good classification performance when cells were classified based on the generated findings. These results indicate that a task-specific model is an effective approach for generating imaging findings in lung cytology. Full article

This paper proposes and experimentally evaluates a multi-level CPU-oriented execution method for high-throughput portion-based processing of file-backed Variant Call Format (VCF) data and automated mutation classification. The approach is based on a formally defined local processing scheme and integrates three coordinated levels of parallelism: block-based partitioning of file-backed VCF portions read sequentially into localized fragments with data-level parallel processing; task-level decomposition of feature construction into independent transformations; and execution-level specialization via JIT compilation of numerical kernels. To prevent performance degradation caused by nested parallelism, a resource-control mechanism is introduced as an execution rule that bounds effective parallelism and mitigates oversubscription, improving throughput stability on a single multi-core CPU node. Experiments on a public chromosome-17 VCF dataset for BRCA1-region pathogenicity classification demonstrate that the proposed multi-level local CPU execution (parsing/filtering, feature construction, and JIT-specialized numeric kernels) reduces runtime from 291.25 s (sequential) to 73.82 s, yielding a 3.95× speedup. When combined with resource-coordinated parallel model training, the end-to-end runtime further decreases to 51.18 s, corresponding to a 5.69× speedup, while preserving classification quality (accuracy 0.8483, precision 0.8758, recall 0.8261, F1 0.8502). A stage-wise ablation analysis quantifies the contribution of each execution level and confirms consistent scaling under resource-bounded execution. Full article

Modern cyber threats demand coordinated defensive strategies that extend beyond centralized security mechanisms. However, existing multi-agent platforms exhibit critical limitations in explicit communication and real-time coordination for cyberdefense operations. This work proposes a hierarchical multi-agent architecture for autonomous cyberdefense that addresses these limitations through structured inter-agent communication and distributed coordination. The architecture integrates a centralized monitor agent with specialized defensive swarms deployed across operational hosts. It is implemented using SPADE 4.1 (Smart Python Agent Development Environment) to enable XMPP-based (Extensible Messaging and Presence Protocol) communication with low-latency messaging and location transparency. Four specialized swarms—Network Defender, Host Defender, Anomaly Detection, and Forensic and Recovery—perform autonomous defensive tasks. A secure authentication mechanism ensures trusted communication between monitor and deployer agents. The system was evaluated in a controlled virtualized environment using the Network Defender Swarm as an illustrative case. The experimental results focus on internal coordination behavior, messaging efficiency, and end-to-end detection time across increasing levels of parallelism. A scan agent scalability analysis shows that moderate parallelism (2–16 agents) yields the lowest Total Detection Time (12.88 s across the full TCP port range), while excessive agent counts degrade performance. Results demonstrate how the proposed architecture supports low-latency communication, efficient coordination, and parallel task execution. Message latency benchmarks show improvements compared to classical agent frameworks such as JADE. These findings provide initial evidence that communication-centric multi-agent architectures can facilitate coordinated and adaptive cyberdefense operations, while serving as a platform for further experimental evaluation. Full article

This review summarizes the existing literature to investigate the role of excessive dynamic genu valgum (DGV) upon landing on subsequent movement performance in athletes. General systems theory and kinetic chain theory comprise the underlying theoretical frameworks, with an emphasis on regional interdependency in the context of lower-limb kinematics. Using a snowballing methodology, information was obtained from PubMed, CINAHL, Wiley Online Library, ProQuest, and Scopus databases, as well as through the utilization of Google Scholar and relevant biomechanics and movement analysis textbooks. Limitations include a paucity of research in the absence of injury and on DGV and subsequent performance post landing. Numerous factors, such as strength deficits of the predominant stabilizers of the knee in the frontal plane, fatigue, presence of dual tasks, and ingrained motor control, may influence medial knee excursion upon landing. Increased medial knee excursion during the transition from force attenuation to control is theorized to reduce the mechanical advantage of the quadriceps, impairing the efficiency of the stretch–shortening cycle for subsequent athletic movement performance. Mechanical and cognitive factors may influence knee biomechanics during landing and subsequent movement efficiency; however, the existing literature would benefit from further exploration of the differences in movement mechanics (e.g., acceleration) post landing in excessive DGV and the role of the trunk and subtalar joint on knee kinematics through the context of regional interdependency. This review is novel in investigating DGV from the perspective of movement performance rather than injury. Full article

The emergence of Building Information Modelling, Internet of Things, and Cave Automatic Virtual Environments (CAVEs) has created new opportunities for remote monitoring and decision-making in the operational built environment, yet empirical evidence supporting their use as alternatives to on-site observation remains limited. This study evaluates task and human performance in a controlled experiment comparing a CAVE with a real-world setting (n = 26). Situation awareness, workload, anxiety, presence, usability, and user experience were measured across conditions. Participants in the CAVE demonstrated substantially higher situation awareness (M = 92.1%) than those in the real-world condition (M = 56.8%), alongside significantly lower overall workload (NASA-TLX weighted workload = 38.3 vs. 53.8). Anxiety remained consistently low in the CAVE (ΔSTAI = –1.0), whereas participants in the real-world condition exhibited higher baseline anxiety followed by a large reduction during task execution (ΔSTAI = –13.2). The CAVE also elicited high levels of spatial presence, involvement, and realism relative to comparable projection-based systems, while usability ratings (SUS) were above industry benchmarks (M = 74.2). Together, these findings indicate that controlled immersive representations of built environments can support sensemaking and reduce extraneous cognitive load relative to live, uncontrolled on-site observation, with important implications for remote facilities management and operational decision-making. Full article

Aim: This study compared spectral profile analysis thresholds, speech-in-noise perception, and cerebral asymmetry among Carnatic musicians, Bharatanatyam dancers, and non-trained individuals and examined the influence of training duration on these measures. Method: A total of 105 right-handed adults (18–30 years) with normal hearing were divided into Carnatic musicians (n = 35), Bharatanatyam dancers (n = 35), and non-trained controls (n = 35). Spectral stream segregation was measured using the spectral profile analysis task, and speech-in-noise perception was evaluated using the Kannada QuickSIN under right, left, and binaural conditions. Cerebral asymmetry was derived from the Laterality Index. As data were non-normally distributed, non-parametric tests were used. Results: Significant group differences emerged for spectral profile thresholds, with dancers outperforming musicians and controls. Both trained groups showed superior speech-in-noise performance compared to non-trained individuals across all listening conditions, though no differences were observed between musicians and dancers. Non-trained listeners displayed a clear right-ear advantage, whereas trained groups showed minimal or no hemispheric asymmetry. Training duration negatively correlated with selected spectral profile thresholds in both trained groups and with binaural SNR-50 in dancers, indicating training-related auditory enhancement. Conclusions: Musicians and dancers demonstrate better spectral discrimination, improved speech-in-noise perception, and reduced cerebral asymmetry compared to non-trained peers. These findings underscore training-induced auditory neuroplasticity and suggest that long-term engagement in music or dance promotes efficient auditory processing and greater bilateral hemispheric involvement. Full article

One of the most harmful and deceptive forms of cybercrime is phishing, which targets users with malicious emails and websites. In this paper, we focus on the use of natural language processing (NLP) techniques and transformer models for phishing email detection. The Nazario Phishing Corpus is preprocessed and blended with real emails from the Enron dataset to create a robustly balanced dataset. Urgency, deceptive phrasing, and structural anomalies were some of the neglected features and sociolinguistic traits of the text, which underwent tokenization, lemmatization, and noise filtration. We fine-tuned two transformer models, Bidirectional Encoder Representations from Transformers (BERT) and the Robustly Optimized BERT Pretraining Approach (RoBERTa), for binary classification. The models were evaluated on the standard metrics of accuracy, precision, recall, and F1-score. Given the context of phishing, emphasis was placed on recall to reduce the number of phishing attacks that went unnoticed. The results show that RoBERTa has more general performance and fewer false negatives than BERT and is therefore a better candidate for deployment on security-critical tasks. Full article

Distinct from the traditional Modular Multilevel Converter (MMC) which focuses on fundamental frequency operation, the Static Var and Filter (SVF) within the Multi-Source Line-Commutated Converter (SLCC) system is tasked with the core function of high-frequency harmonic filtering. This paper reveals a unique engineering reliability issue stemming from this functional difference: to satisfy the Nyquist sampling theorem for precise tracking and elimination of high-frequency harmonics, the update frequency of the capacitor voltage balancing algorithm in the SLCC-SVF system is forced to increase significantly. Mathematical modeling and quantitative analysis demonstrate that this strong coupling between harmonic tracking demands and the voltage sorting strategy directly drives an abnormal surge in the average switching frequency (reaching over five times that of the fundamental condition), severely threatening device safety. To address this, an optimized adaptive hybrid modulation strategy is proposed. The system operates under Nearest Level Modulation (NLM) in normal conditions and automatically transitions to Carrier Phase-Shifted PWM (CPS-PWM)—leveraging its closed-loop balancing capability—when switching frequency or junction temperature exceeds safety thresholds. Furthermore, a non-integer frequency ratio optimization theory for low-modulation indices is constructed specifically for SVF conditions to prevent low-frequency oscillations. PLECS simulation results validate the theoretical analysis, showing that the proposed strategy effectively reduces the average switching frequency by approximately 20% under complex harmonic conditions, significantly enhancing thermal stability and operational reliability while guaranteeing filtering performance. Full article

To address the heavy reliance on experiential knowledge, fragmented multi-source information, and limited intelligence in decision-making for aircraft skin spraying processes, this paper proposes a knowledge reasoning method based on a knowledge graph. The authors construct a knowledge graph that integrates multi-structure ontology and physical rule constraints. This graph systematically organizes and manages multi-dimensional knowledge, including painting object attributes, paint performance indicators, and spraying parameters. On this basis, a three-stage reasoning mechanism with multi-granularity semantic understanding, knowledge enhancement, feature fusion, and multi-constraint intelligent matching (MKM) is designed. The model can perform semantic analysis of the user’s fuzzy query, implicit knowledge completion, and dynamic subgraph matching, so as to give the aircraft skin spraying process plan that meets the constraints of safety, compatibility, and feasibility. The experimental results show that the proposed method is superior to the traditional case-based reasoning method, graph convolutional network method, and knowledge graph embedding method in the key evaluation indices of Hit@1, Hit@3, and MRR in the knowledge reasoning task of aircraft skin spraying process. It also has good robustness and promotion value when data are scarce and parameters are uncertain. This study provides a feasible method of intelligent management and dynamic decision-making in terms of aircraft skin spraying process knowledge, and may be applied to other manufacturing fields. Full article

The enhanced long-range navigation (eLoran) system serves as an important backup method for the global navigation satellite system (GNSS) system. In long-distance transmission scenarios, the signal propagation delay of the eLoran system is affected by fluctuations in meteorological factors along the path. Regarding these issues, such as the potential timing system errors caused by meteorological factors and the limitation on the accuracy of the timing system, in this paper, an innovative prediction model is proposed to predict the propagation delay data by fusing the propagation delay data of multiple differential reference stations on the path and the path-weighted meteorological data. By collecting and processing actual data, four types of prediction tasks were designed. Comparative analyses of the prediction performance of eight common models were conducted on a unified dataset. The results show that the Pucheng–Zhengzhou path-weighted ten-factor back-propagation neural network (PZWT-BPNN) model performs the best, achieving a balance between prediction accuracy and training efficiency. This model effectively suppresses the timing errors caused by meteorological fluctuations and improves the prediction accuracy of the propagation delay of the system, providing corresponding technical support for key fields such as low-altitude economy and transportation. Full article

One of the key artefacts of epigraphy in Southeast Asia is the Singapore Stone inscription, which is, unfortunately, in a poor condition. There are huge spaces that separate the readable characters, rendering the text incomplete. This renders a traditional reconstruction and interpretation by philologists extremely challenging. We consider epigraphic restoration as a data-restoration task in this paper. We represent the inscription as a system of categorical symbols, in keeping with the original spatial disposition of characters and spaces. Our model is trained in a conservative, data-driven manner using the observed symbols to learn the local transition statistics, and it takes advantage of this information to make plausible predictions of the most likely characters in missing sequences that are short and well-constrained. The procedure generates a probabilistic hypothesis of restoration, which can be audited, as opposed to one definitive reading. The validation of masked-character recovery demonstrates that the model has a mean top-one error of 53.3%, which represents a significantly worse performance compared with simple baseline methods. The process is focused on interaction and transparency with experts. It relies upon assurance scores and prioritised alternative completions of each proposed reconstruction, as a useful means to produce hypotheses in computational epigraphy and the digital humanities. Full article

Background/Objectives: Electroencephalography (EEG) is a promising modality for fatigue detection because it directly reflects neural states; however, it is hindered by the need for subject-specific calibration and its reliance on unstable labeling. Moreover, classical EEG features are sensitive to intrinsic brain rhythm variations, causing pronounced domain shifts that degrade performance across sessions and subjects. Methods: Motivated by the biological fatigue rebound mechanism, we propose a robust cross-subject metric which we name Short-Term Second-Order Differential Entropy (ST-SODE). ST-SODE effectively suppresses the interference of background brain rhythms, enhancing robustness to cross-domain drift; consequently, its one-dimensional output can provide an indication of fatigue states without additional model training. Results: ST-SODE is validated on the public driving fatigue regression dataset SEED-VIG and on a private Vigilance classification dataset based on the N-Back task. ST-SODE achieves a correlation coefficient of 0.56 on SEED-VIG dataset (vs. 0.4 for differential entropy, DE) and a binary classification accuracy of 93.75% on the Vigilance dataset, outperforming other EEG-based fatigue metrics. Conclusions: ST-SODE offers a reliable solution for deployment in fields such as driving, manufacturing, and healthcare, where it could reduce safety incidents caused by fatigue. Full article

Background/Objectives: Perceptual awareness and decision formation unfold gradually as sensory evidence increases. Near the threshold of awareness, small differences in neural processing efficiency can be amplified into marked behavioral variability. Open-skill athletes are trained to make rapid decisions under dynamic and uncertain conditions, yet it remains unclear whether their perceptual advantage reflects enhanced early sensory sensitivity or more efficient late-stage evidence accumulation. This study aimed to identify the processing stage at which open-skill sports expertise exerts its influence. Methods: Twenty-five open-skill athletes and twenty-three non-athlete controls completed a visual orientation discrimination task with eight graded levels of stimulus visibility, ranging from subliminal to clearly visible. Behavioral performance was analyzed together with hierarchical drift–diffusion modeling to estimate latent decision parameters. Event-related potentials (ERPs) were recorded using a 64-channel EEG system during an active decision task and a passive viewing task, focusing on early (N2, P2) and late (P3) components. ERP–behavior correlations were examined across visibility levels. Results: No group differences were observed at the lowest visibility levels. Group differences emerged selectively at intermediate to high visibility levels, where athletes showed higher accuracy and a tendency toward faster responses. Drift–diffusion modeling revealed that this advantage was driven by higher drift rates in athletes, with no group differences in non-decision time, boundary separation, or starting point. Early ERP components (N2, P2) were strongly modulated by stimulus visibility but showed no consistent group differences. In contrast, the P3 component exhibited earlier and more pronounced differentiation across visibility levels in athletes. In the passive viewing task, group differences were substantially reduced. ERP–behavior analyses showed stronger and earlier P3–behavior coupling in athletes. Conclusions: Open-skill sports expertise selectively optimizes late-stage evidence accumulation and its translation into behavior, rather than enhancing unconscious or early sensory processing. Full article

Uncovering latent structures from complex, degraded data is a central challenge in modern unsupervised learning, with critical implications for downstream tasks. This principle is exemplified in the domain of aerial imagery, where the quality of images captured by drones is often compromised by complex, flight-induced degradations, thereby raising the information entropy and obscuring essential semantic patterns. Conventional super-resolution methods, trained on generic data, fail to restore these unique artifacts, thereby limiting their effectiveness for vessel identification, a task that fundamentally relies on clear pattern recognition. To bridge this gap, we introduce a novel adaptive super-resolution framework for ship images captured by drones. The approach integrates a static stage for foundational feature extraction and a dynamic stage for adaptive scene reconstruction, enabling robust performance in complex aerial environments. Furthermore, to ensure the super-resolution model’s generalizability and effectiveness, we optimize the design of degradation methods based on the characteristics of drone aerial images and construct a high-resolution dataset of ship images captured by drones. Extensive experiments demonstrate that our method surpasses existing state-of-the-art algorithms, confirming the efficacy of our proposed model and dataset. Full article

Underwater vehicles performing sampling tasks often encounter significant buoyancy variations due to payload adjustments and environmental changes, which severely challenge the stability and accuracy of controllers. To address this issue, this paper proposes a hybrid control framework that integrates Proximal Policy Optimization (PPO) with adaptive PID tuning. The framework employs PPO to dynamically adjust PID parameters online while incorporating output saturation, stepwise quantization, and dead zone filtering to ensure control safety and actuator longevity. A dual-error state representation—combining instantaneous error and its derivative—along with actuator command buffering is introduced to compensate for system lag and inertia. Comparative simulations and experimental tests demonstrate that the proposed method achieves faster convergence, lower steady-state error, and smoother control signals compared to both conventional PID and pure PPO-based control. The framework is validated through pool tests and field trials, confirming its robustness under realistic hydrodynamic disturbances. This work provides a practical and safe solution for adaptive depth control of sampling-capable AUVs operating in dynamic underwater environments. Full article