Search Results (358)

Technical aspects of desert locust (Schistocerca gregaria) management have markedly improved since the late 1980s. Examples include modernized electronic communication systems linking stakeholders, global positioning system precision for reporting and treatment of locust aggregations, ultra-low-volume insecticide formulations and application techniques that reduce both environmental impact and chemical use, and computerized integration of multidisciplinary data for monitoring and forecasting outbreaks, upsurges, and plagues. Despite the remote and rugged terrain where the species thrives, tools and vehicles for surveillance and control generally exist—although they are not always available when needed. As technical aspects of desert locust control continue to be surmounted, human-based factors remain substantial, underlying, multifaceted obstacles. Funding shortfalls are frequently cited but rarely analyzed in depth. This article focuses on these underlying human constraints, including rigid conceptual dogmas, diverse forms of insecurity, political interference, weak communication among stakeholders, decreasing donor interest, confusion between emergency response and development objectives, loss of institutional memory, inadequate staff training, and limited attention to dynamic, real-time developments. These human-based impediments are critical because they underlie systemic unpreparedness and hinder the transition toward more integrated, proactive, and sustainable locust management approaches. As such, they contribute to the onset, intensity, and prolonged duration of desert locust episodes. Full article

Traffic violations, the primary cause of road accidents, threaten public safety by disrupting traffic flow and causing substantial casualties and economic losses. Accurate spatiotemporal prediction of violations offers critical insights for proactive traffic management. While Graph Attention Network (GAT) methods excel in spatiotemporal forecasting, their practical deployment is hindered by prohibitive computational costs when handling dynamic large-scale data. To address this issue, we propose a Lightweight Traffic Violation Prediction with Graph Attention Distillation (LTVPGA) model, transferring spatial topology comprehension from a complex GAT to an efficient multilayer perceptron (MLP) via knowledge distillation. Our core contribution lies in topology-invariant knowledge transfer, where spatial relation priors distilled from the teacher’s attention heads enable the MLP student to bypass explicit graph computation. This approach achieves significant efficiency gains for large-scale data—notably accelerated inference time and reduced memory overhead—while preserving modeling capability. We conducted a performance comparison between LTVPGA, Conv-LSTM, and GATR (teacher model). LTVPGA achieved revolutionary efficiency: consuming merely 15% memory and 0.6% training time of GATR while preserving nearly the same accuracy. This capacity enables practical deployment without sacrificing fidelity, providing a scalable solution for intelligent transportation governance. Full article

Accurate state-of-charge (SOC) estimation is crucial in smart-building energy management systems, where rooftop photovoltaics and lithium-ion energy storage systems must be coordinated to align renewable generation with real-time demand. This paper introduces a novel, modular hybrid framework for SOC estimation, which synergistically combines the predictive power of artificial neural networks (ANNs), the logical consistency of finite state automata (FSA), and an adaptive dynamic supervisor layer. Three distinct ANN architectures—feedforward neural network (FFNN), long short-term memory (LSTM), and 1D convolutional neural network (1D-CNN)—are employed to extract comprehensive temporal and spatial features from raw data. The inherent challenge of ANNs producing physically irrational SOC values is handled by processing their raw predictions through an FSA module, which constrains physical validity by applying feasible transitions and domain constraints based on battery operational states. To further enhance the adaptability and robustness of the framework, two advanced supervisor mechanisms are developed for model selection during estimation. A lightweight rule-based supervisor picks a model transparently using recent performance scores and quick signal heuristics, whereas a more advanced double deep Q-network (DQN) reinforcement-learning supervisor continuously learns from reward feedback to adaptively choose the model that minimizes SOC error under changing conditions. This RL agent dynamically selects the most suitable ANN+FSA model, significantly improving performance under varying and unpredictable operational conditions. Comprehensive experimental validation demonstrates that the hybrid approach consistently outperforms raw ANN predictions and conventional extended Kalman filter (EKF)-based methods. Notably, the RL-based supervisor exhibits good adaptability and achieves lower error results in challenging high-variance scenarios. Full article

Territorial transformations in Indigenous regions are shaped by intersecting ecological, political, and cultural dynamics. In San Juan Bautista Valle Nacional, Oaxaca, the construction of the Cerro de Oro dam disrupted river flows, displaced livelihoods, and triggered the decline of irrigated agriculture. This study examines the long-term impacts of these changes on land use, demographics, and cultural practices, emphasizing women’s contributions to community resilience. Using a mixed-methods approach, the study integrates geospatial analysis (1992–2021), census data (2000–2020), documentary review, and ethnographic fieldwork, including participatory mapping. Results show a shift toward seasonal rainfed agriculture, fluctuating forest cover, and a rise in female-headed households. Women have emerged as central actors in adapting to change through practices such as seed saving, agroforestry, and backstrap-loom weaving. These spatially grounded practices, enacted across varied socio-ecological zones, sustain food systems, preserve biodiversity, and reinforce biocultural memory. Although often overlooked in formal governance, women’s territorial agency plays a vital role in shaping land use and community adaptation. This research highlights the need to recognize Indigenous women’s roles in managing change and sustaining territorial heritage. Acknowledging these contributions is essential for building inclusive, culturally grounded, and sustainable development pathways in regions facing structural and environmental pressures. Full article

Learning has established itself as a fundamental pillar for the adaptation and continuous growth of organisations. This article analyses the impact of organisational learning on innovation and institutional performance in universities, focusing on five interdependent dimensions: organisational culture, knowledge management, organisational memory, continuous feedback, and dynamic capabilities. Through a narrative review of the specialised literature, a systemic framework is proposed that conceives organisational learning as an integral and strategic process, where each dimension contributes in key ways to institutional strengthening. Organisational culture fosters shared values and readiness for change; knowledge management enables the generation and application of relevant knowledge; organisational memory guarantees the continuity and transfer of learning; constant feedback facilitates adaptation; and dynamic capabilities prepare the university to face complex and changing contexts. As a practical contribution, an operational agenda is designed that links each dimension with a strategic action, a follow-up indicator, a suggested institutional tool, and theoretical references. This proposal seeks to offer an adaptable roadmap for management teams, quality assurance units, and university management training spaces. Full article

Parkinson’s disease (PD) is a progressive neurodegenerative disorder that severely impacts motor function, necessitating early detection for effective management. However, current diagnostic methods are expensive and resource-intensive, limiting their accessibility. This study proposes a non-invasive, gait-based screening approach for PD using time-series analysis of video-derived motion data. Gait patterns indicative of PD are analyzed using videos containing walking sequences of PD subjects. The video data are processed via computer vision and human pose estimation techniques to extract key body points. Classification is performed using K-Nearest Neighbors (KNN) and Long Short-Term Memory (LSTM) networks in conjunction with time-series techniques, including Dynamic Time Warping (DTW), Bag of Patterns (BoP), and Symbolic Aggregate Approximation (SAX). KNN classifies based on similarity measures derived from these methods, while LSTM captures complex temporal dependencies. Additionally, Shapelet-based Classification is independently explored for its ability to serve as a self-contained classifier by extracting discriminative motion patterns. On a self-collected dataset (43 instances: 8 PD and 35 healthy), DTW-based classification achieved 88.89% accuracy for both KNN and LSTM. On an external dataset (294 instances: 150 healthy and 144 PD with varying severity), KNN and LSTM achieved 71.19% and 57.63% accuracy, respectively. The proposed approach enhances PD detection through a cost-effective, non-invasive methodology, supporting early diagnosis and disease monitoring. By integrating machine learning with clinical insights, this study demonstrates the potential of AI-driven solutions in advancing PD screening and management. Full article

Children with COVID-19 typically experience milder symptoms and lower hospitalization rates, though severe cases do occur. Understanding age-related immune responses is crucial for future preparedness. We characterized immune response dynamics to SARS-CoV-2 in 145 samples from 119 pediatric patients (<18 years) with confirmed infection, assessed at four distinct time points: <14 days, 14 days–3 months, 3–6 months, and 6–12 months post-infection. At infection, patients presented increased activated T-cells, higher levels of exhaustion (i.e., PD-1⁺), lower numbers of unswitched memory B-cells, and increased antibody-secreting cells (ASCs). Both humoral and cellular anti-SARS-CoV-2 responses increased over time (all patients showed measurable responses in the last assessment). Asymptomatic/mildly symptomatic patients (58.6%) showed increased specific cellular responses from infection onwards, along with enriched memory B-cell subsets (but not ASCs), and distinct T-cell activation profiles. Children with severe disease were younger, predominantly boys, displayed altered T/B-cell ratios, and reduced PHA responses when infected. Compared to adolescents, younger children showed lower antibody titers and weaker cellular responses to SARS-CoV-2, possibly underlining the higher prevalence of severe manifestations in younger children. Our study illustrates important age-, gender-, and disease severity-dependent variations in immune responses to SARS-CoV-2, which can be helpful in improving patient management and immunization strategies adjusted to age groups. Full article

Open-vocabulary semantic segmentation aims to label each pixel of an image based on text descriptions provided at inference time. Recent approaches for this task are based on methods which require two stages: the first one uses a mask generator to generate mask proposals, while the other one deals with segment classification using a pre-trained vision–language model, such as CLIP. However, since CLIP is pre-trained on natural images, the model struggles with segmentation masks because of their abstract nature. In this paper, we introduce OpenMamba, a novel approach to creating high-level guidance maps to assist in extracting CLIP features within the masked regions for classification. High-level guidance maps are generated by leveraging both visual and textual modalities and introducing State Space Duality (SSD) as an efficient way to tackle the open-vocabulary semantic segmentation task. Also, we propose a new matching technique for the mask proposals, based on IoU with a dynamic threshold conditioned by mask quality and we introduce a contrastive-based loss to assure that similar mask proposals achieve similar CLIP embeddings. Comprehensive experiments across open-vocabulary benchmarks show that our method can achieve superior performance compared to other approaches while managing to reduce memory consumption. Full article

Deployment of Unmanned Aerial Vehicles (UAVs) continues to expand rapidly across a wide range of applications, including environmental monitoring, precision agriculture, and disaster response. Despite their increasing ubiquity, UAVs remain inherently vulnerable to security threats due to resource-constrained hardware, energy limitations, and reliance on open wireless communication channels. These factors render traditional cryptographic solutions impractical, thereby necessitating the development of lightweight, UAV-specific security mechanisms. This review article presents a comprehensive analysis of lightweight encryption techniques and key management strategies designed for energy-efficient and secure UAV communication. Special emphasis is placed on recent cryptographic advancements, including the adoption of the ASCON family of ciphers and the emergence of post-quantum algorithms that can secure UAV networks against future quantum threats. Key management techniques such as blockchain-based decentralized key exchange, Physical Unclonable Function (PUF)-based authentication, and hierarchical clustering schemes are evaluated for their performance and scalability. To ensure comprehensive protection, this review introduces a multilayer security framework addressing vulnerabilities from the physical to the application layer. Comparative analysis of lightweight cryptographic algorithms and multiple key distribution approaches is conducted based on energy consumption, latency, memory usage, and deployment feasibility in dynamic aerial environments. Unlike design- or implementation-focused studies, this work synthesizes existing literature across six interconnected security dimensions to provide an integrative foundation. Our review also identifies key research challenges, including secure and efficient rekeying during flight, resilience to cross-layer attacks, and the need for standardized frameworks supporting post-quantum cryptography in UAV swarms. By highlighting current advancements and research gaps, this study aims to guide future efforts in developing secure communication architectures tailored to the unique operational constraints of UAV networks. Full article

The evolution toward sixth generation (6G) wireless networks promises higher performance, greater flexibility, and enhanced intelligence. However, it also introduces a substantially enlarged attack surface driven by open, disaggregated, and multi-vendor Open RAN (O-RAN) architectures that will be utilised in 6G networks. This paper addresses the urgent need for a practical Zero Trust (ZT) deployment model tailored to O-RAN specification. To do so, we introduce a novel hybrid ZT deployment model that establishes the trusted foundation for AI/ML-driven security in O-RAN, integrating macro-level enclave segmentation with micro-level application sandboxing for xApps/rApps. In our model, the Policy Decision Point (PDP) centrally manages dynamic policies, while distributed Policy Enforcement Points (PEPs) reside in logical enclaves, agents, and gateways to enable per-session, least-privilege access control across all O-RAN interfaces. We demonstrate feasibility via a Proof of Concept (PoC) implemented with Kubernetes and Istio and based on the NIST Policy Machine (PM). The PoC illustrates how pods can represent enclaves and sidecar proxies can embody combined agent/gateway functions. Performance discussion indicates that enclave-based deployment adds 1–10 ms of additional per-connection latency while CPU/memory overhead from running a sidecar proxy per enclave is approximately 5–10% extra utilisation, with each proxy consuming roughly 100–200 MB of RAM. Full article

In the field of mobile crowdsensing (MCS), a large number of tasks rely on the participation of ordinary mobile device users for data collection and processing. This model has shown great potential for applications in environmental monitoring, traffic management, public safety, and other areas. However, the enthusiasm of participants and the quality of uploaded data directly affect the reliability and practical value of the sensing results. Therefore, the design of incentive mechanisms has become a core issue in driving the healthy operation of MCS. The existing research, when optimizing long-term utility rewards for participants, has often failed to fully consider dynamic changes in trustworthiness. It has typically relied on historical data from a single point in time, overlooking the long-term dependencies in the time series, which results in suboptimal decision-making and limits the overall efficiency and fairness of sensing tasks. To address this issue, a credibility-aware incentive mechanism based on long short-term memory and proximal policy optimization (CIM-LP) is proposed. The mechanism employs a Markov decision process (MDP) model to describe the decision-making process of the participants. Without access to global information, an incentive model combining long short-term memory (LSTM) networks and proximal policy optimization (PPO), collectively referred to as LSTM-PPO, is utilized to formulate the most reasonable and effective sensing duration strategy for each participant, aiming to maximize the utility reward. After task completion, the participants’ credibility is dynamically updated by evaluating the quality of the uploaded data, which then adjusts their utility rewards for the next phase. Simulation results based on real datasets show that compared with several existing incentive algorithms, the CIM-LP mechanism increases the average utility of the participants by 6.56% to 112.76% and the task completion rate by 16.25% to 128.71%, demonstrating its significant advantages in improving data quality and task completion efficiency. Full article

The growing demand for efficient energy management has become essential for achieving sustainable development across social, economic, and environmental sectors. Accurate energy demand forecasting plays a pivotal role in energy management. However, energy demand data present unique challenges due to their complex characteristics, such as multi-seasonality, hidden structures, long-range dependency, irregularities, volatilities, and nonlinear patterns, making energy demand forecasting challenging. We propose a hybrid dimension reduction deep learning algorithm, Temporal Variational Residual Network (TVRN), to address these challenges and enhance forecasting performance. This model integrates variational autoencoders (VAEs), Residual Neural Networks (ResNets), and Bidirectional Long Short-Term Memory (BiLSTM) networks. TVRN employs VAEs for dimensionality reduction and noise filtering, ResNets to capture local, mid-level, and global features while tackling gradient vanishing issues in deeper networks, and BiLSTM to leverage past and future contexts for dynamic and accurate predictions. The performance of the proposed model is evaluated using energy consumption data, showing a significant improvement over traditional deep learning and hybrid models. For hourly forecasting, TVRN reduces root mean square error and mean absolute error, ranging from 19% to 86% compared to other models. Similarly, for daily energy consumption forecasting, this method outperforms existing models with an improvement in root mean square error and mean absolute error ranging from 30% to 95%. The proposed model significantly enhances the accuracy of energy demand forecasting by effectively addressing the complexities of multi-seasonality, hidden structures, and nonlinearity. Full article

Urban multimodal travel trajectory prediction is a core challenge in Intelligent Transportation Systems (ITSs). It requires modeling both spatiotemporal dependencies and dynamic interactions among different travel modes such as taxi, bike-sharing, and buses. To address the limitations of existing methods in capturing these diverse trajectory characteristics, we propose a spatiotemporal multi-model ensemble framework, which is an ensemble model called GLEN (GCN and LSTM Ensemble Network). Firstly, the trajectory feature adaptive driven model selection mechanism classifies trajectories into dynamic travel and fixed-route scenarios. Secondly, we use a Graph Convolutional Network (GCN) to capture dynamic travel patterns and Long Short-Term Memory (LSTM) network to model fixed-route patterns. Subsequently the outputs of these models are dynamically weighted, integrated, and fused over a spatiotemporal grid to produce accurate forecasts of urban total traffic flow at multiple future time steps. Finally, experimental validation using Beijing’s Chaoyang district datasets demonstrates that our framework effectively captures spatiotemporal and interactive characteristics between multimodal travel trajectories and outperforms mainstream baselines, thereby offering robust support for urban traffic management and planning. Full article

The Working Set concept, originally introduced by P. Denning for memory management, defines a dynamic subset of system elements actively in use. Designed to reduce page faults and prevent thrashing, it has proven effective in optimizing memory performance. This study explores the interdisciplinary potential of the Working Set by applying it to two distinct domains: virtual memory systems and epidemiological modeling. We demonstrate that focusing on the active subset of a system enables optimization in both contexts—minimizing page faults and containing epidemics via dynamic isolation. The effectiveness of this approach is validated through memory access simulations and agent-based epidemic modeling. The advantages of using the Working Set as a general framework for describing the behavior of dynamic systems are discussed, along with its applicability across a wide range of scientific and engineering problems. Full article

Ventilation in subway and railway tunnels is a critical safety component, especially during fire emergencies, where effective smoke and heat management is essential for successful evacuation and firefighting efforts. The Subway Environmental Simulation (SES, Version 4.1) model is widely used for predicting airflow and thermal conditions during fire events, but its accuracy in real-world applications requires validation. This study compares SES predictions with experimental data from the Memorial Tunnel fire ventilation tests to evaluate its performance in simulating the effects of jet fans on longitudinal ventilation. The analysis focuses on SES’s ability to predict flow rate and temperature distributions. Results showed reasonable agreement between SES-predicted airflows and temperatures. However, SES tended to underpredict temperatures upstream and near the fire source, indicating a limitation in simulating thermal behavior close to the fire. These findings suggest that SES can be a reliable tool for tunnel ventilation design if certain safety margins, based on the error values identified in this study, are considered. Nonetheless, further improvements are necessary to enhance its accuracy, particularly in modeling heat transfer dynamics and the impact of fire-induced temperature changes. Future work should focus on conducting additional full-scale test validations and model refinements to improve SES’s predictive capabilities for fire safety planning. Full article