Search Results (368)

The rapid growth in large-scale distributed video conferencing, remote education, and real-time broadcasting poses significant challenges to traditional centralized streaming systems, particularly regarding scalability, cost, and reliability under high concurrency. Centralized approaches often encounter bottlenecks, increased bandwidth expenses, and diminished fault tolerance. This paper proposes a novel decentralized real-time broadcasting system employing a peer-to-peer (P2P) chain topology based on IPv6 networking and the Secure Reliable Transport (SRT) protocol. By exploiting the global addressing capability of IPv6, our solution simplifies direct node interconnections, effectively eliminating complexities associated with Network Address Translation (NAT). Furthermore, we introduce an innovative chain-relay transmission method combined with distributed node management strategies, substantially reducing reliance on central servers and minimizing deployment complexity. Leveraging SRT’s low-latency UDP transmission, packet retransmission, congestion control, and AES-128/256 encryption, the proposed system ensures robust security and high video stream quality across wide-area networks. Additionally, a WebSocket-based real-time fault detection algorithm coupled with a rapid fallback self-healing mechanism is developed, enabling millisecond-level fault detection and swift restoration of disrupted links. Extensive performance evaluations using Video Multi-Resolution Fidelity (VMRF) metrics across geographically diverse and heterogeneous environments confirm significant performance gains. Specifically, our approach achieves substantial improvements in latency, video quality stability, and fault tolerance over existing P2P methods, along with over tenfold enhancements in frame rates compared with conventional RTMP-based solutions, thereby demonstrating its efficacy, scalability, and cost-effectiveness for real-time video streaming applications. Full article

The goal of on-device continual learning is to enable models to adapt to streaming data without forgetting previously acquired knowledge, even with limited computational resources and memory constraints. Recent research has demonstrated that weighted regularization-based methods are constrained by indirect knowledge preservation and sensitive hyperparameter settings, and dynamic architecture methods are ill-suited for on-device environments due to increased resource consumption as the structure scales. In order to compensate for these limitations, replay-based continuous learning, which maintains a compact structure and stable performance, is gaining attention. The limitations of replay-based continuous learning are (1) the limited amount of historical training data that can be stored due to limited memory capacity, and (2) the computational resources of on-device systems are significantly lower than those of servers or cloud infrastructures. Consequently, designing strategies that balance the preservation of past knowledge with rapid and cost-effective updates of model parameters has become a critical consideration in on-device continual learning. This paper presents an empirical survey of replay-based continual learning studies, considering the nearest class mean classifier with replay-based sparse weight updates as a representative method for validating the feasibility of diverse edge devices. Our empirical comparison of standard benchmarks, including CIFAR-10, CIFAR-100, and TinyImageNet, deployed on devices such as Jetson Nano and Raspberry Pi, showed that the proposed representative method achieved reasonable accuracy under limited buffer sizes compared with existing replay-based techniques. A significant reduction in training time and resource consumption was observed, thereby supporting the feasibility of replay-based on-device continual learning in practice. Full article

Wide-angle images often suffer from severe radial distortion, compromising geometric accuracy and challenging image correction and real-time stitching, especially in resource-constrained embedded environments. To address this, this study proposes a wide-angle image correction and stitching framework based on a Swin Transformer, optimized for lightweight deployment on edge devices. The model integrates multi-scale feature extraction, Thin Plate Spline (TPS) control point prediction, and optical flow-guided constraints, balancing correction accuracy and computational efficiency. Experiments on synthetic and real-world datasets show that the method outperforms mainstream algorithms, with PSNR gains of 3.28 dB and 2.18 dB on wide-angle and fisheye images, respectively, while maintaining real-time performance. To validate practical applicability, the model is deployed on a Jetson TX2 NX device, and a real-time dual-camera stitching system is built using C++ and DeepStream. The system achieves 15 FPS at 1400 × 1400 resolution, with a correction latency of 56 ms and stitching latency of 15 ms, demonstrating efficient hardware utilization and stable performance. This study presents a deployable, scalable, and edge-compatible solution for wide-angle image correction and real-time stitching, offering practical value for applications such as smart surveillance, autonomous driving, and industrial inspection. Full article

The Segment Anything Model 2 (SAM2) has achieved state-of-the-art performance in pixel-level object segmentation for both static and dynamic visual content. Its streaming memory architecture maintains spatial context across video sequences, yet struggles with long-term tracking due to its static inference framework. SAM 2’s fixed temporal window approach indiscriminately retains historical frames, failing to account for frame quality or dynamic motion patterns. This leads to error propagation and tracking instability in challenging scenarios involving fast-moving objects, partial occlusions, or crowded environments. To overcome these limitations, this paper proposes SAM2Plus, a zero-shot enhancement framework that integrates Kalman filter prediction, dynamic quality thresholds, and adaptive memory management. The Kalman filter models object motion using physical constraints to predict trajectories and dynamically refine segmentation states, mitigating positional drift during occlusions or velocity changes. Dynamic thresholds, combined with multi-criteria evaluation metrics (e.g., motion coherence, appearance consistency), prioritize high-quality frames while adaptively balancing confidence scores and temporal smoothness. This reduces ambiguities among similar objects in complex scenes. SAM2Plus further employs an optimized memory system that prunes outdated or low-confidence entries and retains temporally coherent context, ensuring constant computational resources even for infinitely long videos. Extensive experiments on two video object segmentation (VOS) benchmarks demonstrate SAM2Plus’s superiority over SAM 2. It achieves an average improvement of 1.0 in J&F metrics across all 24 direct comparisons, with gains exceeding 2.3 points on SA-V and LVOS datasets for long-term tracking. The method delivers real-time performance and strong generalization without fine-tuning or additional parameters, effectively addressing occlusion recovery and viewpoint changes. By unifying motion-aware physics-based prediction with spatial segmentation, SAM2Plus bridges the gap between static and dynamic reasoning, offering a scalable solution for real-world applications such as autonomous driving and surveillance systems. Full article

E-commerce live streaming in China has become a major retail channel, yet hosts often employ subtle phonetic or semantic “morphs” to evade moderation and make unsubstantiated claims, posing risks to consumers. To address this, we study the Live Auditory Morph Resolution (LiveAMR) task, which restores morphed speech transcriptions to their true forms. Building on prior text-based morph resolution, we propose an LLM-enhanced training framework that mines three types of explanation knowledge—predefined morph-type labels, LLM-generated reference corrections, and natural-language rationales constrained for clarity and comprehensiveness—from a frozen large language model. These annotations are concatenated with the original morphed sentence and used to fine-tune a lightweight T5 model under a standard cross-entropy objective. In experiments on two test sets (in-domain and out-of-domain), our method achieves substantial gains over baselines, improving $F_{0.5}$ by up to 7 pp in-domain (to 0.943) and 5 pp out-of-domain (to 0.799) compared to a strong T5 baseline. These results demonstrate that structured LLM-derived signals can be mined without fine-tuning the LLM itself and injected into small models to yield efficient, accurate morph resolution. Full article

Soil texture, defined by the proportions of sand, silt, and clay particles in the soil, is one of the most essential physical properties of soil. High-resolution soil texture data can provide critical parameter support for soil hydrological modeling, agricultural production management, and ecosystem assessment. In digital soil mapping, previous studies often predicted the sand, silt, and clay contents in soil and then indirectly calculated soil texture. Currently, approaches that directly map soil texture by classification modeling are gaining increasing attention due to the decreased error from data conversion, but few studies have systematically compared these two methods yet. In this study, we comprehensively assessed the performance of direct and indirect predicting soil texture using four machine learning algorithms (e.g., extreme gradient boosting, random forest, gradient boosting decision tree, and extremely randomized tree) with 190 covariates from the Digital Elevation Model, Sentinel-1/2 satellite images, and classification maps and generated a 10 m resolution soil texture map based on 405 topsoil (0–20 cm) sample data collected in Suichuan County, China. The results showed that compared with indirect predictions, direct predictions improved overall accuracy (OA) by 20.57–44.19% and the Kappa coefficient (Kappa) by 0.220–0.402. Among the models used, the XGB model achieved the highest accuracy (OA: 0.948; Kappa: 0.931) and the lowest uncertainty (confusion index: 0.052). The direct prediction map (nine classes recorded) exhibited more detailed and diverse spatial distribution patterns than the indirect prediction map (six classes recorded), aligning better with the actual environment. Based on accuracy validation and spatial distribution, the performance of the XGB model was best during direct prediction. The Shapley additive explanation from the XGB model revealed that the normalized height and stream power indices were the most significant factors driving the soil texture in the study area. Our results provide a reference for future studies on soil texture mapping using machine learning models. Full article

In today’s digital era, social media platforms like Instagram have become deeply embedded in daily life, generating billions of content items each day. This vast stream of publicly accessible data presents a unique opportunity for researchers to gain insights into human behaviour and personality. However, leveraging such unstructured and highly variable data for psychological analysis introduces significant challenges, including data sparsity, noise, and ethical considerations around privacy. This study addresses these challenges by exploring the potential of machine learning to infer personality traits from Instagram content. Motivated by the growing demand for scalable, non-intrusive methods of psychological assessment, we developed a personality prediction system combining convolutional neural networks (CNNs) and random forest (RF) algorithms. Our model is grounded in the Big Five Personality framework, which includes Extraversion, Agreeableness, Conscientiousness, Neuroticism, and Openness. Using data collected with informed consent from 941 participants, we extracted visual features from their Instagram images using two pretrained CNNs, which were then used to train five RF models, each targeting a specific trait. The proposed system achieved an average mean absolute error of 0.1867 across all traits. Compared to the PAN-2015 benchmark, our method demonstrated competitive performance. These results highlight that using social media data for personality prediction offers potential applications in personalized content delivery, mental health monitoring, and human–computer interactions. Full article

A bench test apparatus was developed to address the impact of varying terrain undulation on sowing depth in multi-row wheat sowing machines. In addition, a real-time sowing depth control model was proposed and implemented, enabling automatic adjustment of the sowing depth and ensuring uniform seed placement. The model operates by first specifying a target sowing depth, then acquiring real-time sowing depth measurements via a laser range sensor and terrain feature data ahead of the machine via an array-based LiDAR sensor. These two data streams undergo multi-sensor fusion to produce an accurate error and error rate. A fuzzy PID control algorithm then performs online parameter tuning of the PID gains, generating the control output needed to drive the stepper motor and adjust the depth-limiting wheel height, thereby precisely regulating the sowing depth. Experimental results demonstrate that under representative test conditions, the system achieves excellent sowing depth control performance; average error reductions of 10.7%, 22.9%, and 9.6% were observed when using fuzzy PID control versus no control. This work provides a technical foundation for intelligent sowing depth control in wheat sowing machines and lays the groundwork for future in-field adaptive operation and multi-scenario integrated control. Full article

The construction industry urgently requires sustainable alternatives to conventional cement to mitigate its environmental footprint, which includes 8% of global CO₂ emissions. This review critically examines the potential of rice husk ash (RHA) and silica fume (SF)—industrial and agricultural byproducts—as high-performance supplementary cementitious materials (SCMs) in soil–cement composites. Their pozzolanic reactivity, microstructural enhancement mechanisms, and durability improvements (e.g., compressive strength gains of up to 31.7% for RHA and 250% for SF) are analyzed. This study highlights the synergistic effects of RHA/SF blends in refining pore structure, reducing permeability, and enhancing resistance to chemical attacks. Additionally, this paper quantifies the environmental benefits, including CO₂ emission reduction (up to 25% per ton of cement replaced) and resource recovery from agricultural/industrial waste streams. Challenges such as material variability, optimal dosage (10–15% RHA, 5–8% SF), and regulatory barriers are discussed, alongside future directions for scalable adoption. This work aligns with SDGs 9, 11, and 12, offering actionable insights for sustainable material design. Full article

The construction industry’s escalating environmental footprint, coupled with the underutilization of construction waste streams, necessitates innovative approaches to sustainable material design. This study investigates the dual functionality of recycled clay brick powder (RCBP) as both a supplementary cementitious material (SCM) and an alkali–silica reaction (ASR) inhibitor in hybrid mortar systems incorporating recycled glass (RG) and recycled clay brick (RCB) aggregates. Leveraging the pozzolanic activity of RCBP’s residual aluminosilicate phases, the research quantifies its influence on mortar durability and mechanical performance under varying substitution scenarios. Experimental findings reveal a nonlinear relationship between RCBP dosage and mortar properties. A 30% cement replacement with RCBP yields a 28-day activity index of 96.95%, confirming significant pozzolanic contributions. Critically, RCBP substitution ≥20% effectively mitigates ASRs induced by RG aggregates, with optimal suppression observed at 25% replacement. This threshold aligns with microstructural analyses showing RCBP’s Al³⁺ ions preferentially reacting with alkali hydroxides to form non-expansive gels, reducing pore solution pH and silica dissolution rates. Mechanical characterization reveals trade-offs between workability and strength development. Increasing RCBP substitution decreases mortar consistency and fluidity, which is more pronounced in RG-RCBS blends due to glass aggregates’ smooth texture. Compressively, both SS-RCBS and RG-RCBS mortars exhibit strength reduction with higher RCBP content, yet all specimens show accelerated compressive strength gain relative to flexural strength over curing time. Notably, 28-day water absorption increases with RCBP substitution, correlating with microstructural porosity modifications. These findings position recycled construction wastes and glass as valuable resources in circular economy frameworks, offering municipalities a pathway to meet recycled content mandates without sacrificing structural integrity. The study underscores the importance of waste synergy in advancing sustainable mortar technology, with implications for net-zero building practices and industrial waste valorization. Full article

Bridges are fundamental components of transportation infrastructure, facilitating the efficient movement of people and goods. However, the conservation of heritage bridges introduces additional challenges, encompassing environmental, social, cultural, and economic dimensions of sustainability. This study investigates risk mitigation strategies for a heritage-listed, 120-year-old reinforced concrete bridge in Australia—one of the nation’s earliest examples of reinforced concrete construction, which remains operational today. The structure faces multiple risks, including passage of overweight vehicles, environmental degradation, progressive crack development due to traffic loading, and potential foundation scouring from an adjacent stream. Due to the heritage status and associated legal constraints, only non-invasive testing methods were employed. Ambient vibration testing was conducted to identify the bridge’s dynamic characteristics under normal traffic conditions, complemented by non-contact displacement monitoring using laser distance sensors. A digital twin structural model was subsequently developed and validated against field data. This model enabled the execution of various “what-if” simulations, including passage of overweight vehicles and loss of foundation due to scouring, providing quantitative assessments of potential risk scenarios. Drawing on insights gained from the case study, the article proposes a six-phase Incident Response Framework tailored for heritage bridge management. This comprehensive framework incorporates remote sensing technologies for incident detection, digital twin-based structural assessment, damage containment and mitigation protocols, recovery planning, and documentation to prevent recurrence—thus supporting the long-term preservation and functionality of heritage bridge assets. Full article

Municipal wastewater effluent (MWWE) is a common source of nutrient enrichment and provides a route for emerging substances of concern (ESOCs) to enter aquatic systems. Community composition and abundance metrics of benthic macroinvertebrates are commonly utilized to assess ecological impacts associated with nutrient enrichment; however, the responses of these metrics in systems with diverse chemical mixtures from MWWE, are not well understood. This study specifically addresses the effects of cumulative loading of tertiary-treated MWWE through responses in benthic macroinvertebrate communities in experimental control and treatment streams. Treatment streams used source river water previously exposed to upstream wastewater treatment plants but with an additional 5% by volume tertiarily treated MWWE, while control streams used only source river water. Surbers and artificial substrate rock baskets were used to examine impacts on both established and colonizing benthic communities, respectively. No significant differences were observed between the control and treatment streams in any of the community metrics of well-established benthic communities. In contrast, significant decreases in colonizing taxon diversity and evenness were found between treatment and control streams. The dominant taxa (most abundant family, by percentage of sample) in the community, often filter feeders, significantly increased in percentage of the total community in treatment streams. This response was consistent with a nutrient enrichment effect, with no evidence of ESOC related toxicity. This study highlights the need for bioassessment programs to utilize approaches involving varied in-situ sampling methods and controlled exposure systems to gain a better understanding of how various stages of community-level development are impacted by urban pollutants such as MWWE. Full article

Commercial wearable systems for surface electromyography (sEMG) acquisition often trade bandwidth, synchronization, and battery life for miniaturization, and their proprietary designs inhibit reproducibility and cost-effective customization. To address these limitations, we developed MOT, a fully wireless, multichannel platform built from commodity components that can be replicated in academic laboratories. Each sensor node integrates an AD8232 analog front-end configured for 19–690 Hz bandwidth (59 dB mid-band gain) with a 12-bit successive approximation ADC sampling at 1 kS/s. Packets of 120 samples are broadcast via the low-latency ESP-NOW 2.45 GHz protocol to a central hub, which timestamps and streams data to a host PC over USB-UART. Bench tests confirmed the analog response and showed mains interference at least 40 dB below voluntary contraction levels; the cumulative packet loss remained below 0.5% for six simultaneous channels at 100 m line-of-sight, with end-to-end latency under 3 ms. A 180 mAh Li-ion cell was used to power each node for 1.8 h of continuous operation at 100 mA average draw, and the complete sensor, including enclosure, was found to weigh 22 g. MOT reduced a 60 Hz artifact magnitude by up to 22 dB while preserving signal bandwidth. The hardware, therefore, provides a compact and economical solution for biomechanics, rehabilitation, and human–machine interface research that demands mobile, high-fidelity sEMG acquisition. Full article

The United Kingdom has long been a frontrunner in green finance, establishing programs like the Green Finance Institute to promote corporate engagement in sustainable initiatives. The Green Finance Strategy, enacted in 2019, aligns UK financial procedures with international standards, including the EU taxonomy for sustainable Activities. The study examined how sustainable finance enhances the corporate reputation of the firms listed on the London Stock Exchange. A purposive sampling yielded 17 years of data from 143 non-financial companies from the Thomson Reuters Eikon DataStream between 2007 and 2023. In dealing with the issue of endogeneity and auto-serial correlation, the Generalized Methods of Movement (GMM) was employed to provide reliable and unbiased estimation results. The study revealed a positive impact of green bond issues, environmental expenditures, and policies for emission reduction on corporate reputation. The moderating relationship between green bond issues, environmental expenditures, and board diversity revealed a positive and significant relationship with corporate reputation. Managers should ensure that their endorsed activities gain public recognition and align with sustainability goals, particularly by emphasizing the issuance of green bonds in their financing strategy. They should also collaborate with environmental experts and stakeholders to ensure that the outcomes of funded projects are evaluated in line with international ESG standards. Full article

Vibrational double diffusion has gained increasing attention in recent studies due to its role in enhancing mixing, disrupting thermal boundary layers, and stabilizing convection structures, especially in nanofluids and porous media. This study focuses on the case of two-phase nanofluid flow in the presence of vibrational effects. The flow domain is a fined chamber that is filled with a non-Darcy porous medium. Two concentration formulations are proposed for the species concentration and nanoparticle concentration. The thermal radiation is in both the x- and y-directions, while the flow domain is considered to be inclined. The solution technique depends on an effective finite volume method. The periodic behaviors of the stream function, Nusselt numbers, and Sherwood numbers against the progressing time are presented and interpreted. From the major results, a significant reduction in harmonic behaviors of the stream function is obtained as the lengths of the fins are raised while the gradients of the temperature and concentration are improved. Also, a higher rate of heat and mass transfer is obtained when the vibration frequency is raised. Furthermore, for fixed values of the Rayleigh number and vibration frequency (Ra = 10⁴, σ = 500), the heat transfer coefficient improves by 27.2% as the fin length increases from 0.1 to 0.25. Full article