Search Results (335)

This study proposes a behavioral monitoring framework for newborn piglets based on SPMF-YOLO object detection and ByteTrack multi-object tracking, which enables precise quantification of early postnatal activity levels and health assessment. The method enhances small-object detection performance by incorporating the SPDConv module, the MFM module, and the NWD loss function into YOLOv11. When combined with the ByteTrack algorithm, it achieves stable tracking and maintains trajectory continuity for multiple targets. An annotated dataset containing both detection and tracking labels was constructed using video data from 10 piglet pens for evaluation. Experimental results indicate that SPMF-YOLO achieved a recognition accuracy rate of 95.3% for newborn piglets. When integrated with ByteTrack, it achieves 79.1% HOTA, 92.2% MOTA, and 84.7% IDF1 in multi-object tracking tasks, thereby outperforming existing methods. Building upon this foundation, this study further quantified the cumulative movement distance of each newborn piglet within 30 min after birth and proposed a health-assessment method based on statistical thresholds. The results demonstrated an overall consistency rate of 98.2% across pens and an accuracy rate of 92.9% for identifying abnormal individuals. The results validated the effectiveness of this method for quantifying individual behavior and assessing health status in newborn piglets within complex farming environments, providing a feasible technical pathway and scientific basis for health management and early intervention in precision animal husbandry. Full article

The Internet of Vehicles (IoV) is becoming increasingly vulnerable to zero-day (ZD) cyberattacks, which often bypass conventional intrusion detection systems. To mitigate this challenge, this study proposes Zero-Day Bidirectional Encoder Representations from Transformers approach (ZDBERTa), a zero-shot learning (ZSL)-based framework for ZD attack detection, evaluated on the CICIoV2024 dataset. Unlike conventional AI models, ZSL enables the classification of attack types not previously encountered during the training phase. Two dataset variants are formed: Variant 1, created through synthetic traffic generation using a mixture of pattern-based, crossover, and mutation techniques, and Variant 2, augmented with a Generative Adversarial Network (GAN). To replicate realistic zero-day conditions, denial-of-service (DoS) attacks were omitted during training and introduced only at testing. The proposed ZDBERTa incorporates a Byte-Pair Encoding (BPE) tokenizer, a multi-layer transformer encoder, and a classification head for prediction, enabling the model to capture semantic patterns and identify previously unseen threats. The experimental results demonstrate that ZDBERTa achieves 86.677% accuracy on Variant 1, highlighting the complexity of zero-day detection, while performance significantly improves to 99.315% on Variant 2, underscoring the effectiveness of GAN-based augmentation. To the best of our knowledge, this is the first research to explore ZD detection within CICIoV2024, contributing a novel direction toward resilient IoV cybersecurity. Full article

Portable and wearable sensors have gained attention in recent years to perform measurements in many different applications. Sensors based on Electrical Impedance Spectroscopy (EIS) are particularly promising, because they can make accurate measurements with minimum perturbation to the sample under test. Electrochemical biosensors are devices that use electrochemical techniques to measure a target analyte. In the case of electrochemical biosensors based on EIS, the measured impedance spectrum is fitted to that of an equivalent electrical circuit, whose component values are then used to estimate the concentration of the target analyte. Fitting EIS data is usually carried out by sophisticated algorithms running on a PC. In this paper, we have evaluated the feasibility to perform EIS data fitting using simple Artificial Neural Networks (ANNs) that can be run on resource constrained microcontrollers, which are typically used for portable and wearable sensors. We considered a typical case of an impedance spectrum in the range 0.1 Hz–10 kHz, modeled by using the simplified Randles equivalent circuit. Our analyses have shown that simple ANNs can be a low power alternative to perform EIS data fitting on low-cost microcontrollers with a memory occupation in the order of kilo bytes and a measurement accuracy between 1% and 3%. Full article

Illegal broadcasting is one of the primary challenges for Over the Top (OTT) service providers. Watermarking is a method used to trace illegal redistribution of video content. However, watermarking introduces processing overhead due to the embedding of unique patterns into the video content, which results in additional latency. End-to-end network latency, caused by network congestion or heavy load on the origin server, can slow data transmission, impacting the time it takes for the segment to reach the client. This paper addresses 5xx errors (e.g., 503, 504) at the Content Delivery Network (CDN) in real-world video streaming platforms, which can negatively impact Quality of Experience (QoE), particularly when watermarking techniques are employed. To address the performance issues caused by the integration of watermarking technology, we enhanced the system architecture by introducing and optimizing a shield cache in front of the packager at the origin server and fine-tuning the CDN configuration. These optimizations significantly reduced the processing load on the packager, minimized latency, and improved overall content delivery. As a result, we achieved a 6% improvement in the Key Performance Indicator (KPI), reflecting enhanced system stability and video quality. Full article

Covert channels enable hidden communication that poses significant security risks, particularly when smartphones are used as transmitters. This paper presents the first end-to-end implementation and evaluation of an electromagnetic (EM) covert channel on modern Samsung Galaxy S21, S22, and S23 smartphones (Samsung Electronics Co., Ltd., Suwon, Republic of Korea). We first demonstrate that a previously proposed method relying on zero-volume playback is no longer effective on these devices. Through a detailed analysis of EM emissions in the 0.1–2.5 MHz range, we discovered that consistent, volume-independent signals can be generated by exploiting the hardware’s recovery delay after silent audio playback. Based on these findings, we developed a complete system comprising a stealthy Android application for transmission, a time-based modulation scheme, and a demodulation technique designed around the characteristics of the generated signals to ensure reliable reception. The channel’s reliability and robustness were validated through evaluations of modulation time, probe distance, and message length. Experimental results show that the maximum error-free bit rate (bits per second, bps) reached 0.558 bps on Galaxy S21 and 0.772 bps on Galaxy S22 and Galaxy S23. Reliable communication was feasible up to 0.5 cm with a near-field probe, and a low alignment-aware bit error rate (BER) was maintained even for 100-byte messages. This work establishes a practical threat, and we conclude by proposing countermeasures to mitigate this vulnerability. Full article

Digital transformation has re-engineered tourism marketing and how destination branding competes for tourist attention, yet scholarship offers little systematic quantification of these changes. Drawing on 160 peer-reviewed studies published between 1990 and 2025, we combine grounded-theory thematic synthesis with a random-effect meta-analysis of 60 datasets to trace branding performance across five technological eras (pre-Internet and brochure era: to mid-1990s; Web 1.0: 1995–2004; Web 2.0: 2004–2013; mobile first: 2013–2020; AI-XR: 2020–2025). Results reveal three structural shifts: (i) dialogic engagement replaces one-way promotion, (ii) credibility migrates to user-generated content, and (iii) artificial intelligence–driven personalisation reconfigures relevance, while mobile and virtual reality marketing extend immersion. Meta-analytic estimates show the strongest gains for engagement intentions (g = 0.57), followed by brand awareness (g = 0.46) and image (g = 0.41). Other equity dimensions (attitudes, loyalty, perceived quality) also improved on average, but to a lesser degree. Visual, UGC-rich, and influencer posts on highly interactive platforms consistently outperform brochure-style content, while robustness checks (fail-safe N, funnel symmetry, leave-one-out) confirm stability. We conclude that digital tools amplify, rather than replace, co-creation, credibility, and context. By fusing historical narrative with statistical certainty, the study delivers a data-anchored roadmap for destination marketers, researchers, and policymakers preparing for the AI-mediated decade ahead. Full article

Modeling mobile robots is crucial to odometry estimation, control design, and navigation. Classical state-space models (SSMs) have traditionally been used for system identification, while recent advances in deep learning, such as Long Short-Term Memory (LSTM) networks, capture complex nonlinear dependencies. However, few direct comparisons exist between these paradigms. This paper compares two multivariate modeling approaches for a differential drive robot: a classical SSM and an LSTM-based recurrent neural network. Both models predict the robot’s linear (v) and angular ($\omega$) velocities using experimental data from a five-minute navigation sequence. Performance is evaluated in terms of prediction accuracy, odometry estimation, and computational efficiency, with ground-truth odometry obtained via a SLAM-based method in ROS2. Each model was tuned for fair comparison: order selection for the SSM and hyperparameter search for the LSTM. Results show that the best SSM is a second-order model, while the LSTM used seven layers, 30 neurons, and 20-sample sliding windows. The LSTM achieved a FIT of 93.10% for v and 90.95% for $\omega$, with an odometry RMSE of 1.09 m and 0.23 rad, whereas the SSM outperformed it with FIT values of 94.70% and 91.71% and lower RMSE (0.85 m, 0.17 rad). The SSM was also more resource-efficient (0.00257 ms and 1.03 bytes per step) compared to the LSTM (0.0342 ms and 20.49 bytes). The results suggest that SSMs remain a strong option for accurate odometry with low computational demand while encouraging the exploration of hybrid models to improve robustness in complex environments. At the same time, LSTM models demonstrated flexibility through hyperparameter tuning, highlighting their potential for further accuracy improvements with refined configurations. Full article

Vehicular Ad Hoc Networks (VANETs) enable critical communication for Intelligent Transportation Systems (ITS) but are vulnerable to cybersecurity threats, such as Gray Hole attacks, where malicious nodes selectively drop packets, compromising network integrity. Traditional detection methods struggle with the intermittent nature of these attacks, necessitating advanced solutions. This study proposes a machine learning-based Intrusion Detection System (IDS) to detect Gray Hole attacks in VANETs. Methods: This study proposes a machine learning-based Intrusion Detection System (IDS) to detect Gray Hole attacks in VANETs. Features were extracted from network traffic simulations on NS-3 and categorized into time-, packet-, and protocol-based attributes, where NS-3 is defined as a discrete event network simulator widely used in communication protocol research. Multiple classifiers, including Random Forest, Support Vector Machine (SVM), Logistic Regression, and Naive Bayes, were evaluated using precision, recall, and F1-score metrics. The Random Forest classifier outperformed others, achieving an F1-score of 0.9927 with 15 estimators and a depth of 15. In contrast, SVM variants exhibited limitations due to overfitting, with precision and recall below 0.76. Feature analysis highlighted transmission rate and packet/byte counts as the most influential for detection. The Random Forest-based IDS effectively identifies Gray Hole attacks, offering high accuracy and robustness. This approach addresses a critical gap in VANET security, enhancing resilience against sophisticated threats. Future work could explore hybrid models or real-world deployment to further validate the system’s efficacy. Full article

Pedestrian safety at signalized intersections remains a pressing concern in rapidly urbanizing cities. This study introduces a trajectory–signal behavior spectrum, grounded in Behavior Spectrum Theory (BST), to quantify crossing risk using readily observable data. Unmanned aerial vehicle (UAV) video is employed to record pedestrian movements, which are then detected with YOLOv8 and tracked with ByteTrack, producing frame-level trajectories without dependence on line-of-sight instrumentation. Five spatiotemporal features—speed, acceleration, crossing time, remaining pedestrian-signal green time, and red-phase duration—are compiled into the spectrum. Features are normalized using the interquartile range (IQR) method, and objective weights are determined with an improved CRITIC (Criteria Importance Through Intercriteria Correlation) scheme that incorporates a median-based coefficient of variation and absolute correlation for conflict measurement. The resulting risk eigenvalues are clustered with K-means into four levels: no risk, low, medium, and high. A case study of 1210 crossings at a two-way eight-lane intersection in Harbin, China (576 compliant, 634 non-compliant) demonstrates the approach. Results show greater variability among non-compliant speeds (mean 1.29 m/s) compared with compliant crossings (mean 1.40 m/s), with more extreme deviations. Clustering achieved silhouette coefficients of 0.60 for compliant and 0.69 for non-compliant groups, while expert validation on 20 samples yielded substantial agreement (Fleiss’ Kappa = 0.87). This study provides a systematic and interpretable method for risk classification, which supports both theoretical understanding and applied traffic safety management. Full article

Homomorphic encryption solutions tend to be costly in terms of memory and computational resources, making them difficult to implement. In this paper, we present Kyber AHE, a lightweight additive homomorphic encryption scheme for computing the addition modulo 2 of two binary strings in the encrypted domain. It is based on the CRYSTALS-Kyber public key encryption (PKE) scheme, which is the basis of the NIST module-lattice-based key-encapsulation mechanism standard. Apart from being quantum-safe, Kyber PKE has other interesting features such as the use of compressed ciphertexts, reduced sizes of keys, low execution times, and the ability to easily increase the security level. The operations performed in the encrypted domain by Kyber AHE are the decompression of ciphertexts, the component-wise modulo q addition of polynomials, and the compression of the results. A great advantage of Kyber AHE is that it can be easily implemented along with CRYSTALS-Kyber without the need for additional libraries. Among the applications of homomorphic encryption, biometric template protection schemes are a promising solution to provide data privacy by comparing biometric features in the encrypted domain. Therefore, we present the application of Kyber AHE for the protection of biometric templates. Experimental results have been obtained using Kyber AHE in an iris biometric template protection scheme with 256-byte features using Kyber512, Kyber768, and Kyber1024 instances. The sizes of the encrypted iris features are 6.0, 8.5, and 12.5 kB for NIST security levels I, III, and V, respectively. Using a commercial laptop, the encryption ranges from 0.755 to 1.73 ms, the evaluation from 0.096 to 0.161 ms, and the decryption from 0.259 to 0.415 ms, depending on the security level. Full article

Accurate fruit counting is crucial for data-driven decision-making in modern precision agriculture. In strawberry cultivation, a labor-intensive sector, automated, scalable yield estimation is especially critical. However, dense foliage, variable lighting, visual ambiguity of ripeness stages, and fruit clustering pose significant challenges. To overcome these, we developed a real-time multi-stage framework for strawberry detection and counting by optimizing a YOLOv8s detector and integrating a class-aware tracking system. The detector was enhanced with a lightweight C3x module, an additional detection head for small objects, and the Wise-IOU (WIoU) loss function, thereby improving performance against occlusion. Our final model achieved a 92.5% mAP@0.5, outperforming the baseline while reducing the number of parameters by 27.9%. This detector was integrated with the ByteTrack multiple object tracking (MOT) algorithm. Our system enabled accurate, automated fruit counting in complex greenhouse environments. When validated on video data, results showed a strong correlation with ground-truth counts (R² = 0.914) and a low mean absolute percentage error (MAPE) of 9.52%. Counting accuracy was highest for ripe strawberries (R² = 0.950), confirming the value for harvest-ready estimation. This work delivers an efficient, accurate, and resource-conscious solution for automated yield monitoring in commercial strawberry production. Full article

Side-channel analysis (SCA) poses a persistent threat to cryptographic hardware by exploiting unintended physical leakages. To address the limitations of traditional single-modality SCA methods, we propose a novel multi-modal side-channel analysis framework that targets the recovery of encryption keys by leveraging the imperfections inherent in hardware implementations. The core objective is to extract and classify information-rich segments from power and electromagnetic (EM) signals in order to recover secret keys without profiling or labeling. Our approach introduces a unified pipeline combining joint peak-based segmentation, isometric compression of variable-length trace segments, and multi-modal feature fusion. A key component of the framework is unsupervised clustering, which serves to automatically classify trace segments corresponding to different cryptographic operations (e.g., different key-dependent leakage classes), thereby enabling key byte hypothesis testing and full key reconstruction. Experimental results on an FPGA-based AES-128 implementation demonstrate that our method achieves up to 99.2% clustering accuracy and successfully recovers the entire encryption key using as few as 1–3 traces. Moreover, the proposed approach significantly reduces sample complexity and maintains resilience in low signal-to-noise conditions. These results highlight the practicality of our technique for side-channel vulnerability assessment and its potential to inform the design of more robust cryptographic hardware. Full article

In recent years, the application of deep learning technology in the field of food engineering has developed rapidly. As an essential food raw material and processing target, the number of kernels per maize plant is a critical indicator for assessing crop growth and predicting yield. To address the challenges of frequent target ID switching, high falling speed, and the limited accuracy of traditional methods in practical production scenarios for maize kernel falling count, this study designs and implements a real-time kernel falling counting system based on a Convolutional Neural Network (CNN). The system captures dynamic video streams of kernel falling using a high-speed camera and innovatively integrates the YOLOv8 object detection framework with the ByteTrack multi-object tracking algorithm to establish an efficient and accurate kernel trajectory tracking and counting model. Experimental results demonstrate that the system achieves a tracking and counting accuracy of up to 99% under complex falling conditions, effectively overcoming counting errors caused by high-speed motion and object occlusion, and significantly enhancing robustness. This system combines high intelligence with precision, providing reliable technical support for automated quality monitoring and yield estimation in food processing production lines, and holds substantial application value and prospects for widespread adoption. Full article

With the development of precision livestock farming, in order to achieve the goal of fine management and improve the health and welfare of dairy cows, research on dairy cow motion monitoring has become particularly important. In this study, considering the problems surrounding a large amount of model parameters, the poor accuracy of multi-target tracking, and the nonlinear motion of dairy cows in dairy farming scenes, a lightweight detection model based on improved YOLO v11n was proposed and four tracking algorithms were compared. Firstly, the Ghost module was used to replace the standard convolutions in the YOLO v11n network and a more lightweight attention mechanism called ELA was replaced, which reduced the number of model parameters by 18.59%. Then, a loss function called SDIoU was used to solve the influence of different cow target sizes. With the above improvements, the improved model achieved an increase of 2.0 percentage points and 2.3 percentage points in mAP@75 and mAP@50-95, respectively. Secondly, the performance of four tracking algorithms, including ByteTrack, BoT-SORT, OC-SORT, and BoostTrack, was systematically compared. The results show that 97.02% MOTA and 89.81% HOTA could be achieved when combined with the OC-SORT tracking algorithm. Considering the demand of equipment in lightweight models, the improved object detection model in this paper reduces the number of model parameters while offering better performance. The OC-SORT tracking algorithm enables the tracking and localization of cows through video surveillance alone, creating the necessary conditions for the continuous monitoring of cows. Full article

In some cases, computer systems need to handle both little-endian and big-endian data, even if it differs from their native endianness. This paper proposes an RISC-V extension that makes it possible to remove the overhead introduced when dealing with foreign-endian data. It can be implemented with little engineering effort and a negligible impact on performance and hardware resources. Our results demonstrate that the extension can reduce the overhead of foreign-endian data processing by 62% or 37% compared to software-based solutions that use the base Instruction Set Architecture (ISA) or current bit manipulation extensions, respectively. This performance boost has the potential to benefit both new and legacy software once compiler and library support have been put in place. Full article