DSiam-CnK: A CBAM- and KCF-Enabled Deep Siamese Region Proposal Network for Human Tracking in Dynamic and Occluded Scenes.

Despite the accuracy and robustness attained in the field of object tracking, algorithms based on Siamese neural networks often over-rely on information from the initial frame, neglecting necessary updates to the template; furthermore, in prolonged tracking situations, such methodologies encounter challenges in efficiently addressing issues such as complete occlusion or instances where the target exits the frame. To tackle these issues, this study enhances the SiamRPN algorithm by integrating the convolutional block attention module (CBAM), which enhances spatial channel attention. Additionally, it integrates the kernelized correlation filters (KCFs) for enhanced feature template representation.

Free-Space to SMF Integration and Green to C-Band Conversion Based on PPLN.

In this study, we experimentally demonstrate a PPLN-based free-space to SMF (single-mode fiber) conversion system capable of efficient long-wavelength down-conversion from 518 nm, optimized for minimal loss in highly turbid water, to 1540 nm, which is ideal for low-loss transmission in standard SMF. Leveraging the nonlinear optical properties of periodically poled lithium niobate (PPLN), we achieve a wavelength conversion efficiency of 1.6% through difference frequency generation while maintaining a received optical signal-to-noise ratio of 10.

Calibration and Performance Evaluation of Cost-Effective Capacitive Moisture Sensor in Slope Model Experiments.

Understanding the factors that contribute to slope failures, such as soil saturation, is essential for mitigating rainfall-induced landslides. Cost-effective capacitive soil moisture sensors have the potential to be widely implemented across multiple sites for landslide early warning systems. However, these sensors need to be calibrated for specific applications to ensure high accuracy in readings.

Point Cloud Wall Projection for Realistic Road Data Augmentation.

Several approaches have been developed to generate synthetic object points using real LiDAR point cloud data for advanced driver-assistance system (ADAS) applications. The synthetic object points generated from a scene (both the near and distant objects) are essential for several ADAS tasks. However, generating points from distant objects using sparse LiDAR data with precision is still a challenging task.

The Design of a Low-Noise CMOS Image Sensor Using a Hybrid Single-Slope Analog-to-Digital Converter.

In this study, we describe a low-noise complementary metal-oxide semiconductor (CMOS) image sensor (CIS) with a 10/11-bit hybrid single-slope analog-to-digital converter (SS-ADC). The proposed hybrid SS-ADC provides a resolution of 11 bits in low-light and 10 bits in high-light. To this end, in the low-light section, the digital-correlated double sampling method using a double data rate structure was used to obtain a noise performance similar to that of the 11-bit SS-ADC under low-light conditions, while maintaining linear in-out characteristics.

Enhancing Biophysical Muscle Fatigue Model in the Dynamic Context of Soccer.

In the field of muscle fatigue models (MFMs), the prior research has demonstrated success in fitting data in specific contexts, but it falls short in addressing the diverse efforts and rapid changes in exertion typical of soccer matches. This study builds upon the existing model, aiming to enhance its applicability and robustness to dynamic demand shifts. The objective is to encapsulate the complexities of soccer dynamics with a streamlined set of parameters.

Determination of the Bentonite Content in Molding Sands Using AI-Enhanced Electrical Impedance Spectroscopy.

Molding sand mixtures in the foundry industry are typically composed of fresh and reclaimed sands, water, and additives such as bentonite. Optimizing the control of these mixtures and the recycling of used sand after casting requires an efficient in-line monitoring method, which is currently unavailable. This study explores the potential of an AI-enhanced electrical impedance spectroscopy (EIS) system as a solution.

CabbageNet: Deep Learning for High-Precision Cabbage Segmentation in Complex Settings for Autonomous Harvesting Robotics.

Reducing damage and missed harvest rates is essential for improving efficiency in unmanned cabbage harvesting. Accurate real-time segmentation of cabbage heads can significantly alleviate these issues and enhance overall harvesting performance. However, the complexity of the growing environment and the morphological variability of field-grown cabbage present major challenges to achieving precise segmentation.

Machine Learning-Based Modeling of pH-Sensitive Silicon Nanowire (SiNW) for Ion Sensitive Field Effect Transistor (ISFET).

The development of ion-sensitive field-effect transistor (ISFET) sensors based on silicon nanowires (SiNW) has recently seen significant progress, due to their many advantages such as compact size, low cost, robustness and real-time portability. However, little work has been done to predict the performance of SiNW-ISFET sensors. The present study focuses on predicting the performance of the silicon nanowire (SiNW)-based ISFET sensor using four machine learning techniques, namely multilayer perceptron (MLP), nonlinear regression (NLR), support vector regression (SVR) and extra tree regression (ETR).

Identification Method for Railway Rail Corrugation Utilizing CEEMDAN-PE-SPWVD.

Rail corrugation intensifies wheel-rail vibrations, often leading to damage in vehicle-track system components within affected sections. This paper proposes a novel method for identifying rail corrugation, which combines Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), permutation entropy (PE), and Smoothed Pseudo Wigner-Ville Distribution (SPWVD). Initially, vertical acceleration data from the axle box are decomposed using CEEMDAN to extract intrinsic mode functions (IMFs) with distinct frequencies.

Design and Test of a Calibration System for Avalanche Photodiodes Used in X-Ray Compton Polarimeters for Space.

The development and calibration of a measurement system designed for assessing the performance of the avalanche photodiodes (APDs) used in the Compton scattering polarimeter of the CUSP project is discussed in this work. The designed system is able to characterize the APD gain GAPD and energy resolution across a wide range of temperatures (from -20 °C to +60 °C) and bias voltages Vbias (from 260 V to 410 V). The primary goal was to experimentally determine the GAPD dependence on the and Vbias in order to establish a strategy for stabilizing GAPD by compensating for fluctuations, acting on Vbias.

Use of Laccase Enzymes as Bio-Receptors for the Organic Dye Methylene Blue in a Surface Plasmon Resonance Biosensor.

Methylene blue is a cationic organic dye commonly found in wastewater, groundwater, and surface water due to industrial discharge into the environment. This emerging pollutant is notably persistent and can pose risks to both human health and the environment. In this study, we developed a Surface Plasmon Resonance Biosensor employing a BK7 prism coated with 3 nm chromium and 50 nm of gold in the Kretschmann configuration, specifically for the detection of methylene blue.

Research on the Stress Characteristics of Reuse of Semi-Rigid Base.

Semi-rigid bases are widely used in road construction due to their excellent properties, high rigidity, and frost resistance, and they have been in service for many years. However, as the service life increases, the maintenance demands also grow, with traditional maintenance methods still being the primary approach. Based on a typical case using ground-penetrating radar (GPR) technology, this study explores the issue of cracks in semi-rigid bases and their impact on overlay layers.

An Accurate Book Spine Detection Network Based on Improved Oriented R-CNN.

Book localization is crucial for the development of intelligent book inventory systems, where the high-precision detection of book spines is a critical requirement. However, the varying tilt angles and diverse aspect ratios of books on library shelves often reduce the effectiveness of conventional object detection algorithms. To address these challenges, this study proposes an enhanced oriented R-CNN algorithm for book spine detection.

Enhanced FFT-Root-MUSIC Algorithm Based on Signal Reconstruction via CEEMD-SVD for Joint Range and Velocity Estimation for FMCW Radar.

Frequency-modulated continuous-wave (FMCW) radar is used to extract range and velocity information from the beat signal. However, the traditional joint range-velocity estimation algorithms often experience significant performances degradation under low signal-to-noise ratio (SNR) conditions. To address this issue, this paper proposes a novel approach utilizing the complementary ensemble empirical mode decomposition (CEEMD) combined with singular value decomposition (SVD) to reconstruct the beat signal prior to applying the FFT-Root-MUSIC algorithm for joint range and velocity estimation.

Optimization of Imaging Reconnaissance Systems Using Super-Resolution: Efficiency Analysis in Interference Conditions.

Image reconnaissance systems are critical in modern applications, where the ability to accurately detect and identify objects is crucial. However, distortions in real-world operational conditions, such as motion blur, noise, and compression artifacts, often degrade image quality, affecting the performance of detection systems. This study analyzed the impact of super-resolution (SR) technology, in particular, the Real-ESRGAN model, on the performance of a detection model under disturbed conditions.

Improvement of an Edge-IoT Architecture Driven by Artificial Intelligence for Smart-Health Chronic Disease Management.

One of the health challenges in the 21st century is to rethink approaches to non-communicable disease prevention. A solution is a smart city that implements technology to make health smarter, enables healthcare access, and contributes to all residents' overall well-being. Thus, this paper proposes an architecture to deliver smart health.

Towards Accurate Photogrammetry Using Molded Markers.

Traditional marker-based photogrammetry systems often require the attachment and removal of a sticker for each measured point, involving labor-intensive manual steps. This paper presents an innovative approach that utilizes raised, cross-shaped markers, referred to as 'molded markers', directly embedded into composite pieces. In this study, these markers, commonly employed in other industrial processes, serve as fiducial markers for accurate photogrammetry.

Semantically-Enhanced Feature Extraction with CLIP and Transformer Networks for Driver Fatigue Detection.

Drowsy driving is a leading cause of commercial vehicle traffic crashes. The trend is to train fatigue detection models using deep neural networks on driver video data, but challenges remain in coarse and incomplete high-level feature extraction and network architecture optimization. This paper pioneers the use of the CLIP (Contrastive Language-Image Pre-training) model for fatigue detection.

An Experimental Study of the Flexural Bearing Capacity of Reinforced Concrete Beams Damaged by Explosions Using Piezoelectric Smart Aggregates.

Two identically sized RC beams were fabricated to investigate the effects of explosive loads on the flexural behaviour of Reinforced Concrete (RC) beams. One of the beams was subjected to an explosive load to induce post-explosion damage, and subsequently, both beams underwent flexural capacity testing. Integrating piezoelectric smart aggregates (SAas) within the beams facilitated continuous observation of the damage conditions, allowing for the assessment of internal concrete deterioration from explosive impacts to bending failures.

Extended Reality to Assess Short-Term Spatial Memory-A Comparative Study of Mixed Reality, Augmented Reality, and Virtual Reality.

A Mixed Reality (MR) application using an optical see-through headset was developed to assess short-term spatial memory. A study with 29 participants was conducted. Data from this study were compared to two previous studies using mobile Augmented Reality (AR) and Virtual Reality (VR) with headsets.

LiDAR-Based Negative Obstacle Detection for Unmanned Ground Vehicles in Orchards.

In orchard environments, negative obstacles such as ditches and potholes pose significant safety risks to robots working within them. This paper proposes a negative obstacle detection method based on LiDAR tilt mounting. With the LiDAR tilted at 40°, the blind spot is reduced from 3 m to 0.

Fused Multi-Domains and Adaptive Variational Mode Decomposition ECG Feature Extraction for Lightweight Bio-Inspired Key Generation and Encryption.

Security is one of the increasingly significant issues given advancements in technology that harness data from multiple devices such as the internet of medical devices. While protecting data from unauthorized user access, several techniques are used including fingerprints, passwords, and others. One of the techniques that has attracted much attention is the use of human features, which has proven to be most effective because of the difficulties in impersonating human-related features.

Exploring Technology Acceptance of Healthcare Devices: The Moderating Role of Device Type and Generation.

The increasing adoption of healthcare devices necessitates a deeper understanding of the factors that influence user acceptance in this rapidly evolving area. Therefore, this study examined the factors influencing the technology acceptance of healthcare devices, focusing on radar sensors and wearable devices. A total of 1158 valid responses were used to test hypotheses, mediation, and moderation effects using SmartPLS 4.

Comparison of Mean Values and Entropy in Accelerometry Time Series from Two Microtechnology Sensors Recorded at 100 vs. 1000 Hz During Cumulative Tackles in Young Elite Rugby League Players.

Several microtechnology devices quantify the external load of team sports using Global Positioning Systems sampling at 5, 10, or 15 Hz. However, for short, explosive actions, such as collisions, these sample rates may be limiting. It is known that very high-frequency sampling is capable of capturing changes in actions over a short period of time.