搜索结果：Intel

Precision agriculture leverages advanced technologies to optimize crop management, increase yield and promote sustainable farming practices. Despite significant progress in agricultural automation, continuous field monitoring remains a challenge for farmers due to labor demands and variable environmental conditions. To address this, the use of mobile robots equipped with intelligent perception systems enables autonomous data collection and analysis in real agricultural environments. This work presents a dataset focused on crop monitoring, containing images of corn and beet fields captured by a ground mobile robot. The images were acquired using the Summit XL platform from Robotnik, equipped with an Intel RealSense D455 camera and collected under natural daylight conditions. The robot was teleoperated across the crop fields while recording rosbags that include RGB images, suitable for tasks such as plant detection. The dataset comprises 10,080 images organized following the YOLO object detection format, with 9104 training images, 493 validation images, and 483 test images. All images are annotated with bounding boxes in normalized YOLO format, distinguishing between two crop classes: beet and corn. To enhance model robustness, the dataset includes augmented versions created through geometric transformations and photometric variations. Privacy protection measures were implemented using automated person detection and anonymization. This dataset aims to support research in precision agriculture, particularly in developing intelligent systems for crop monitoring, plant health assessment, and autonomous agricultural inspection. All data are publicly available through a single Hugging Face repository.

This article provides a salmon fillet dataset to investigate the detection of distinct regions, undesirable spots, and possibly the higher nutrient content measurements. Since we know that the belly of salmon is high in omega-3 fatty acids, we can use computer vision and image processing to identify the belly areas of salmon fillets (for trim A, B, and C cuts, trim A cut has the largest belly area) and determine the percentage of these fatty acids. As a result, this dataset becomes essential for training models that identify and examine the belly regions. Datasets were acquired from Lerøy Aurora, a salmon processing plant in Skjervøy, Norway, as well as images taken in our lab during experiments. To acquire the images at the Lerøy plant, two settings were used: (i) using a stand with 3 Intel RealSense RGB-D cameras and (ii) using a stand with 1 Intel RealSense RGB-D camera, depending on the amount of space available to put our setup near the production line. The camera equipment was positioned close to the production line. In total, 712 RGB images, 10 ROS (Robot Operating System) bags with 3 camera settings, and 5 ROS bags with 1 camera setting were taken in the Lerøy plant, while 60 RGB images were captured at the NMBU lab. ROS nodes were utilized to capture both the ROS bags (which carried RGB-D information) and the RGB images. To facilitate further research on salmon fillets, this collection also contains 509 multispectral images of fish fillets. The dataset is intended primarily as a benchmarking and pre-training resource, demonstrating the potential of computer vision for salmon fillet analysis. In conclusion, this comprehensive dataset provides a solid base for potential research on automated salmon fillet analysis. This will enable computer vision and image processing to enhance quality control and nutritional evaluation of salmon fillets.

The integration and miniaturization of chips lead to significant power consumption and heat accumulation. Typically, the energy consumption of cooling systems accounts for morn than 50% of the input energy. Current thermal management technologies do not offer solutions for on-chip thermal energy loss. Herein, we propose an on-chip integrated thermal recovery system, which can simultaneously achieve efficient heat dissipation. Present system on chips is based on hydrovoltaic generator technology, consisting of electrodes and gel. With the deep ultraviolet LED (236 nm) chip suffering from severe heat accumulation as a prototype, upon integration with the thermal recovery system, not only maintain the chip temperature below 40 °C, but also converts waste heat into stored electrical energy, resulting in a 610.70% improvement in overall energy utilization efficiency. To demonstrate its general applicability in commercial CPU systems, we used the commercial Intel G3220 chip and as an example, by incorporating four HEG units, the temperature was reduced from 93 °C to below 60 °C, effectively enhancing computational performance and extending the chip's lifespan.

This work describes the development and validation of an algorithm to improve ultrasound volume reconstruction from noisy initial scans taken using a tracked freehand ultrasound device. The algorithm was first tested and refined in simulation using an approximate kidney shape model re-sliced to represent various real life scan conditions. Next, an Intel RealSense D435i camera was used to track the pose of a commercial ultrasound probe. This device was used to scan a phantom with a known volume and shape. Finally, repeated scans were taken in vivo to test the repeatability of volume measurements. The simulation experiments were used to refine algorithm hyperparameters. The volume of the phantom was measured to within 2.5-17% (1-11.5% with automatic pass finding) of ground truth for four different scan styles, compared to traditional methods that underestimate the volume by 17.5%. In 11 human subjects, right kidney volume was measured within between 3.6-14.6% (7.7-23.3% with automatic pass finding) variation between scans. The proposed algorithm was demonstrated to produce repeatable volume measurement results in both phantom and in vivo scans. The proposed algorithm improves the clinical translatability and repeatability of freehand volume ultrasound systems.

Ultrasonic vocalizations (USVs) in rodents are a key tool in neuroscience for investigating emotion, social behavior, and disease models. However, commercial recording systems remain expensive and generate massive datasets that require heavy post-processing. We present an open-hardware acquisition chain-from microphone to computer-designed to compute and display sonograms in near real time, thus reducing both storage needs and analysis workload. The system integrates (i) a custom ultrasonic microphone capable of detecting signals up to 100 kHz, (ii) a dedicated analog front-end with band-pass and anti-aliasing filtering, (iii) an Intel® Cyclone V GX FPGA implementing on-board Fast Fourier Transform processing and power calculation, and (iv) a lightweight software interface for data transfer and visualization. All design files, including Printed Circuit Board (PCB) layouts, VHDL codes, and C software, are openly released to ensure reproducibility. Compared to traditional microcontroller-based acquisitions, this architecture reduces raw data storage by more than 50% while maintaining a frequency resolution of ∼0.39 kHz and a temporal resolution of ∼2.5 ms - sufficient to resolve both 22 kHz and 50 kHz USVs. Validated with synthetic signals and experimental recordings, the platform provides neuroscientists with a low-cost, modular, and fully transparent tool for studying ultrasonic communication.

Improving the speed and efficiency of database search algorithms that deduce peptides from mass spectrometry (MS) data has been an active area of research for more than three decades. The significance of the need for faster database search methods has rapidly increased due to the growing interest in studying non-model organisms, meta-proteomics, and proteogenomic data, which are notorious for their enormous search space. Poor scalability of serial algorithms with the growing size of the database and increasing parameters of post-translational modifications is a widely recognized problem. While high-performance computing techniques can be used on supercomputing machines, the need for real-time, on-the-instrument solutions necessitates the development of an efficient system-on-chip that optimizes design constraints such as cost, performance, and power of the system. To show case that such a system can work, we present an FPGA-based computational framework called FiCOPS to accelerate database search using a hardware/software co-design methodology. First, we theoretically analyze the database-search algorithm (closed-search) to reveal opportunities for parallelism and uncover computational bottlenecks. We then design an FPGA-based architectural template to exploit parallelism inherent in the search workload. We also formulate an analytical performance model for the architecture template to perform rapid design space exploration and find a near-optimal accelerator configuration. Finally, we implement our design on the Intel Stratix 10 FPGA platform and evaluate it using real-world datasets. Our experiments demonstrate that FiCOPS achieves 3.5 times speed-up over existing CPU solutions and 3 times and 5 times reduction in power consumption compared to existing CPU and GPU solutions.

BackgroundPrecise anthropometric data are vital for ergonomic assessment and farm machinery design. Manual methods, although dependable, are labor-intensive and susceptible to error.ObjectiveThis study aimed to develop and validate a computer vision (CV) based non-contact system for anthropometric measurements, focusing on stature, vertical reach, trochanteric height, and chest circumference.MethodsAn Intel RealSense D435i stereo camera with OpenCV, mediapipe captured images from three angles (front, diagonal, side) at 2.5-3.5&#x2005;m. Thirty-two participants (16 male, 16 female) were measured, with manual anthropometry as reference. Accuracy was assessed using mean absolute difference (MAD) and mean absolute percentage error (MAPE), while reliability was examined via intraclass correlation coefficient (ICC, p&#x2009;<&#x2009;0.05).ResultsThe 3.0&#x2005;m front-facing view yielded the most accurate measurements. CV-based anthropometry slightly underestimated stature for males (1596 vs. 1646&#x2005;mm) and females (1456 vs. 1521&#x2005;mm; MAD 53-65&#x2005;mm; MAPE 3-4%), with excellent reliability (ICC&#x2009;>&#x2009;0.90, &#x3b1;&#x2009;>&#x2009;0.85). Vertical reach showed the largest bias (83-90&#x2005;mm; MAPE 4-5%), yet reliability remained high (ICC 0.88-0.91). Trochanteric height had minimal discrepancies (29-36&#x2005;mm; MAPE&#x2009;&#x2264;&#x2009;4%) with good consistency (ICC 0.85-0.90). Chest circumference showed small bias (&#xb1;10&#x2005;mm; MAPE 3-4%) but lower reliability (ICC 0.75-0.80), likely due to respiration. Overall, CV measurements were reliable, non-invasive, and scalable.ConclusionsThe CV-based system offers a precise, scalable, and non-contact alternative to manual anthropometry, enabling reliable data collection for ergonomic evaluation and improved man-machine compatibility in agriculture.

The ERBB4 gene encodes a tyrosine kinase receptor for neuregulins and EGF family members, and plays a crucial role in various neurobiological processes. At present, the phenotypic manifestations of genetic variants that disrupt ERBB4 gene function (null variants) are not well established. A search for new patients with null variants in ERBB4 was initiated through an international data-sharing collaboration via GeneMatcher, and by searching the databases Decipher and ClinVar. Diagnosis had been performed using chromosomal microarray analysis, whole-exome sequencing, or whole-genome sequencing. Twenty-four new patients from 13 unrelated families with null variants in ERBB4 were identified. Genetic findings included single- or multiple-exon deletions in eight families, a reciprocal translocation disrupting ERBB4 in one family, and sequence variants in four. Variants arose de novo in four probands, were inherited in eight, and had an unknown inheritance pattern in one. Co-segregation of variants with clinical manifestations was observed within families. The predominant clinical features included neurodevelopmental disorders (intellectual disability, neurodevelopmental delay, autism spectrum disorder, and attention deficit hyperactivity disorder), speech delay, challenging behaviors, hypotonia, psychiatric conditions and seizures. This study represents the largest case series of patients with neurological disorders and null variants in the ERBB4 gene. Our findings support haploinsufficiency as the most plausible pathophysiological mechanism underlying ERBB4-related disorders and broaden the spectrum of associated phenotypes. Autism spectrum disorders and psychiatric manifestations have emerged as frequent, previously underrecognized features. Penetrance appears to be high but incomplete, and expressivity is highly variable, with a tendency toward intrafamilial phenotypic conservation.

Coronary slow flow (CSF), present in 1-7% of coronary angiograms, occurs in patients with angiographically normal epicardial arteries and is associated with acute coronary syndrome, representing an unmet need in coronary microvascular dysfunction (CMD) management. This study proposes an anatomy-guided spatiotemporal dynamical fusion (AG-STDF) framework for CSF screening. AG-STDF integrates anatomical electrophysiological territory mapping with 12-lead electrocardiogram (ECG) dynamics. ECG signals are decomposed into coronary territories-left anterior descending (LAD), left circumflex (LCX), and right coronary artery (RCA)-and static morphology is fused with intrinsic dynamics (derived from dynamic modeling) using joint recurrence quantification and multi-scale decomposition. AG-STDF achieves an AUROC of 0.9467 $\pm$ 0.0272 for CSF detection. At the vessel level, where therapeutic decisions are made per 2024 European Society of Cardiology guidelines, AG-STDF predicts corrected thrombolysis in myocardial infarction frame counts (CTFC) with an $\text{R}^{\text{2}}$ = 0.5951 $\pm$ 0.0666 (AUROC: 0.8428). Notably, AG-STDF performs steadily in right-dominant coronary patients, with favorable results in LAD ($\text{R}^{\text{2}}$ = 0.6753) and mild fluctuations in LCX ($\text{R}^{\text{2}}$ = 0.5673) and RCA ($\text{R}^{\text{2}}$ = 0.5296) due to anatomical variations and competitive perfusion. Anatomical constraints and spatiotemporal fusion improve AUROC by 3.5% (p $< $ 0.01) and 9.47% (p $< $ 0.05). When equipped with an Intel Core i5-10500 and NVIDIA GTX 1660S, AG-STDF processes a 10-second ECG segment in 19.37 s. AG-STDF allows accurate, non-invasive CSF detection and vessel-level assessment in right-dominant populations. It serves as a cost-effective CMD screening tool that may reduce invasive testing and support early diagnosis.

This study was prompted by the rapid acceleration of AI capabilities in the trans former era since 2018 and the concurrent regulatory shift that elevated legal accountability and public governance to central policy and research priorities. It contributes by treating 2018-2025 as a distinct governance regime in which transformer-enabled capability scaling and foundation models shifted AI gov ernance debates toward enforceable accountability architectures. The study maps the regulation-accountability-public governance nexus as an operational problem: which accountability forums dominate, which regulatory instruments anchor in the field, and which public-administration mechanisms remain underdeveloped. Using multiple queries in the Web of Science Core Collection, validated with Scopus, and analyzed with Bibliometrix and complementary science-mapping techniques, the study examines publication trends, influen tial contributors and outlets, collaboration networks, and citation and thematic structures. Publication output increases sharply after 2022, aligning with major regulatory milestones such as the EU AI Act. Results show a strong European concentration, with European actors serving as central hubs in collaboration networks and indicate that 2018-2021 publications form a foundational intel lectual core. The field is anchored in legally oriented concepts (law, transparency, governance, accountability, data protection), while themes such as legitimacy, institutional logics, and rights operationalization remain underdeveloped. Despite growing interdisciplinarity, thematic fragmentation persists, highlighting the need for stronger integration across legal scholarship, public administration, and tech nical AI research, and providing a focused basis for future research and policy agendas.

Formal verification using temporal logics such as computation tree logic (CTL) is essential for validating safety and correctness in complex systems. However, traditional model-checking techniques face severe scalability limitations due to the state explosion problem and their reliance on exhaustive symbolic traversal. Moreover, existing learning-based verification methods often lack formal guarantees and interpretability. These challenges create a pressing need for scalable, learning-based verification methods that preserve verification reliability while improving computational efficiency. This article introduces a novel deep reinforcement learning (DRL)-based model checking framework that learns to verify CTL formulas directly through interaction with system models. Unlike traditional symbolic model checkers such as NuSMV, the proposed DRL-CTL checker trained using proximal policy optimization (PPO) interprets CTL semantics over system models represented as Kripke structures without performing symbolic state-space traversal at inference time. Reward functions are designed for individual CTL operators, and fixed-point reasoning is incorporated to handle global temporal properties such as $AG(\phi)$ and $EG(\phi)$ . Experimental results show that the proposed method achieves near-constant inference time of approximately 2 ms per formula on an Intel Core i9-13900K CPU (24 cores, 3.0 GHz), 64 GB RAM, NVIDIA RTX 4090 GPU (24 GB VRAM), reduces verification time by up to 90% compared with traditional model checkers, and scales to models with more than $10^{1192}$ reachable states. The framework also produces witnesses and counterexamples and yields verification outcomes identical to those of symbolic checkers in our experiments. These results highlight the potential of DRL to serve as a scalable, efficient, and explainable alternative to classical CTL model checking.

Traditional visual SLAM pipelines are typically designed under the static-world assumption and often degrade severely in indoor environments with frequent human motion. To improve trajectory accuracy and front-end stability in such scenarios while maintaining real-time throughput, we present SY-SLAM, an RGB-D SLAM system for dynamic indoor environments with frequent human motion. (S stands for SuperPoint, which is used as a detector-only learned keypoint front-end, and Y stands for YOLO, which provides asynchronous person-aware keypoint suppression based on detected human bounding boxes.) We integrate a TensorRT-deployed detector-only SuperPoint module to improve keypoint repeatability and robustness while retaining ORB binary descriptors for efficient matching and place recognition within the ORB-SLAM3 framework. To avoid feature starvation while preserving keypoint quality, we further introduce an adaptive SuperPoint keypoint selection strategy that applies stricter filtering when keypoints are abundant and relaxes the selection constraints when they are scarce. In parallel, an asynchronous YOLOv8s TensorRT thread performs person detection with temporal bounding-box memory, and keypoints inside detected person regions are removed before ORB descriptor computation and matching to reduce dynamic-feature contamination in the front end. We evaluate SY-SLAM on five dynamic TUM RGB-D fr3 sequences using ATE and RPE metrics. Compared with ORB-SLAM3, SY-SLAM reduces ATE RMSE by 93.45% across four dynamic walking sequences. On the widely reported fr3/w/x sequence, SY-SLAM achieves competitive accuracy with recent dynamic SLAM methods while maintaining real-time performance. The system runs in real time at 46.8 Hz (21.36 ms per frame) on an Intel i9-13900H CPU with an NVIDIA RTX 4070 Laptop GPU.

This data article describes a curated RGB-Depth image dataset captured using an Intel RealSense D435 stereo depth camera mounted on an autonomous mobile platform during field deployments at commercial baby broccoli farms in Victoria, Australia. The dataset comprises 1759 paired RGB images (640 &#xd7; 480 pixels) and corresponding 16-bit depth frames acquired under both daytime (natural sunlight) and night-time (LED illumination) conditions, designed to support research in agricultural computer vision and robotic harvesting. Images were selected from 39,765 raw acquisitions through a reproducible Python curation pipeline applying quality filtering (blur detection, brightness thresholds, corruption detection), perceptual hash-based duplicate removal, and manual review. The final dataset includes 924 daytime and 835 night-time image pairs containing baby broccoli plants at various growth stages. The dataset provides RGB camera intrinsic parameters and pixel-aligned depth maps to enable 3D point cloud reconstruction. Potential applications include developing deep learning models for crop detection and segmentation, validating depth-based size estimation methods, and benchmarking illumination-robust vision systems. All data and curation code are publicly available under a CC BY 4.0 license.

This paper presents an immersive teleoperation framework for service robots that combines real-time 3D human pose estimation with a Virtual Reality (VR) interface to support intuitive, natural robot control. The operator is tracked using MediaPipe for 2D landmark detection and an Intel RealSense D455 RGB-D (Red-Green-Blue plus Depth) camera for depth acquisition, enabling 3D reconstruction of key joints. Joint angles are computed using efficient vector operations and mapped to the kinematic constraints of an anthropomorphic arm on the CHARMIE service robot. A VR-based telepresence interface provides stereoscopic video and head-motion-based view control to improve situational awareness during manipulation tasks. Experiments in real-world object grasping demonstrate reliable arm teleoperation and effective telepresence; however, vision-only estimation remains limited for axial rotations (e.g., elbow and wrist yaw), particularly under occlusions and unfavorable viewpoints. The proposed system provides a practical pathway toward low-cost, sensor-driven, immersive human-robot interaction for service robotics in dynamic environments.

In recent years, two-dimensional transition-metal dichalcogenides (2D TMDs) have emerged as attractive alternative channel materials for next-generation field-effect transistors. Despite significant advances in integrating 2D TMDs into electronic devices, challenges remain, such as fabrication-induced damage, particularly from plasma processes commonly employed in device integration such as etching, cleaning, and deposition. This work systematically identifies and minimizes the sources of plasma-induced damage associated with plasma-enhanced atomic layer deposition (PEALD), particularly during PEALD of TMD films onto CVD-grown TMD substrates for contact applications. On the basis of Raman, photoluminescence, and X-ray photoelectron spectroscopy, damage caused by Ar/H2S plasmas to monolayer WSe2 was reduced by removing Ar from the plasma, reducing the plasma power, and increasing the process chamber pressure. The optimized plasma parameters were subsequently applied to develop an alternative PEALD process for polycrystalline NbxW1-xS2, leading to enhanced preservation of mono-to-few-layer WSe2 within PEALD NbxW1-xS2/MOCVD WSe2 heterostructures, as shown by charge carrier mobility measurements and Raman spectroscopy. The understanding gained from this work provides broadly applicable strategies for reducing plasma-induced damage in 2D materials, paving the way for more robust plasma processing techniques for integration of 2D materials in high-performance heterostructure-based electronic devices.

The widespread adoption of Internet of Things (IoT) devices has opened new possibilities for data-driven decision making while simultaneously raising serious concerns about the protection of sensitive personal information. This paper presents an integrated privacy-preserving data aggregation framework that strategically combines homomorphic encryption, secure multi-party computation, and differential privacy mechanisms. We design a hierarchical three-tier protocol architecture in which IoT devices encrypt their measurements using Paillier homomorphic encryption, edge nodes carry out secure aggregation through distributed computation, and cloud servers inject calibrated differential privacy noise prior to threshold-based decryption. The framework reduces reliance on trusted third parties through Shamir secret sharing while striving to maintain computational efficiency appropriate for resource-constrained devices. Experimental evaluation involving 1000 simulated IoT devices across 30 independent trials demonstrates that the protocol completes aggregation in 3.82&#x2009;&#xb1;&#x2009;0.35&#xa0;s (mean&#x2009;&#xb1;&#x2009;standard deviation) with 2.8% &#xb1; 0.6% relative error under moderate privacy budgets (&#x3b5;&#x2009;=&#x2009;1.0, 95% CI: [2.4%, 3.2%]). Security analysis under the semi-honest adversary model indicates that the protocol satisfies semantic security assumptions and &#x3b5;-differential privacy guarantees. These results suggest that meaningful privacy protection can be achieved while preserving practical utility, offering a potential solution for privacy-sensitive IoT deployments in smart cities, healthcare monitoring, and industrial applications, although certain limitations regarding scalability and adversary models require further investigation.