Search Results (52)

The widespread use of WiFi Internet-of-Things (IoT) devices has rendered them valuable tools for detecting information about the physical environment. Recent studies have demonstrated that WiFi Channel State Information (CSI) can detect physical events like movement, occupancy increases, and gestures. This paper empirically investigates the conditions under which WiFi sensing technology remains effective for keystroke detection. To achieve this timely goal of assessing whether it can raise any privacy concerns, experiments are conducted using commodity hardware to predict the accuracy of WiFi CSI in detecting keys pressed on a keyboard. Our novel results show that, in an ideal setting with a robotic arm, the position of a specific key can be predicted with $99\%$ accuracy using a simple machine learning classifier. Furthermore, human finger localisation over a key and actual key-press recognition is also successfully achieved, with $94\%$ and $89\%$ reduced accuracy values, respectively. Moreover, our detailed investigation reveals that to ensure high accuracy, the gap distance between each test object must be substantial, while the size of the test group should be limited. Finally, we show WiFi sensing technology has limitations in small-scale gesture recognition for generic settings where proper device positioning is crucial. Specifically, detecting keyed words achieves an overall accuracy of $94\%$ for the forefinger and $87\%$ for multiple fingers when only the right hand is used. Accuracy drops to $56\%$ when using both hands. We conclude WiFi sensing is effective in controlled indoor environments, but it has limitations due to the device location and the limited granularity of sensing objects. Full article

Large-language-model (LLM) APIs demonstrate impressive reasoning capabilities, but their size, cost, and closed weights limit the deployment of knowledge-aware AI within biomedical research groups. At the other extreme, standard attention-based neural language models (SANLMs)—including encoder–decoder architectures such as Transformers, Gated Recurrent Units (GRUs), and Long Short-Term Memory (LSTM) networks—are computationally inexpensive. However, their capacity for semantic reasoning in noisy, open-vocabulary knowledge bases (KBs) remains unquantified. Therefore, we investigate whether compact SANLMs can (i) reason over hybrid OpenIE-derived KBs that integrate commonsense, general-purpose, and non-communicable-disease (NCD) literature; (ii) operate effectively on commodity GPUs; and (iii) exhibit semantic coherence as assessed through manual linguistic inspection. To this end, we constructed four training KBs by integrating ConceptNet (600k triples), a 39k-triple general-purpose OpenIE set, and an 18.6k-triple OpenNCDKB extracted from 1200 PubMed abstracts. Encoder–decoder GRU, LSTM, and Transformer models (1–2 blocks) were trained to predict the object phrase given the subject + predicate. Beyond token-level cross-entropy, we introduced the Meaning-based Selectional-Preference Test (MSPT): for each withheld triple, we masked the object, generated a candidate, and measured its surplus cosine similarity over a random baseline using word embeddings, with significance assessed via a one-sided t-test. Hyperparameter sensitivity (311 GRU/168 LSTM runs) was analyzed, and qualitative frame–role diagnostics completed the evaluation. Our results showed that all SANLMs learned effectively from the point of view of the cross entropy loss. In addition, our MSPT provided meaningful semantic insights: for the GRUs (256-dim, 2048-unit, 1-layer): mean similarity $\left({\mu }_{sts}\right)$ of 0.641 to the ground truth vs. 0.542 to the random baseline (gap 12.1%; $p<{10}^{-180}$). For the 1-block Transformer: ${\mu }_{sts}=0.551$ vs. $0.511$ (gap 4%; $p<{10}^{-25}$). While Transformers minimized loss and accuracy variance, GRUs captured finer selectional preferences. Both architectures trained within <24 GB GPU VRAM and produced linguistically acceptable, albeit over-generalized, biomedical assertions. Due to their observed performance, LSTM results were designated as baseline models for comparison. Therefore, properly tuned SANLMs can achieve statistically robust semantic reasoning over noisy, domain-specific KBs without reliance on massive LLMs. Their interpretability, minimal hardware footprint, and open weights promote equitable AI research, opening new avenues for automated NCD knowledge synthesis, surveillance, and decision support. Full article

Robust indoor robot navigation typically demands either costly sensors or extensive training data. We propose a cost-effective RGB-D navigation pipeline that couples feature-based relative pose estimation with a lightweight multi-layer-perceptron (MLP) policy. RGB-D keyframes extracted from human-driven traversals form nodes of a topological map; edges are added when visual similarity and geometric–kinematic constraints are jointly satisfied. During autonomy, LightGlue features and SVD give six-DoF relative pose to the active keyframe, and the MLP predicts one of four discrete actions. Low visual similarity or detected obstacles trigger graph editing and Dijkstra replanning in real time. Across eight tasks in four Habitat-Sim environments, the agent covered 190.44 m, replanning when required, and consistently stopped within 0.1 m of the goal while running on commodity hardware. An information-theoretic analysis over the Multi-Illumination dataset shows that LightGlue maximizes per-second information gain under lighting changes, motivating its selection. The modular design attains reliable navigation without metric SLAM or large-scale learning, and seamlessly accommodates future perception or policy upgrades. Full article

Precise temperature control in high-temperature furnaces is challenged by nonlinearities, parameter drift, and high thermal inertia. This study proposes an adaptive control strategy combining a classical PID loop with real-time gain updates from a feed-forward artificial neural network (ANN). Implemented on an 18 kW retrofitted Blue-M furnace, the system was characterized by second-order transfer functions for heating and forced convection cooling. A dataset of 9702 samples was built from eight fixed PID configurations tested under a multi-ramp thermal profile. The selected 3-64-64-32-2 ANN, executed in Python and interfaced with LabVIEW, computes optimal gains in 0.054 ms while preserving real-time monitoring capabilities. Experimental results show that the ANN-assisted PID reduces the mean absolute error to 5.08 °C, limits overshoot to 41% (from 53%), and shortens settling time by 20% compared to the best fixed-gain loop. It also outperforms a fuzzy controller and remains stable under ±5% signal noise. Notably, gain reversals during cooling prevent temperature spikes, improving transient response. Relying on commodity hardware and open-source tools, this approach offers a cost-effective solution for legacy furnace upgrades and provides a replicable model for adaptive control in high-temperature, safety-critical environments like metal processing, battery cycling, and nuclear systems. Full article

Digital agriculture has rapidly developed in the last decade in many countries where the share of agricultural production is a significant part of the total volume of gross production. Digital agroecosystems are developed using a variety of IT solutions, software and hardware tools, wired and wireless data transmission technologies, open source code, Open API, etc. A special place in agroecosystems is occupied by electronic payment technologies and blockchain technologies, which allow farmers and other agricultural enterprises to conduct commodity and monetary transactions with suppliers, creditors, and buyers of products. Such ecosystems contribute to the sustainable development of agriculture, agricultural engineering, and management of production and financial operations in the agricultural industry and related industries, as well as in other sectors of the economy of a number of countries. The introduction of crypto solutions in the agricultural sector is designed to create integrated platforms aimed at helping farmers manage supply lines or gain access to financial services. At the same time, there are risks of illegal use of computing power for cryptocurrency mining—cryptojacking. This article offers a thorough risk assessment of cryptojacking attacks on endpoint systems, focusing on identifying critical vulnerabilities within IT infrastructures and outlining practical preventive measures. The analysis examines key attack vectors—including compromised websites, infected applications, and supply chain infiltration—and explores how unauthorized cryptocurrency mining degrades system performance and endangers data security. The research methodology combines an evaluation of current cybersecurity trends, a review of specialized literature, and a controlled experiment simulating cryptojacking attacks. The findings highlight the importance of multi-layered protection mechanisms and ongoing system monitoring to detect malicious activities at an early stage. 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

Acoustic target recognition has always played a central role in marine sensing. Traditional signal processing techniques that have been used for target recognition have shown limitations in accuracy, particularly with commodity hardware. To address such limitations, we present the results of our experiments to assess the capabilities of AI-enabled acoustic buoys using OpenEar™, a commercial, off-the-shelf, software-defined hydrophone sensor, for detecting and tracking fast-moving vessels. We used a triangular sparse sensor network to investigate techniques necessary to estimate the detection, classification, localization, and tracking of boats transiting through the network. Emphasis was placed on evaluating the sensor’s operational detection range and feasibility of onboard AI for cloud-based data fusion. Results indicated effectiveness for enhancing maritime domain awareness and gaining insight into illegal, unreported, and unregulated activities. Additionally, this study provides a framework for scaling autonomous sensor networks to support persistent maritime surveillance. Full article

Typically, developing new digital agriculture technologies requires substantial on-site resources and data. However, the crop’s growth cycle provides only limited time windows for experiments and equipment validation. This study presents a photorealistic digital twin of a commercial-scale strawberry farm, coupled with a simulated ground vehicle, to address these constraints by generating high-fidelity synthetic RGB and LiDAR data. These data enable the rapid development and evaluation of a deep learning-based machine vision pipeline for fruit detection and sizing without continuously relying on real-field access. Traditional simulators often lack visual realism, leading many studies to mix real images or adopt domain adaptation methods to address the reality gap. In contrast, this work relies solely on photorealistic simulation outputs for training, eliminating the need for real images or specialized adaptation approaches. After training exclusively on images captured in the virtual environment, the model was tested on a commercial-scale strawberry farm using a physical ground vehicle. Two separate trials with field images resulted in F1-scores of 0.92 and 0.81 for detection and a sizing error of 1.4 mm (R² = 0.92) when comparing image-derived diameters against caliper measurements. These findings indicate that a digital twin-driven sim2real transfer can offer substantial time and cost savings by refining crucial tasks such as stereo sensor calibration and machine learning model development before extensive real-field deployments. In addition, the study examined geometric accuracy and visual fidelity through systematic comparisons of LiDAR and RGB sensor outputs from the virtual and real farms. Results demonstrated close alignment in both topography and textural details, validating the digital twin’s ability to replicate intricate field characteristics, including raised bed geometry and strawberry plant distribution. The techniques developed and validated in this strawberry project have broad applicability across agricultural commodities, particularly for fruit and vegetable production systems. This study demonstrates that integrating digital twins with simulation tools can significantly reduce the need for resource-intensive field data collection while accelerating the development and refinement of agricultural robotics algorithms and hardware. Full article

The high costs of acquiring and maintaining high-performance computing (HPC) resources pose significant barriers for medium-sized enterprises and educational institutions, often forcing them to rely on expensive cloud-based solutions with recurring costs. This paper introduces CommC, a multi-purpose commodity hardware cluster designed to reduce operational expenses and extend hardware lifespan by repurposing underutilized computing resources. By integrating virtualization (KVM and Proxmox) and containerization (Kubernetes and Docker), CommC creates a scalable, secure, and cost-efficient computing environment. The proposed system enables seamless resource sharing, ensuring high availability and fault tolerance for both containerized and virtualized workloads. To demonstrate its versatility, we deploy big data engines like Apache Spark alongside traditional web services, showcasing CommC’s ability to support diverse workloads efficiently. Our cost analysis reveals that CommC reduces computing expenses by up to 77.93% compared to cloud-based alternatives while also mitigating e-waste accumulation by extending the lifespan of existing hardware. This significantly improves environmental sustainability compared to cloud providers, where frequent hardware turnover contributes to rising carbon emissions. This research contributes to the fields of cloud computing, resource management, and sustainable IT infrastructure by providing a replicable, adaptable, and financially viable alternative to traditional cloud-based solutions. Future work will focus on automating resource allocation, enhancing real-time monitoring, and integrating advanced security mechanisms to further optimize performance and usability. Full article

Image inpainting for indoor environments presents unique challenges due to complex spatial relationships, diverse lighting conditions, and domain-specific object configurations. This paper introduces a resource-efficient post-processing framework that enhances domain-specific image inpainting through an adaptation mechanism. Our architecture integrates a convolutional neural network with residual connections optimized via a multi-term objective function combining perceptual losses and adaptive loss weighting. Experiments on our curated dataset of 4000 indoor household scenes demonstrate improved performance, with training completed in 20 min on commodity GPU hardware with 0.14 s of inference latency per image. The framework exhibits enhanced results across standard metrics (FID, SSIM, LPIPS, MAE, and PSNR), showing improvements in structural coherence and perceptual quality while preserving cross-domain generalization abilities. Our methodology offers a novel approach for efficient domain adaptation in image inpainting, particularly suitable for real-world applications under computational constraints. This work advances the development of domain-aware image restoration systems and provides architectural insights for specialized image processing frameworks. Full article

Continuous movement monitoring helps quickly identify pig abnormalities, enabling immediate action to enhance pig welfare. However, continuous and precise monitoring of daily pig movement on farms remains challenging. We present an approach to automatically and precisely monitor the movement of group-housed pigs. The instance segmentation model YOLOv8m-seg was applied to detect the presence of pigs. We then applied a spatial moment algorithm to quantitatively summarize each detected pig’s contour as a corresponding center point. The agglomerative clustering (AC) algorithm was subsequently used to gather the pig center points of a single frame into one point representing the group-housed pigs’ position, and the movement volume was obtained by calculating the displacements of the clustered group-housed pigs’ center points of consecutive frames. We employed the method to monitor the movement of group-housed pigs from April to July 2023; more than 1500 h of top-down pig videos were recorded by a surveillance camera. The F1 scores of the trained YOLOv8m-seg model during training were greater than 90% across most confidence levels, and the model achieved an mAP50-95 of 0.96. The AC algorithm performs with an average extraction time of less than 1 millisecond; this method can run efficiently on commodity hardware. Full article

This research paper examines the risks posed by the MIH EV Open platform to German automotive suppliers, in particular, the risk of commoditization and falling into a commodity trap. The term commodity trap describes a situation in which companies dealing with standardized products or services face intense price and margin pressure and struggle to differentiate themselves from competitors. The MIH EV Open platform, established by Foxconn, also known as Hon Hai Precision Industry Co. Ltd., headquartered in Tucheng, Taipei, Taiwan, aims to create a collaborative platform for the comprehensive development of key software, hardware components, and services in the electric vehicle (EV) industry. It unites over 2700 companies from more than 70 countries and fosters collaboration to accelerate the development and market entry of new EV products. This paper analyzes the MIH EV Open business ecosystem model and assesses the strengths and weaknesses of German suppliers in addressing these challenges. This study highlights strategic approaches, including innovation, portfolio adaptation, customer relationships, and sustainability practices, that can enable German suppliers to mitigate commodity trap risks. The findings underscore the importance of proactive, segment-specific strategies amidst the transformation of the automotive industry. Key insights are provided on the potential impact of open platform ecosystems and recommendations for German automotive suppliers to maintain competitiveness. This research fills a gap in the literature by examining the commoditization risks posed by the MIH EV Open platform for German automotive suppliers. Unlike previous studies that focus on traditional market structures, this study explores the novel dynamics introduced by platform ecosystems and provides strategic insights to mitigate these risks. Full article

In the ever-evolving landscape of tomographic imaging algorithms, this literature review explores a diverse array of themes shaping the field’s progress. It encompasses foundational principles, special innovative approaches, tomographic implementation algorithms, and applications of tomography in medicine, natural sciences, remote sensing, and seismology. This choice is to show off the diversity of tomographic applications and simultaneously the new trends in tomography in recent years. Accordingly, the evaluation of backprojection methods for breast tomographic reconstruction is highlighted. After that, multi-slice fusion takes center stage, promising real-time insights into dynamic processes and advanced diagnosis. Computational efficiency, especially in methods for accelerating tomographic reconstruction algorithms on commodity PC graphics hardware, is also presented. In geophysics, a deep learning-based approach to ground-penetrating radar (GPR) data inversion propels us into the future of geological and environmental sciences. We venture into Earth sciences with global seismic tomography: the inverse problem and beyond, understanding the Earth’s subsurface through advanced inverse problem solutions and pushing boundaries. Lastly, optical coherence tomography is reviewed in basic applications for revealing tiny biological tissue structures. This review presents the main categories of applications of tomography, providing a deep insight into the methods and algorithms that have been developed so far so that the reader who wants to deal with the subject is fully informed. Full article

Virtual Private LAN Services (VPLS) is an ethernet-based Virtual Private Network (VPN) service that provides multipoint-to-multipoint Layer 2 VPN service, where each site is geographically dispersed across a Wide Area Network (WAN). The adaptability and scalability of VPLS are limited despite the fact that they provide a flexible solution for connecting geographically dispersed sites. Furthermore, the construction of tunnels connecting customer locations that are separated by great distances adds a substantial amount of latency to the user traffic transportation. To address these issues, a novel Hierarchical VPLS (H-VPLS) architecture has been developed using 802.1Q tunneling (also known as Q-in-Q) on high-speed and commodity routers to satisfy the additional requirements of new VPLS applications. The Vector Packet Processing (VPP) performs as the router’s data plane, and FRRouting (FRR), an open-source network routing software suite, acts as the router’s control plane. The router is designed to seamlessly forward VPLS packets using the Request For Comments (RFCs) 4762, 4446, 4447, 4448, and 4385 from The Internet Engineering Task Force (IETF) integrated with VPP. In addition, the Label Distribution Protocol (LDP) is used for Multi-Protocol Label Switching (MPLS) Pseudo-Wire (PW) signaling in FRR. The proposed mechanism has been implemented on a software-based router in the Linux environment and tested for its functionality, signaling, and control plane processes. The router is also implemented on commodity hardware for testing the functionality of VPLS in the real world. Finally, the analysis of the results verifies the efficiency of the proposed mechanism in terms of throughput, latency, and packet loss ratio. Full article

The increasing network speeds of today’s Internet require high-performance, high-throughput network devices. However, the lack of affordable, flexible, and readily available devices poses a challenge for packet classification and filtering. This problem is exacerbated by the increase in volumetric Distributed Denial-of-Service (DDoS) attacks, which require efficient packet processing and filtering. To meet the demands of high-speed networks and configurable network processing devices, this paper investigates a hybrid hardware/software packet filter prototype that combines reconfigurable FPGA technology and high-speed software filtering on commodity hardware. It uses a novel approach that offloads filtering rules to the hardware and employs a Longest Prefix Matching (LPM) algorithm and allowlists/blocklists based on millions of IP prefixes. The hybrid filter demonstrates improvements over software-only filtering, achieving performance gains of nearly 30%, depending on the rulesets, offloading methods, and traffic types. The significance of this research lies in developing a cost-effective alternative to more-expensive or less-effective filters, providing high-speed DDoS packet filtering for IPv4 traffic, as it still dominates over IPv6. Deploying these filters on commodity hardware at the edge of the network can mitigate the impact of DDoS attacks on protected networks, enhancing the security of all devices on the network, including Internet of Things (IoT) devices. Full article