Search Results (195)

Autonomous ground vehicle navigation in dynamic real-world environments demands path planning systems that simultaneously accommodate real-time environmental hazards and diverse user-defined objectives requirements that classical algorithms, with their static, single-objective cost functions, cannot fulfil. This paper presents the Semantic Personalised Path Planning (SPPP) system, centred on a novel Semantic Personalised Cost (SPC) algorithm that augments the A* search framework with a dynamically computed personalised cost term. The SPC function integrates eight real-time semantic obstacle categories including traffic congestion, weather severity, road surface conditions, and construction activity with eight user-defined preference dimensions spanning safety, travel time, emergency response, comfort, and battery efficiency. An adaptive scaling mechanism amplifies obstacle penalties near the goal, and a gradient-based weight evolution rule refines preference weights iteratively over successive route segments. The user-defined preference activation directly personalises the routing objective to individual operational needs, with the gradient-based evolution further refining preference alignment over successive route segments. Experiments were conducted in two phases: 500 randomised obstacle configurations on a controlled 8 × 8 grid, and a real 847-node road graph extracted from OpenStreetMap around SRM Institute of Science and Technology, Kattankulathur, representing a single 1.4 km urban corridor, with obstacle scores derived from live Mapbox Traffic and OpenWeatherMap application programming interface data. Under the full emergency preference scenario, SPPP achieves 94.3% obstacle avoidance versus 31.7% for the Euclidean distance threshold A* baseline, a difference statistically significant at p < 0.001 under the Wilcoxon signed-rank test with Cohen’s d ≈ 18.9. Real-world computation time of 1.91 ms on a standard laptop and 3.76 ms on a Raspberry Pi 4 confirms deployability on embedded autonomous vehicle hardware. Full article

This paper investigates whether a low-code workflow engine can operate as practical Industrial Internet of Things (IIoT) middleware at the edge when cloud application programming interface (API) rate limits make direct telemetry upload unsustainable. The main contribution is a dual-path architecture in which a Hot Path persists all telemetry locally, while a Cold Path selectively forwards only anomalous or summary events to cloud services. The architecture is implemented as a lightweight containerized stack based on n8n, Eclipse Mosquitto, InfluxDB, and Grafana, and evaluated on a Raspberry Pi 4 under baseline, cloud-only saturation, and edge-filtered stress scenarios. Under the cloud-only condition, the external endpoint is throttled to approximately 60 requests/min, yielding a rejection rate of 98.0% (95% Wilson confidence interval: 97.43–98.44%). Under the dual-path condition, the same inbound load is fully retained locally while outbound cloud traffic is reduced by 98.0%, thereby avoiding throttling without sacrificing edge-side data fidelity. The measured Hot Path processing latency remains around 5 ms on average, with observed peaks below 10 ms, which is compatible with soft real-time monitoring workloads. Compared with more established low-code tools such as Node-RED, the novelty of the study is not the existence of visual orchestration itself, but the combination of containerized deployment, explicit hot/cold decoupling, and an empirical rate-limit mitigation analysis focused on low-cost edge hardware. Full article

Wide-area maritime surveillance is an increasingly important focus for countries with large Exclusive Economic Zones (EEZ), such as Portugal, which are responsible for monitoring and protecting these zones and their resources. Passive acoustic autonomous buoy networks equipped with hydrophones are a promising approach for wide-area maritime surveillance. However, achieving a discrete, low-cost system introduces many technical challenges. This work describes a practical, low-power, two-state architecture that separates continuous ship detection from detailed vessel class classification. First, an always-on microcontroller performs continuous binary ship presence detection and triggers the higher-power classifier only when a vessel is detected. The high-accuracy acoustic classifier was tested across embedded controllers to identify the minimum platform capable of sustaining its intended 1 Hz classification rate. A Raspberry Pi 5 achieved the 1 s target with a measured continuous consumption of 4 W; however, adding sensing, storage, and communications is expected to raise the always-on consumption to around 5 W. If this node was used by itself, a week-long autonomy requirement, therefore, would imply 840 Wh of usable energy storage, and recovering this deficit rapidly under limited insolation would require several hundred watts of photovoltaic capacity, driving both buoy volume and cost up. To address this, an always-on edge node based on an ESP32-S3 microcontroller was implemented, running a lightweight binary detection of a vessel presence model trained in Edge Impulse using a subset of Ocean Networks Canada recordings. The edge node consumes $0.69$ W continuously and is intended to trigger a wake-up line to power the higher-performance node only when a ship is detected, reducing average energy demand while maintaining the ability to run a richer classifier on demand. The presented architecture, profiling workflow, and energy calculations provide a path to power-aware passive acoustic monitoring systems suitable for extended maritime deployments. Full article

Thread counting is used to assess the quality and cultural significance of Philippine indigenous textiles such as Kalinga and Piña. We developed a portable system that automates the process using a Raspberry Pi 4 and the Alex Krizhevsky Convolutional Neural Network. The system processes textile images, employing AlexNet to count warp and weft threads, and displays results for real-time fabric assessment. Initial tests yielded an accuracy rate of ninety-six percent. By integrating AI and portability, this work provides a technical solution while contributing to the sustainability of cultural heritage. Full article

Additive manufacturing enables the development of low-cost, self-built robotic systems; however, their performance is typically not characterized by validated metrics. The paper presents a photogrammetric concept intended for system-independent application to characterize planar positioning accuracy and repeatability without access to internal controller data. The method is based on a Raspberry Pi 4 camera system, image processing in Python 3.12.0 and OpenCV 4.12.0, and a universal additively manufactured robot tool attachment. Two position estimation strategies are investigated: a marker-based approach using ArUco markers and a markerless blob-analysis method based on a ruby sphere. Camera calibration is evaluated using different patterns, with a compact CharUco board exhibiting the lowest RMS reprojection error (~1 px). Experimental validation follows selected elements of ISO 9283:1998 and comprises 30 repetitions at five target poses for linear and axial motion strategies. The results show lower positional deviations for marker-based methods compared to the markerless approach, with a two-marker configuration yielding the lowest mean deviation under the investigated conditions. Sub-millimeter positioning accuracy and repeatability are achieved, and linear motion exhibits lower repeatability deviations than axial motion. The proposed approach provides a cost-effective and flexible solution for external robot characterization, particularly suited for self-built and resource-constrained systems. Full article

Image-based AI offers a low-cost alternative to traditional turbidity sensors in farm ponds, yet the prevailing shift toward Vision Transformers (ViTs) critically overlooks two field realities: the chronic scarcity of annotated data (Small Data) and the strict computational limits of edge hardware. This study presents a frugal computer vision framework that challenges the need for complex architectures in environmental screening. By systematically benchmarking six deep learning models across a calibrated high-turbidity dataset (200–800 NTU, 700 images) under standardized capture conditions, we demonstrate that traditional Convolutional Neural Networks (CNNs) possess a crucial inductive bias for this task. Specifically, ResNet-50 significantly outperformed modern ViTs in both accuracy (96.3% vs. 80.0%) and data efficiency, effectively capturing spatial scattering patterns without the massive data requirements that hindered transformer convergence. Deployed on a resource-constrained Raspberry Pi 4, the CNN-based system achieved an inference latency of 46 ms, demonstrated in an initial hardware-in-the-loop field proof-of-concept (82.4% agreement under baseline, calm-weather conditions, $n=17$). This edge-native approach not only provides actionable spatial turbidity maps to guide on-farm filtration and livestock management decisions but also establishes a critical architectural baseline: under controlled capture protocols, mature CNNs consistently outperform ViTs, establishing them as the optimal architecture for frugal, small-data agricultural Internet of Things (IoT) deployments. Full article

This paper evaluates the feasibility of real-time traffic data analysis on resource-constrained edge devices using a hybrid processing approach. The proposed architecture integrates an LF Edge eKuiper complex event processing engine, deployed within Docker containers, with a native YOLO deep learning model for pedestrian detection. The model processes video frames at 480 × 240 resolution on CPU-only Raspberry Pi devices, achieving up to 30 FPS. The research specifically investigates the performance limits of Raspberry Pi 3 and Raspberry Pi 4 platforms when simultaneously processing high-throughput simulated traffic data from the SUMO simulator (Belgrade scenario, with vehicle distributions and densities adjusted for small, medium, and large traffic volumes) and live video streams, respectively. Experimental results indicate that while both platforms can process up to 2600 messages per second in the settings without image processing, the introduction of a camera sensor reveals a significant hardware bottleneck. The Raspberry Pi 4 maintains robust real-time performance with an average complex event detection latency of less than 500 ms. In contrast, the Raspberry Pi 3 exhibits severe performance degradation, with image processing delays exceeding 8 s, rendering it unsuitable for real-time safety alerts. The findings demonstrate that with appropriate hardware selection, edge-based complex event processing can successfully detect critical safety events, such as sudden vehicle acceleration near pedestrians, without relying on cloud infrastructure. Full article

FAEST is a National Institute of Standards and Technology post-quantum signature candidate based on the Vector Oblivious Linear Evaluation-in-the-Head paradigm, whose signing performance is dominated by repeated Advanced Encryption Standard Counter-based Pseudorandom Generator calls. The reference implementation provides no FAEST-specialized acceleration for Advanced RISC Machine platforms. This paper proposes a three-layer Advanced Reduced Instruction Set Computer Machine NEON Single Instruction Multiple Data optimization: a register-resident 256-byte S-box with Table Lookup/Table Lookup with Extension-based SubBytes and four-way/eight-way parallel Advanced Encryption Standard processing; a fixed-length Pseudorandom Generator specialized for the FAEST tree structure; and Portable Operating System Interface for Unix thread-based parallelization of independent Vector Oblivious Linear Evaluation instances. Evaluated on all 12 parameter sets of FAEST v2 on Raspberry Pi 4 (without Advanced Reduced Instruction Set Computer Machine version 8 crypto-extensions) and Apple M2 (with hardware Advanced Encryption Standard support), the proposed method achieves signing speedups of up to 136.9x on Raspberry Pi 4 and 330.1x on Apple M2 over the pure-C reference. On Raspberry Pi 4, the NEON implementation outperforms OpenSSL; on Apple M2, the NEON-plus-Portable Operating System Interface for Unix thread configuration outperforms hardware-accelerated OpenSSL across all parameters, confirming that NEON SIMD combined with task-level parallelization can exceed hardware-accelerated single-thread throughput on Advanced Reduced Instruction Set Computer Machine-based platforms. Full article

We developed an augmented Sungka board that integrates traditional Filipino gameplay with embedded sensor technology. Each pit is equipped with load cell sensors and HX711 analog-to-digital converters to accurately detect marble distribution and movement in real time. A Raspberry Pi 4 serves as the central controller, handling sensor data acquisition, game state processing, rule enforcement, and output display through a liquid crystal display. The system enables automatic score tracking, move validation, and real-time board updates without altering the physical structure or rules of Sungka. A rule-based decision algorithm using fuzzy logic and heuristic search evaluates possible moves in constant time, allowing seamless real-time interaction. Across 10,000 simulated games, the algorithm achieved win rates of 84.9% against random, 77.7% against greedy, and 56.3% against exact-match strategies, with statistically consistent performance. By combining reliable hardware sensing with intelligent decision support, the proposed system enhances engagement while preserving the cultural authenticity of Sungka. Full article

Biometric systems are widely used in security and forensic applications. Conventionally, contact-based footprint scanners require physical contact, which presents significant limitations. These devices raise hygiene concerns and are impractical in field identification conditions, such as forensic investigations or disaster victim identification, where quick and non-invasive methods are essential. To address these challenges, a contactless footprint acquisition and identification system was developed using image processing techniques and a Convolutional Neural Network (CNN) based on the Visual Geometry Group–16 layer architecture. The system employs a Raspberry Pi 4, a Logitech C922 camera, and a ring light to capture footprints without direct surface contact. Captured images are processed with Contrast Limited Adaptive Histogram Equalization (CLAHE) to improve contrast and mean thresholding to generate binary images for clearer feature extraction. System performance was evaluated using a multiclass confusion matrix. The CNN correctly classified 158 of 160 test images, achieving an accuracy of 98.75%. This result demonstrates higher accuracy than earlier studies that used older CNN models, such as Alex Krizhevsky’s Network and LeCun’s Network-5, which performed with fewer subjects and lower accuracy rates. The developed system shows potential for biometric security, forensic investigations, and disaster response, where contactless and reliable identification is required. Future research can expand the dataset with more diverse footprints, test performance under varied conditions, and extend the approach to other contactless biometrics such as palmprints or ears. Full article

NetworkGuard is a modular edge-based virtual network sensing framework designed for residential smart home security. The system interprets network telemetry—such as DNS queries, firewall events, VPN latency, and connection establishment delay—as structured sensing signals for gateway-level monitoring. Implemented on a Raspberry Pi 4 and managed via an Android interface, NetworkGuard integrates DNS filtering (Pi-hole), firewall enforcement (UFW), encrypted VPN tunneling (WireGuard), and an AI-assisted advisory layer for contextual log interpretation. During a six-week residential deployment, DNS blocking efficiency improved from 81.2% to 97.0% following blocklist refinement, while VPN connection establishment time decreased from approximately 3012 ms to 2410 ms after configuration tuning. ICMP-based measurements indicated a stable tunnel latency under moderate traffic conditions. Controlled validation scenarios—including DNS manipulation attempts, port scanning, and VPN interruption testing—confirmed consistent firewall enforcement and tunnel containment. The results demonstrate that layered security principles can be adapted into a lightweight, reproducible edge architecture suitable for small-scale residential IoT environments without a reliance on enterprise infrastructure. Full article

The early and accurate detection of plant diseases is essential for crop management and agricultural loss control, especially under resource limitations. We propose an optimized YOLO11n architecture, designated as YOLO11_Opt, targeting real-time inference on low-cost embedded systems. The model is computationally efficient through the selective narrowing of its width and depth, while performing competitively in two-class object recognition tasks. Pepper leaves were chosen as the materials for study. Three methods of quantization (FP32, FP16, and INT8) were investigated. After running the experiments, the results showed that YOLO11_Opt greatly reduces the computational complexity: the complexity decreased from 6.3 GFLOPS and 2.58 million parameters in the typical YOLO11n model to a very small 0.5 GFLOPS and 0.33 million parameters, while maintaining competitive detection capabilities. The improved FP32 model has a mAP (0.5:0.95) of 0.913 and a precision of 0.991, while the old version has 0.961 mAP and 0.996 precision. Lastly, implementations on embedded hardware prove that the method is feasible: the detection accuracy of the system in live classification is around 92% with Raspberry Pi 4 and 94% with NVIDIA Jetson Nano, with inference times of as little as 1.9 ms on NVIDIA Jetson Nano and 8.3 ms on Raspberry Pi 4. Thus, YOLO11_Opt demonstrates significant potential as a reliable, high-performance, low-cost solution to identifying plant diseases on devices in precision agriculture. Full article

This paper presents an ARMv8/NEON-oriented implementation of NCC-Sign targeting the NTT-friendly trinomial parameter sets (NCC-Sign-1/3/5), whose dominant cost arises from mixed-radix NTT computations with $n=2^a·3^b$. We design lane-local SIMD kernels—including a four-lane Montgomery multiply–reduce, a centered modular reduction pass, a fused stage-0 butterfly, and streamlined radix-2/radix-3 pipelines—and extend them with three further optimizations: (i) radix-2 multi-stage butterfly merging to halve intermediate load/store traffic, (ii) a stride-3 vectorization technique exploiting NEON structure load/store instructions (vld3q/vst3q) to fully vectorize small-len radix-3 stages that would otherwise fall back to scalar execution, and (iii) NEON-parallel pointwise Montgomery multiplication. Using cycle-accurate PMU measurements under identical toolchains for baseline and optimized builds on Apple M1 Pro, we observe geometric-mean speedups of 1.40× for key generation, 2.24× for signing, and 2.01× for verification across NCC-Sign-1/3/5, with per-kernel gains of up to 5–6× for NTT/INTT and 7.5× for pointwise multiplication. To contextualize these results, we provide a direct comparison with the NEON-optimized ML-DSA (Dilithium) implementation of Becker et al. on the same platform, a cross-platform evaluation on Arm Cortex-A72 (Raspberry Pi 4), a Montgomery-versus-Barrett microbenchmark supporting our design choice, and an empirical constant-time assessment via dudect confirming that no timing leakage is detected in any NEON kernel under 30 million measurements. Full article

Biodiversity monitoring in tropical ecosystems is constrained by limited infrastructure, insufficient localized datasets, and reliance on cloud-based tools. We introduce BEMAX, a lightweight convolutional neural network for offline classification of endangered tree species in the Bohol Biodiversity Complex, Philippines. A curated leaf-image dataset from five species and an unknown class was collected using a Raspberry Pi camera. The MobileNetV2-based model achieved a 93.89% validation accuracy and an 88.33% field accuracy. Deployed on a Raspberry Pi 4 with touchscreen and camera integration, BEMAX demonstrates embedded AI as a replicable framework for conservation in data-scarce environments. Full article

Guava is a popular fruit in the Philippines, as it offers various health benefits. Its leaves are used in traditional medicine to aid in wound healing, stomach disorders, pain relief, and more. In this study, we classified guava leaf diseases using Support Vector Machine (SVM) and You Only Look Once version 8 (YOLOv8). Raspberry Pi 4 is used to control the image preprocessing and the program that utilizes the proposed trained model. The SVM model conducts image classification, while YOLOv8 handles feature extraction and object detection. Grayscale and color thresholding segmentation feature extraction is also implemented in the proposed model. The developed model combines both YOLOv8 and SVM algorithms to evaluate their accuracy using a confusion matrix, achieving a 92.5% accuracy. With its very low error rate, the system can accurately classify guava leaf diseases. Full article