Varela Aldas, José
Preferred name
Varela Aldas, José
Main Affiliation
Ambato
Email
josevarela@uti.edu.ec
ORCID
0000-0002-4084-1424
Scopus Author ID
57192546163
168 results
Now showing 1 - 10 of 168
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Analysis of YOLOv26 Variants (Nano to Extra-Large) for Real-Time Weapon Detection in Video SurveillanceReal-time weapon detection in video surveillance systems is a critical requirement for proactive security applications, particularly under the computational and latency constraints imposed by edge artificial intelligence deployments. While the YOLO family of object detectors has undergone continuous architectural evolution, the recently introduced YOLOv26 represents a significant redesign aimed at improving efficiency, stability, and deployment suitability across a wide range of hardware platforms. This work presents a comprehensive and homogeneous experimental evaluation of the full YOLOv26 model family, ranging from nano (YOLOv26n) to extra-large (YOLOv26x) variants, for real-time weapon detection in surveillance imagery. All models are trained and evaluated under identical conditions using a dataset that explicitly includes visually similar non-weapon objects as hard negatives, enabling a realistic assessment of false positives and false negatives in safety critical scenarios. The analysis encompasses training and validation dynamics, precision, recall evolution, mean Average Precision (mAP) at multiple IoU thresholds, class-wise confusion matrices, and inference latency. Results show that performance improves consistently from smaller to medium sized models, with YOLOv26m achieving the most balanced trade off between detection accuracy, robustness, and computational cost. Larger variants provide marginal accuracy gains at significantly higher complexity, revealing diminishing returns for edge oriented deployments. Overall, the findings demonstrate that the YOLOv26 architecture offers a scalable and mature detection framework, where model selection can be guided by explicit operational criteria rather than raw accuracy alone. This study establishes a strong baseline for future work on real world edge deployment, multi camera surveillance systems, and hardware aware optimization of next generation YOLO detectors. © 2026 IEEE. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Immersive AR–ROS 2 Teleoperation Architecture for a Physical Quadruped Robot(MDPI AG, 2026-07-15) - Some of the metrics are blocked by yourconsent settings
Item type:Publication, ROS2-Based Low-Cost Mobile Robot for Educational Assistance with Reactive Navigation and Semantic-Cached Language Processing(MDPI AG, 2026-07-08); Isa-Jara, RamiroEducational environments, particularly those with limited resources, require affordable mobile robots capable of combining human–robot interaction, autonomous assistance, and academic support without continuous dependence on cloud services. This work presents a low-cost ROS2-based mobile robot implemented on a Raspberry Pi 4B to provide educational assistance in Spanish within controlled classroom environments. The system integrates voice interaction, text-to-speech synthesis, YOLOv8n-based object perception, a specialized door detection model, ultrasonic and inertial sensing, differential-drive control, and a hybrid natural language processing architecture based on semantic caching, local inference, and optional cloud connectivity. Two task-dependent operating modes, education and navigation, selectively activate ROS2 nodes to reduce computational load and energy consumption. Experimental tests conducted in a university classroom evaluated speech recognition, vision models, natural language processing alternatives, sensor behavior, and battery life. The speech recognition module achieved 98% accuracy under both quiet and noisy conditions. YOLOv8n achieved an F1-score of 0.975 for common classroom objects, while the specialized door detector achieved 100% recall with 58.7% precision. The semantic cache correctly resolved recurrent academic queries in the exact-match evaluation, with an average latency of 3.8 s, reducing the need for external language models in known-question scenarios. The robot operated for 96 min in education mode and 75.6 min in navigation mode. These results demonstrate that Spanish voice interaction, reactive navigation, academic question answering, and resource-aware operation can be integrated into a single low-cost edge robotic platform for educational environments. © 2026 by the authors. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Fiber–matrix interaction governs compressive strength in agave-bagasse-reinforced adobe: a factorial experiment with two-way ANOVA and competing mechanism analysis(Frontiers Media SA, 2026-07-31) - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Does the use of dedicated mobile devices in magnetism classes improve student learning?(Frontiers Media SA, 2026-04-21); - Some of the metrics are blocked by yourconsent settings
Item type:Publication, A Multi-Camera Temporal Fusion for False Alarm Suppression in Edge-Based Weapon Surveillance(Institute of Electrical and Electronics Engineers (IEEE), 2026); - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Comparative analysis of previous YOLO detectors and YOLOv26s for real-time weapon detection in video surveillance(Frontiers Media SA, 2026-04-28); - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Hybrid BLE–LoRa architectures for energy-efficient and resilient wireless sensor networks: Experimental validation and adaptive clustering strategies(Springer Science and Business Media LLC, 2026-06-03); Visconti, PaoloWireless Sensor Networks are increasingly deployed in mission-critical scenarios where resilience and energy efficiency are paramount. This paper presents a hybrid architecture combining Bluetooth Low Energy (BLE) and Long Range (LoRa) technologies to enhance both robustness and energy-aware performance in adversarial environments characterized by reactive jamming attacks. A comprehensive experimental testbed was developed, integrating BLE and LoRa nodes, a dual-protocol gateway, and a reactive jammer emulator. We introduce an adaptive clustering algorithm that performs energy-aware role assignment and jamming mitigation based on signal anomaly detection and multi-metric routing. To validate its effectiveness, we conducted an extensive time-series analysis on energy consumption, retransmission rates, and signal resilience under both mitigated and non-mitigated conditions across BLE-only, LoRa-only, and hybrid BLE-LoRa networks. The results show protocol-dependent performance trade-offs under the proposed mitigation algorithm. While LoRa-only and hybrid BLE–LoRa networks exhibit consistent reductions in energy consumption, retransmissions, and variability, the BLE-only configuration demonstrates improved resilience at the cost of a moderate increase in energy usage and retransmission activity due to clustering and control overhead. Notably, the BLE-LoRa architecture balances delivery assurance and energy efficiency while maintaining communication even under interference. Furthermore, we provide statistical modeling and hypothesis testing confirming the mitigation algorithm’s significant impact. These findings offer a critical empirical contribution to the design of resilient and energy-aware heterogeneous WSNs and demonstrate the viability of real-time adaptive mitigation strategies for emerging smart environments - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Multipath Routing Protocol: For Wireless Ad-hoc Networks Based on FibonacciA WANET, which stands for Wireless Ad hoc Network, is a temporary network in which nodes are connected to each other via wireless links and there is no central management. Due to its adaptive structure, WANET is very useful in situations when quick communication link setup is necessary. On the other hand, Channel Contention (CC), degrades the performance of WANET and is a major contributor to packet drops. To solve the CC problem, this paper proposes a routing protocol called Multipath Channel Contention Based Routing (MCCBR). Using MCCBR, several paths are discovered for data transmission that have minimal contention between the source and destination. Then the packets are distributed over the discovered routes based on the Fibonacci sequence. The process of searching for new paths for transmission is initiated when the number of found paths becomes less than 50%. The proposed routing protocol was tested and verified using NS2 simulator. The performance of MCCBR was evaluated against the Ad hoc On Demand Distance Vector (AODV) and Channel Contention Based Routing (CCBR) protocols. MCCBR outperformed AODV and CCBR in terms of Packet Delivery Ratio (PDR), End-to-End (E2E) delay, and normalized Media Access Control (MAC) overhead. © 2026, Zarka Private University. All rights reserved. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Point Mass Planning and NMPC Tracking for Time-Optimal Agile Quadrotor Gate Navigation(Institute of Electrical and Electronics Engineers (IEEE), 2026)