Explainable AI-Enhanced Human Activity Recognition for Human–Robot Collaboration in Agriculture

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(2), P. 650 - 650

Published: Jan. 10, 2025

This study addresses a critical gap in human activity recognition (HAR) research by enhancing both the explainability and efficiency of classification collaborative human–robot systems, particularly agricultural environments. While traditional HAR models often prioritize improving overall accuracy, they typically lack transparency how sensor data contribute to decision-making. To fill this gap, integrates explainable artificial intelligence, specifically SHapley Additive exPlanations (SHAP), thus interpretability model. Data were collected from 20 participants who wore five inertial measurement units (IMUs) at various body positions while performing material handling tasks involving an unmanned ground vehicle field harvesting scenario. The results highlight central role torso-mounted sensors, lumbar region, cervix, chest, capturing core movements, wrist sensors provided useful complementary information, especially for load-related activities. XGBoost-based model, selected mainly allowing in-depth analysis feature contributions considerably reducing complexity calculations, demonstrated strong performance HAR. findings indicate that future should focus on enlarging dataset, investigating use additional placements, real-world trials enhance model’s generalizability adaptability practical applications.

Language: Английский

---

Reliability, Accuracy, and Comprehensibility of AI-Based Responses to Common Patient Questions Regarding Spinal Cord Stimulation

Journal of Clinical Medicine, Journal Year: 2025, Volume and Issue: 14(5), P. 1453 - 1453

Published: Feb. 21, 2025

Background: Although spinal cord stimulation (SCS) is an effective treatment for managing chronic pain, many patients have understandable questions and concerns regarding this therapy. Artificial intelligence (AI) has shown promise in delivering patient education healthcare. This study evaluates the reliability, accuracy, comprehensibility of ChatGPT’s responses to common inquiries about SCS. Methods: Thirteen commonly asked SCS were selected based on authors’ clinical experience pain a targeted review materials relevant medical literature. The prioritized their frequency consultations, relevance decision-making SCS, complexity information typically required comprehensively address questions. These spanned three domains: pre-procedural, intra-procedural, post-procedural concerns. Responses generated using GPT-4.0 with prompt “If you physician, how would answer asking…”. independently assessed by 10 physicians two non-healthcare professionals Likert scale reliability (1–6 points), accuracy (1–3 points). Results: demonstrated strong (5.1 ± 0.7) (2.8 0.2), 92% 98% responses, respectively, meeting or exceeding our predefined thresholds. Accuracy was 2.7 0.3, 95% rated sufficiently accurate. General queries, such as “What stimulation?” are risks benefits?”, received higher scores compared technical like different types waveforms used SCS?”. Conclusions: ChatGPT can be implemented supplementary tool education, particularly addressing general procedural queries However, AI’s performance less robust highly nuanced

Language: Английский

---

Material Perception Data: Reliability Test and Perceptual Qualities Analysis of Material Classes Using Clustering Analysis

Korean Journal of Materials Research, Journal Year: 2025, Volume and Issue: 35(1), P. 26 - 34

Published: Jan. 27, 2025

Language: Английский

---

Effectiveness of Generative Artificial Intelligence-Driven Responses to Patient Concerns in Long-Term Opioid Therapy: Cross-Model Assessment

Biomedicines, Journal Year: 2025, Volume and Issue: 13(3), P. 636 - 636

Published: March 5, 2025

Background: While long-term opioid therapy is a widely utilized strategy for managing chronic pain, many patients have understandable questions and concerns regarding its safety, efficacy, potential dependency addiction. Providing clear, accurate, reliable information essential fostering patient understanding acceptance. Generative artificial intelligence (AI) applications offer interesting avenues delivering education in healthcare. This study evaluates the reliability, accuracy, comprehensibility of ChatGPT’s responses to common inquiries about therapy. Methods: An expert panel selected thirteen frequently asked based on authors’ clinical experience pain targeted review materials. Questions were prioritized prevalence consultations, relevance treatment decision-making, complexity typically required address them comprehensively. We assessed by implementing multimodal generative AI Copilot (Microsoft 365 Chat). Spanning three domains—pre-therapy, during therapy, post-therapy—each question was submitted GPT-4.0 with prompt “If you physician, how would answer asking…”. Ten physicians two non-healthcare professionals independently using Likert scale rate reliability (1–6 points), accuracy (1–3 points). Results: Overall, demonstrated high (5.2 ± 0.6) good (2.8 0.2), most answers meeting or exceeding predefined thresholds. Accuracy moderate (2.7 0.3), lower performance more technical topics like tolerance management. Conclusions: exhibit significant as supplementary tool limitations addressing highly context-specific queries underscore need ongoing refinement domain-specific training. Integrating systems into practice should involve collaboration between healthcare developers ensure safe, personalized, up-to-date

Language: Английский

---

Preference-based assistance optimization for lifting and lowering with a soft back exosuit

Science Advances, Journal Year: 2025, Volume and Issue: 11(15)

Published: April 9, 2025

Wearable robotic devices have become increasingly prevalent in both occupational and rehabilitative settings, yet their widespread adoption remains inhibited by usability barriers related to comfort, restriction, noticeable functional benefits. Acknowledging the importance of user perception this context, study explores preference-based controller optimization for a back exosuit that assists lifting. Considering high mental metabolic effort discrete motor tasks impose, we used forced-choice Bayesian Optimization approach promotes sampling efficiency leveraging domain knowledge about just differences between assistance settings. Optimizing over two control parameters, preferred settings were consistent within uniquely different participants. We discovered overall, participants asymmetric parameter configurations with more lifting than lowering assistance, preferences sensitive anthropometrics. These findings highlight potential perceptually guided wearable devices, marking step toward pervasive these systems real world.

Language: Английский

---

The linguistic feedback of tourism robots significantly influences visitors' ecotourism behaviors

Research Square (Research Square), Journal Year: 2025, Volume and Issue: unknown

Published: April 9, 2025

With the extensive application of artificial intelligence technology in tourism industry, robot-assisted has become a vital strategy for enhancing tourist experiences and promoting sustainable practices. This study aims to explore impact language feedback from robots on tourists' ecotourism behavior analyze potential mediating moderating mechanisms. Through three experimental studies, we found that robot guides with capabilities significantly improve behavior. Specifically, environmental responsibility acts as moderator between robot's behavior, indicating is more effective when tourists have higher sense responsibility. Furthermore, enhances awareness by increasing cognitive trust propensity. The findings practical implications destinations operators designing implementing intelligent services promote ecological engagement.

Language: Английский

---

Design, Modeling, and Control of a Soft Robotic Diaphragm‐Assist Device in a Respiratory Simulator

Advanced Intelligent Systems, Journal Year: 2025, Volume and Issue: unknown

Published: April 28, 2025

The diaphragm is a critical muscle for respiration, responsible up to 70% of the inspiratory effort. Standard treatment patients with severe dysfunction permanently tethering airway mechanical ventilator, which greatly impacts patient autonomy and quality life. Soft robots are ideal assist in complex biological functions, such as contraction. This article introduces soft robotic diaphragm‐assist device designed therapeutic dysfunction, moreover clinically relevant respiratory simulator proposed validation testing tool this treatment. uses fabric‐based pneumatic actuators provide targeted assistance during inhalation. A two‐step control system implemented optimize synchronization support: 1) detecting breath intention from pleural pressure signal trigger 2) regulating device's input Using simulator, demonstrated ability restore abdominal pressures significantly increased transdiaphragmatic simulated conditions dysfunction. research advances field robotics care, providing foundational platform development next‐generation devices aimed at improving life

Language: Английский

---

The linguistic feedback of tourism robots significantly influences visitors’ ecotourism behaviors

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: May 8, 2025

Language: Английский

---

Small-Data Gesture Recognition Using Bending-Sensitive Graphene Strain Sensors and Diffractive Deep Neural Networks

Modeling and Simulation, Journal Year: 2025, Volume and Issue: 14(05), P. 67 - 82

Published: Jan. 1, 2025

Language: Английский

---

ReStory: VLM-Augmentation of Social Human-Robot Interaction Datasets

Lecture notes in computer science, Journal Year: 2025, Volume and Issue: unknown, P. 457 - 466

Published: Jan. 1, 2025

Language: Английский

---