Real-world Test Research Articles

Design and Application of Fuzzy PID Controller Based on MATLAB

In an era where the development of intelligent technology is a pivotal force propelling economic advancement, enhancing production efficiency, diminishing costs, and reshaping daily life, the field of intelligent vehicle control technology has garnered significant attention among automotive researchers. The dynamics of smart cars during driving often exhibit nonlinearity and are susceptible to external environmental disturbances, such as wind resistance and road surface inequality. Traditional PID controllers have limited ability to suppress these interferences, so this study uses fuzzy PID algorithms to solve the inherent challenges in intelligent vehicle control. Through comprehensive analysis of the current landscape and technological advancements in intelligent vehicle control systems, coupled with rigorous MATLAB/Simulink simulations and real-world testing, the study showed that the overshoot of the adaptive fuzzy PID was reduced by 86% compared to the traditional PID. Consequently, it markedly enhances the precision and stability of speed control in intelligent vehicles, providing a groundbreaking perspective and practical methods for the enhancement of intelligent vehicle control systems with considerable application potential.

Nanoenabled Self-Assembled Metal-Organic Algaecides Generated Photosynthetic Inhibition and Oxidative Stress for Sustainable Food Security.

Achieving food sustainability is one of the biggest challenges in the new millennium. Plant factory cultivation systems provide an alternative for food sustainability, while they often suffer from algal blooms. The overuse of conventional algaecides has caused significant environmental pollution and concerns about food security. Here, we design a nanoenabled metal-organic algaecide that is self-assembled from natural polyphenols and two functional metal ions for providing shading effects and delivering active ingredients synergistically to suppress algal blooms. Black wattle tannin (BWT) and Fe3+ ions are utilized to develop self-assembled FeBWT nanoalgaecides with significant shading effects for decreasing light transmission (up to 97 %) and effectively inhibiting algal photosynthesis. Further, the FeBWT is functionalized with Cu2+ ions (bimetallic Cu/FeBWT) to target the algal cells and release Cu2+ ions via phenolic-mediated cell surface interactions, thus enhancing the inhibition efficiency. Importantly, the biosafety of Cu/FeBWT is demonstrated through toxicity tests on zebrafish and NIH3T3 cells. In our real-world field test, the Cu/FeBWT demonstrates high algal inhibition performance (>95 %, over 30 days), and enhances the accumulation of food nutrients in model plant lettuces. Collectively, the supramolecular metal-organic nanoalgaecide provides a promise for nanoagrochemical application and promotes food sustainability and security.

Porous PDMS-ZnO Wearable Gas Sensor for Acetone Biomarker Detection and Breath Analysis.

In response to the growing demand for global health monitoring, we report a nonintrusive health detection method using a compact, conformal wearable ultraviolet (UV)-assisted gas-sensing system based on an intrinsically flexible porous polydimethylsiloxane (PDMS)-zinc oxide (ZnO) composite layer (PPZL) for the breath acetone (BrAce) detection and breath event analysis. The enhanced acetone response is attributed to the synergistic effect of UV irradiation and the high surface area of the porous structure, which also improves the mechanical robustness. The UV-assisted wearable sensor reliably detects acetone concentrations ranging from 1 to 100 ppm at room temperature under 4.05 mW/cm2 UV intensity, even under mechanical strains such as a bending radius of 5 mm and 60% tensile strain. It accurately analyzes different breathing patterns (12-20 breaths per minute) and BrAce concentrations, maintaining a stable performance over 20 days with less than 5% signal degradation. The sensor exhibits response and recovery times of average 110-150 and 130-180 s, respectively, and maintains a consistent 3 ppm BrAce response under varying humidity levels up to 70% relative humidity, ensuring accurate detection of BrAce concentrations during real-world breath tests. Additionally, the sensor targets only specific gases, and the sensor's selectivity is not a key concern. This flexible acetone gas sensor offers a portable solution for health management and a fabrication method for designing flexible metal oxide materials.

Deployment of Artificial Intelligence in Radiology: Strategies for Success.

Radiology, as a highly technical and information-rich medical specialty, is well-suited for artificial intelligence (AI) product development, and many FDA-cleared AI medical devices are authorized for uses within the specialty. In this Clinical Perspective, we discuss the deployment of AI tools in radiology, exploring regulatory processes, the need for transparency, and other practical challenges. We further highlight the importance of rigorous validation, real-world testing, seamless workflow integration, and end-user education. We emphasize the role for continuous feedback and robust monitoring processes, to guide AI tools' adaptation and help ensure sustained performance. Traditional standalone and alternative platform-based approaches to radiology AI implementation are considered. The presented strategies will help achieve successful deployment and fully realize AI's potential benefits in radiology.

Kinematic Constrained RRT Algorithm with Post Waypoint Shift for the Shortest Path Planning of Wheeled Mobile Robots

This paper presents a rapidly exploring random tree (RRT) algorithm with an effective post waypoint shift, which is suitable for the path planning of a wheeled mobile robot under kinematic constraints. In the growth of the exploring tree, the nearest node that satisfies the kinematic constraints is selected as the parent node. Once the distance between the new node and the target is within a certain threshold, the tree growth stops and a target connection based on minimum turning radius arc is proposed to generate an initial complete random path. The most significant difference from traditional RRT-based methods is that the proposed method optimizes the path based on Dubins curves through a post waypoint shift after a random path is generated, rather than through parent node selection and rewiring during the exploring tree growth. Then, it is proved that the method can obtain an optimal path in terms of the shortest length. The optimized path has good convergence and almost does not depend on the state of the initial random path. The comparative test results show that the proposed method has significant advantages over traditional RRT-based methods in terms of the sampling point number, the tree node number, and the path node number. Subsequently, an efficient method is further proposed to avoid unknown obstacles, which utilizes the original path information and thus effectively improves the new path planning efficiency. Simulations and real-world tests are carried out to demonstrate the effectiveness of this method.

Cost-Effective Power Management for Smart Homes: Innovative Scheduling Techniques and Integrating Battery Optimization in 6G Networks

This paper presents an Optimal Power Management System (OPMS) for smart homes in 6G environments, which are designed to enhance the sustainability of Green Internet of Everything (GIoT) applications. The system employs a brute-force search using an exact solution to identify the optimal decision for adapting power consumption to renewable power availability. Key techniques, including priority-based allocation, time-shifting, quality degradation, battery utilization and service rejection, will be adopted. Given the NP-hard nature of this problem, the brute-force approach is feasible for smaller scenarios but sets the stage for future heuristic methods in large-scale applications like smart cities. The OPMS, deployed on Multi-Access Edge Computing (MEC) nodes, integrates a novel demand response (DR) strategy to manage real-time power use effectively. Synthetic data tests achieved a 100% acceptance rate with zero reliance on non-renewable power, while real-world tests reduced non-renewable power consumption by over 90%, demonstrating the system’s flexibility. These results provide a foundation for further AI-based heuristics optimization techniques to improve scalability and power efficiency in broader smart city deployments.

Facilitating the transfer and implementation of practices across health and care systems

Abstract The THCS partnership has developed the initial draft of a framework designed to facilitate the transfer and implementation of solutions across health and care systems. During the workshop, we will present this framework along with the preliminary results of its real-world testing in transfer and implementation activities. The goal of this presentation is to gather feedback on the framework and generate ideas for its further development. Choosing to transfer existing solutions rather than developing new ones can offer several advantages in terms of efficiency, reliability, and cost-effectiveness. Adopting existing solutions can save time and reduce development costs significantly. The THCS framework aims to support, promote, and accelerate the transfer and implementation of solutions across health and care systems. The THCS framework is primarily targeted at individuals involved in planning, coordinating, and executing development activities within health and care organizations. This framework includes: 1) Paradigmatic commitments that underpin its understanding of development activities, transferability, and implementation; 2) Principles for conducting the activities of transferring and adapting solutions developed elsewhere; 3) Guidelines for describing original solutions; and 4) Key development tasks that outline the necessary steps for transferring, adapting, and implementing solutions developed elsewhere.

Next-generation fall detection: harnessing human pose estimation and transformer technology

ABSTRACT Elderly falls are occurring at an alarming rate, with significant health risks for seniors. Current fall detection systems often lack accuracy, efficacy, and privacy considerations. This study examines three leading human pose estimation frameworks combined with transformer deep learning models to develop a lightweight, privacy-preserving fall detection system. Key features include: 1) It runs on low-power devices like Raspberry Pis; 2) It monitors seniors passively, without requiring active participation; 3) It can be deployed in any residential or senior care setting; 4) It does not rely on wearables; and 5) All processing occurs locally, ensuring privacy with only fall alerts transmitted to caregivers. In real-world tests, the model achieved 95.24% sensitivity, 89.80% specificity, 98.00% accuracy, a 90.91% F1 score, and 95.24% precision, highlighting its effectiveness in detecting falls among the elderly while maintaining privacy and security.

Enhanced Diabetes Detection and Blood Glucose Prediction Using TinyML-Integrated E-Nose and Breath Analysis: A Novel Approach Combining Synthetic and Real-World Data

Diabetes mellitus, a chronic condition affecting millions worldwide, necessitates continuous monitoring of blood glucose level (BGL). The increasing prevalence of diabetes has driven the development of non-invasive methods, such as electronic noses (e-noses), for analyzing exhaled breath and detecting biomarkers in volatile organic compounds (VOCs). Effective machine learning models require extensive patient data to ensure accurate BGL predictions, but previous studies have been limited by small sample sizes. This study addresses this limitation by employing conditional generative adversarial networks (CTGAN) to generate synthetic data from real-world tests involving 29 healthy and 29 diabetic participants, resulting in over 14,000 new synthetic samples. These data were used to validate machine learning models for diabetes detection and BGL prediction, integrated into a Tiny Machine Learning (TinyML) e-nose system for real-time analysis. The proposed models achieved an 86% accuracy in BGL identification using LightGBM (Light Gradient Boosting Machine) and a 94.14% accuracy in diabetes detection using Random Forest. These results demonstrate the efficacy of enhancing machine learning models with both real and synthetic data, particularly in non-invasive systems integrating e-noses with TinyML. This study signifies a major advancement in non-invasive diabetes monitoring, underscoring the transformative potential of TinyML-powered e-nose systems in healthcare applications.

Identifying vehicle characteristic target based on subjective ratings from drivers

In virtual tire development, defining vehicle characteristic target is crucial to achieving the desired vehicle performance with the equipped tires. Vehicle performance is generally evaluated through subjective ratings by skilled drivers following SAE J1441 guidelines, as well as the objective performance metrics obtained via vehicle dynamics analysis. However, due to the scarcity and bias in real-world testing dataset, the vehicle characteristic target cannot be determined definitively. To address this issue, we propose a recommendation system that searches the unexplored vehicle characteristic domains. This suggested method provides virtual subjective ratings to enrich the limited real-world dataset from the skilled drivers. Moreover, we highlight the correlation between subjective and objective data using vehicle and tire dynamics simulation software. Based on this augmented data, we predict the vehicle characteristic target according to the subjective rating requirements. The proposed approach was validated through various experiments involving skilled drivers and various vehicle-tire combinations, showing 91.26% to 96.2% consistency in generated steering parameter domains. Domains of stability parameters show that one fewer domain was generated by a conservative driver compared to more lenient driver, which confirms the robustness of the proposed approach in accommodating individual driver preferences.

CMDN: Pre-Trained Visual Representations Boost Adversarial Robustness for UAV Tracking

Visual object tracking is widely adopted to unmanned aerial vehicle (UAV)-related applications, which demand reliable tracking precision and real-time performance. However, UAV trackers are highly susceptible to adversarial attacks, while research on developing effective adversarial defense methods for UAV tracking remains limited. To tackle these challenges, we propose CMDN, a novel pre-processing defense network that effectively purifies adversarial perturbations by reconstructing video frames. This network learns robust visual representations from video frames, guided by meaningful features from both the search region and the template. Comprehensive experiments on three benchmarks demonstrate that CMDN is capable of enhancing a UAV tracker’s adversarial robustness in both adaptive and non-adaptive attack scenarios. In addition, CMDN maintains stable defense effectiveness when transferred to heterogeneous trackers. Real-world tests on the UAV platform also validate its reliable defense effectiveness and real-time performance, with CMDN achieving 27 FPS on NVIDIA Jetson Orin 16 GB (25 W mode).

Bidirectional Planning for Autonomous Driving Framework with Large Language Model.

Autonomous navigation systems often struggle in dynamic, complex environments due to challenges in safety, intent prediction, and strategic planning. Traditional methods are limited by rigid architectures and inadequate safety mechanisms, reducing adaptability to unpredictable scenarios. We propose SafeMod, a novel framework enhancing safety in autonomous driving by improving decision-making and scenario management. SafeMod features a bidirectional planning structure with two components: forward planning and backward planning. Forward planning predicts surrounding agents' behavior using text-based environment descriptions and reasoning via large language models, generating action predictions. These are embedded into a transformer-based planner that integrates text and image data to produce feasible driving trajectories. Backward planning refines these trajectories using policy and value functions learned through Actor-Critic-based reinforcement learning, selecting optimal actions based on probability distributions. Experiments on CARLA and nuScenes benchmarks demonstrate that SafeMod outperforms recent planning systems in both real-world and simulation testing, significantly improving safety and decision-making. This underscores SafeMod's potential to effectively integrate safety considerations and decision-making in autonomous driving.

A Brain Network Analysis Model for Motion Sickness in Electric Vehicles Based on EEG and fNIRS Signal Fusion

Motion sickness is a common issue in electric vehicles, significantly impacting passenger comfort. This study aims to develop a functional brain network analysis model by integrating electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) signals to evaluate motion sickness symptoms. During real-world testing with the Feifan F7 series of new energy-electric vehicles from SAIC Motor Corp, data were collected from 32 participants. The EEG signals were divided into four frequency bands: delta-range, theta-range, alpha-range, and beta-range, and brain oxygenation variation was calculated from the fNIRS signals. Functional connectivity between brain regions was measured to construct functional brain network models for motion sickness analysis. A motion sickness detection model was developed using a graph convolutional network (GCN) to integrate EEG and fNIRS data. Our results show significant differences in brain functional connectivity between participants in motion and non-motion sickness states. The model that combined fNIRS data with high-frequency EEG signals achieved the best performance, improving the F1 score by 11.4% compared to using EEG data alone and by 8.2% compared to using fNIRS data alone. These results highlight the effectiveness of integrating EEG and fNIRS signals using GCN for motion sickness detection. They demonstrate the model’s superiority over single-modality approaches, showcasing its potential for real-world applications in electric vehicles.

Investigating constraint programming and hybrid methods for real world industrial test laboratory scheduling

AbstractIn this paper we deal with a complex real world scheduling problem closely related to the well-known Resource-Constrained Project Scheduling Problem (RCPSP). The problem concerns industrial test laboratories in which a large number of tests are performed by qualified personnel using specialised equipment, while respecting deadlines and other constraints. We present different constraint programming models and search strategies for this problem. Furthermore, we propose a Very Large Neighborhood Search approach based on our CP methods. Our models are evaluated using CP solvers and a MIP solver both on real-world test laboratory data and on a set of generated instances of different sizes based on the real-world data. Further, we compare the exact approaches with VLNS and a Simulated Annealing heuristic. We could find feasible solutions for all instances and several optimal solutions and we show that using VLNS we can improve upon the results of the other approaches.

Exploring Automated Assertion Generation via Large Language Models

Unit testing aims to validate the correctness of software system units and has become an essential practice in software development and maintenance. However, it is incredibly time-consuming and labor-intensive for testing experts to write unit test cases manually, including test inputs ( i.e., prefixes) and test oracles ( i.e., assertions). Very recently, some techniques have been proposed to apply Large Language Models (LLMs) to generate unit assertions and have proven the potential in reducing manual testing efforts. However, there has been no systematic comparison of the effectiveness of these LLMs, and their pros and cons remain unexplored. To bridge this gap, we perform the first extensive study on applying various LLMs to automated assertion generation. The experimental results on two independent datasets show that studied LLMs outperform six state-of-the-art techniques with a prediction accuracy of 51.82% \(\sim\) 58.71% and 38.72% \(\sim\) 48.19%. The improvements achieve 29.60% and 12.47% on average. Besides, as a representative LLM, CodeT5 consistently outperforms all studied LLMs and all baselines on both datasets, with an average improvement of 13.85% and 26.64%, respectively. We also explore the performance of generated assertions in detecting real-world bugs, and find LLMs are able to detect 32 bugs from Defects4J on average, with an improvement of 52.38% against the most recent approach EditAS . Inspired by the findings, we construct a simplistic retrieval-and-repair-enhanced LLM-based approach by transforming the assertion generation problem into a program repair task for retrieved similar assertions. Surprisingly, such a simplistic approach can further improve the prediction accuracy of LLMs by 9.40% on average, leading to new records on both datasets. Besides, we provide additional discussions from different aspects ( e.g., the impact of assertion types and test lengths) to illustrate the capacity and limitations of LLM-based approaches. Finally, we further pinpoint various practical guidelines ( e.g., the improvement of multiple candidate assertions) for advanced LLM-based assertion generation in the near future. Overall, our work underscores the promising future of adopting off-the-shelf LLMs to generate accurate and meaningful assertions in real-world test cases and reduce the manual efforts of unit testing experts in practical scenarios.

A Fuzzy Pure Pursuit for Autonomous UGVs Based on Model Predictive Control and Whole-Body Motion Control

In this paper, we propose an adaptive fuzzy pure pursuit trajectory tracking algorithm for autonomous unmanned ground vehicles (UGVs), addressing the challenges of accurate and stable navigation in complex environments. Traditional pure pursuit methods with fixed look-ahead distances struggle to maintain precision in dynamic and uneven terrains. Our approach uniquely integrates a fuzzy control algorithm that allows for real-time adjustments of the look-ahead distance based on environmental feedback, thereby enhancing tracking accuracy and smoothness. Additionally, we combine this with model predictive control (MPC) and whole-body motion control (WBC), where MPC forecasts future states and optimally adjusts control actions, while WBC ensures coordinated motion of the UGV, maintaining balance and stability, especially in rough terrains. This integration not only improves responsiveness to changing conditions but also enables dynamic balance adjustments during movement. The proposed algorithm was validated through simulations in Gazebo and real-world experiments on physical platforms. In real-world tests, our algorithm reduced the average trajectory tracking error by 45% and the standard deviation by nearly 50%, significantly improving stability and accuracy compared to traditional methods.

Proposed project to retrofit an orchestra pit with acoustic metadiffusers

There is a pressing need for effective acoustic diffusion treatment with a minimal thickness profile, in particular for the retrofitting of orchestra pits. Sound can reach dangerously high levels in these environments, but highly absorptive boundaries in an orchestra pit are usually not desirable, among other reasons because it compromises ensemble conditions. Implementing diffusion retroactively would be difficult, as there is often little space for such treatment. Acoustic metadiffusers offer a promising solution to this, but lack real-world testing and scalable production. This paper describes this knowledge gap, with a view to ultimately creating a target sound field optimised for musician's performance and safety. This would be made possible by the inherent flexibility of metamaterial design concepts, pointing towards the future development of metadiffusers, specifically as regards to their practical implementation. The aim is to be able to soon fill this knowledge gap, contributing to advancing the understanding of acoustic diffusion treatments. An early stage study will be the assessment of the differences between near and far fields produced by such scattering surfaces in order to be sure of the suitability of ultra thin diffusers for use as retrofitted treatment.

Real-world molecular testing patterns in primary advanced or recurrent endometrial cancer (pA/rEC) in the US.

395 Background: Targeted therapy can improve outcomes in women with pA/rEC, but real-world biomarker testing rates are unknown. This study estimated the real-world proportion of patients receiving biomarker testing (within ≤6 months of advanced/recurrent diagnosis) and characterized testing according to sociodemographic and clinical characteristics. Methods: We used the US Flatiron Health electronic health record–derived deidentified database. Records from 1/1/2013 to 8/31/2023 for women ≥18 years old with advanced/recurrent EC were searched to identify testing for DNA mismatch repair/microsatellite instability (MMR/MSI), HER2, and estrogen or progesterone receptors (ER/PR); a subsample dataset from 4/1/2013 to 11/30/2022 was analyzed for additional biomarkers. The subsample has information on additional biomarker testing and was used to evaluate the frequency of testing for these biomarkers. Testing rates were evaluated using descriptive statistics; characteristics associated with testing were identified by multivariate logistic regression. Results: Among persons meeting eligibility criteria (n=2982), the mean age was 65 years; the majority were non-Hispanic White (56%), had commercial insurance (79%), and received care in a community setting (73%). The subsample (n=509) had similar characteristics to the full cohort. Between 2013-2022, 73% (n=2165) of patients received testing for any biomarker. Testing rates for individual biomarkers are shown in the Table. From 2013 to 2021, testing increased for MMR/MSI (17% to 81%), ER/PR (45% to 62%), and HER2 (15% to 43%). The likelihood of testing was higher among patients with primary advanced EC (OR, 1.45; 95% CI, 1.03-2.06), endometrioid carcinoma histology (1.39; 1.01-1.93), commercial insurance (1.51; 1.18-1.93), at an academic facility (1.70; 1.37-2.11), and with no prior surgery (2.29; 1.83-2.86) relative to other attributes. Conclusions: Molecular testing has increased over time, indicating a continuous trend toward personalized treatment decisions. Several factors associated with an increased likelihood of biomarker testing were identified. Understanding these factors can inform approaches to increase access to molecular testing and increase testing rates. Biomarker testing rates, 2013-2022. Biomarker, n (%) 2013 2021 Overall MMR/MSI a 35 (15) 238 (80) 1604 (54) HER2 a 31 (14) 121 (41) 612 (21) ER/PR a 99 (43) 177 (59) 1465 (49) p53/ TP53 b 13 (36) 31 (74) 260 (51) TMB b 3 (8) 14 (33) 91 (18) CTNNB1 b 4 (11) 12 (29) 88 (17) ARID1A b 4 (11) 15 (36) 91 (18) CDK4/6 b 5 (14) 14 (33) 110 (22) POLE b 4 (11) 17 (40) 110 (22) ARID1A, AT-rich interactive domain-containing protein 1A; CDK4/6, cyclin-dependent kinases 4 and 6; CTNNB1, catenin beta-1; POLE, polymerase-epsilon; TMB, tumor mutation burden. a 2013, n=228; 2021, n=298; overall, n=2982. b Rates from subsample dataset (4/1/2013 to 11/30/2022); 2013, n=36; 2021, n=42; overall, n=509.

Software Architecture Design of ASV Rybitwa: Development of an Autonomous Surface Vehicle for Dynamic Navigation and Task Execution

Abstract This paper introduces the software design of an Autonomous Surface Vehicle (ASV) named ASV Rybitwa. It was designed as an easily transportable platform capable of autonomous navigation and performing tasks during the RoboBoat 2024 competition, with emphasis on its modularity, generality and extendibility. The paper presents a software architecture for a small autonomous surface vehicle using novel tools that provide easy system integration and expansion. To meet such requirements, a generic control box connecting an autopilot (PX4) and a onboard computer (NVIDIA Jetson Nano) was developed so as to host the Robot Operating System 2 (ROS2) and to interact with sensors and actuators. Computer vision from three Oak-D cameras, equipped with AI algorithm support (YOLOv8), was used for navigation and obstacle avoidance. The decision-making system was designed using behavioural trees and computer vision, allowing the vehicle’s capabilities to be adapted to the needs of the current tasks and mission. In addition, an Omni X propulsion system was proposed, providing full holonomy and enhancing dynamic positioning and navigation capabilities in complex navigational conditions. In addition this paper describes lessons learned from ASV Rybitwa’s real-world testing during the aforementioned competition.

IPCT-Net: Parallel information bottleneck modality fusion network for obstructive sleep apnea diagnosis

Obstructive sleep apnea (OSA) is a common sleep breathing disorder and timely diagnosis helps to avoid the serious medical expenses caused by related complications. Existing deep learning (DL)-based methods primarily focus on single-modal models, which cannot fully mine task-related representations. This paper develops a modality fusion representation enhancement (MFRE) framework adaptable to flexible modality fusion types with the objective of improving OSA diagnostic performance, and providing quantitative evidence for clinical diagnostic modality selection. The proposed parallel information bottleneck modality fusion network (IPCT-Net) can extract local-global multi-view representations and eliminate redundant information in modality fusion representations through branch sharing mechanisms. We utilize large-scale real-world home sleep apnea test (HSAT) multimodal data to comprehensively evaluate relevant modality fusion types. Extensive experiments demonstrate that the proposed method significantly outperforms existing methods in terms of participant numbers and OSA diagnostic performance. The proposed MFRE framework delves into modality fusion in OSA diagnosis and contributes to enhancing the screening performance of artificial intelligence (AI)-assisted diagnosis for OSA.