Real-world Test Research Articles

Chrysalis: decoding tissue compartments in spatial transcriptomics with archetypal analysis.

Dissecting tissue compartments in spatial transcriptomics (ST) remains challenging due to limited spatial resolution and dependence on single-cell reference data. We present Chrysalis, a computational method that rapidly uncovers tissue compartments through spatially variable gene (SVG) detection and archetypal analysis without requiring external reference data. Additionally, it offers a unique visualisation approach for swift tissue characterisation and provides access to the underlying gene expression signatures, enabling the identification of spatially and functionally distinct cellular niches. Chrysalis was evaluated through various benchmarks and validated against deconvolution, independently obtained cell type abundance data, and histopathological annotations, demonstrating superior performance compared to other algorithms on both in silico and real-world test examples. Furthermore, we showcased its versatility across different technologies, such as Visium, Visium HD, Slide-seq, and Stereo-seq.

Positioning Sensor Data Mining and Correlation Analysis Based on Multi-mode Radio Frequency Identification

Real-time positioning and sensor data mining are critical for various Internet of things (IoT) applications, but current approaches face challenges such as limited accuracy, high cost, and energy inefficiency. This paper proposes a novel fusion intelligent structure that combines radio frequency identification (RFID) technology and wireless sensor networks (WSN) to enable accurate and efficient positioning and data mining. The proposed method consists of two key components: an energy heterogeneity strategy for optimizing network energy consumption, and a data association feature analysis technique for mining sensor data. The results demonstrated that the proposed approach achieved superior positioning accuracy compared to other algorithms, with an average error of less than 0.300 under various conditions. The data detection accuracy was also high, with a maximum false detection rate of 3%. Furthermore, the proposed energy heterogeneity strategy significantly improved network energy utilization and stability. Real-world scenario testing validated the practicality of the proposed approach, with an average positioning error of less than 0.500 meters. These results validate the effectiveness of the proposed RFID-WSN fusion structure for real-time positioning and sensor data mining, providing a promising solution for IoT applications.

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.

How does turbulence intensity affect the fatigue life of composite airfoils based on existing CFD and experimental data?

This research investigates the effect of airflow turbulence intensity on the fatigue life of composite airfoil structures in aerospace engineering. Using advanced Computational Fluid Dynamics (CFD) simulations, this study provides a comprehensive analysis of how varying levels of turbulence intensity—ranging from mild (5%) to severe (30%)—impact the mechanical degradation and fatigue performance of carbon-fiber-reinforced polymers (CFRPs) used in airfoil designs. The research quantifies the relationship between turbulence levels and changes in stress distribution, highlighting critical points of fatigue crack initiation and subsequent propagation. The study includes detailed comparisons of CFD results to experimental data to validate the predictive models and discusses how localized stress fluctuations under high-intensity turbulence accelerate the onset of fatigue failure. We present significant findings that demonstrate a non-linear relationship between turbulence intensity and the reduction in fatigue life, suggesting optimal design modifications for enhanced durability. Furthermore, this paper explores current challenges in merging CFD data with real-world fatigue testing and proposes advanced techniques such as adaptive mesh refinement and hybrid simulation models to improve predictive accuracy and computational efficiency in future research.

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.

GPS-free autonomous navigation in cluttered tree rows with deep semantic segmentation

Segmentation-based autonomous navigation has recently been presented as an appealing approach to guiding robotic platforms through crop rows without requiring perfect GPS localization. Nevertheless, current techniques are restricted to situations where the distinct separation between the plants and the sky allows for the identification of the row’s center. However, tall, dense vegetation, such as high tree rows and orchards, is the primary cause of GPS signal blockage. In this study, we increase the overall robustness and adaptability of the control algorithm by extending the segmentation-based robotic guiding to those cases where canopies and branches occlude the sky and prevent the utilization of GPS and earlier approaches. An efficient Deep Neural Network architecture has been used to address semantic segmentation, performing the training with synthetic data only. Numerous vineyards and tree fields have undergone extensive testing in both simulation and real world to show the solution’s competitive benefits. The system achieved unseen results in orchards, with a Mean Average Error smaller than 9% of the maximum width of each row, improving state-of-the-art algorithms by disclosing new scenarios such as close canopy crops. The official code can be found at: https://github.com/PIC4SeR/SegMinNavigation.git.

Improving separation efficiency of various micropollutants from water by polymer-enhanced ultrafiltration using oxidized alginate featuring less viscous and low filtration resistance

Polymer-enhanced ultrafiltration (PEUF) is an economical and energy-efficient alternative using a versatile water-soluble polymer (WSP) to remove micropollutants by electrostatic interactions, allowing size exclusion through ultrafiltration (UF) membranes due to the WSP being bigger than the pores of UF membranes. However, the WSP used in PEUF is so viscous that it inevitably causes significant filtration resistance and membrane fouling, reducing filtration and energy efficiency. To overcome this problem, in this study, sodium alginate (Alg), which significantly performs in removing cationic pollutants, was oxidized using sodium periodate to produce oxidized alginate (OxAlg). The retention and water flux profiles of OxAlg for three micropollutants, methylene blue (MB), ciprofloxacin, and tetramethylammonium hydroxide, using the PEUF method were investigated in terms of pH, ionic strength, polymer and pollutant amount. A comparison between Alg and OxAlg demonstrated 1.19% to 1.8% higher MB retention rates (99.31%-99.97%) and up to 4.07 times higher water flux depending on the amount of polymer added. Furthermore, OxAlg displayed excellent retention rates of the NF level and 20-60 times higher water flux than typical NF. This outstanding OxAlg performance was mainly due to OxAlg’s properties, such as the low viscosity, flexibility and the resulting accessibility, and appropriate size from the perspective of filtration. Lastly, OxAlg was found to have the potential to surpass the existing WSP in that it showed a higher maximum retention capacity than about 560 to 1250mg/g in the real-world pH enrichment test even before the saturation.

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.