Hasil untuk "Engineering machinery, tools, and implements"

Aldeida Aleti, Baishakhi Ray, Rashina Hoda et al.

With the rapid rise of AI coding agents, the fundamental premise of what it means to be a software engineer is in question. In this vision paper, we re-examine what it means for an AI agent to be considered a software engineer and then critically think about what makes such an agent trustworthy. \textit{Grounded} in established definitions of software engineering (SE) and informed by recent research on agentic AI systems, we conceptualise AI software engineers as participants in human-AI SE teams composed of human software engineers and AI models and tools, and we distinguish trustworthiness as a key property of these systems and actors rather than a subjective human attitude. Based on historical perspectives and emerging visions, we identify key dimensions that contribute to the trustworthiness of AI software engineers, spanning technical quality, transparency and accountability, epistemic humility, and societal and ethical alignment. We further discuss how trustworthiness can be evaluated and demonstrated, highlighting a fundamental trust measurement gap: not everything that matters for trust can be easily measured. Finally, we outline implications for the design, evaluation, and governance of AI SE systems, advocating for an ethics-by-design approach to enable appropriate trust in future human-AI SE teams.

Jiahong Xiang, Wenxiao He, Xihua Wang et al.

The Rust programming language presents a steep learning curve and significant coding challenges, making the automation of issue resolution essential for its broader adoption. Recently, LLM-powered code agents have shown remarkable success in resolving complex software engineering tasks, yet their application to Rust has been limited by the absence of a large-scale, repository-level benchmark. To bridge this gap, we introduce Rust-SWE-bench, a benchmark comprising 500 real-world, repository-level software engineering tasks from 34 diverse and popular Rust repositories. We then perform a comprehensive study on Rust-SWE-bench with four representative agents and four state-of-the-art LLMs to establish a foundational understanding of their capabilities and limitations in the Rust ecosystem. Our extensive study reveals that while ReAct-style agents are promising, i.e., resolving up to 21.2% of issues, they are limited by two primary challenges: comprehending repository-wide code structure and complying with Rust's strict type and trait semantics. We also find that issue reproduction is rather critical for task resolution. Inspired by these findings, we propose RUSTFORGER, a novel agentic approach that integrates an automated test environment setup with a Rust metaprogramming-driven dynamic tracing strategy to facilitate reliable issue reproduction and dynamic analysis. The evaluation shows that RUSTFORGER using Claude-Sonnet-3.7 significantly outperforms all baselines, resolving 28.6% of tasks on Rust-SWE-bench, i.e., a 34.9% improvement over the strongest baseline, and, in aggregate, uniquely solves 46 tasks that no other agent could solve across all adopted advanced LLMs.

Gogulamudi Pradeep Reddy, Duppala Rohan, Shaik Mohammed Abdul Kareem et al.

Alzheimer’s disease (AD), an intense neurological illness, severely impacts memory, behavior, and personality, posing a growing concern worldwide due to the aging population. Early and accurate detection is crucial as it enables preventive measures. However, current diagnostic methods are often inaccurate in identifying the disease in its early stages. Although deep learning-based bioimaging has shown promising results in medical image classification, challenges remain in achieving the highest accuracy for detecting AD. Existing approaches, such as ResNet50, VGG19, InceptionV3, and AlexNet have shown potential, but they often lack reliability and accuracy due to several issues. To address these gaps, this paper suggests a novel bioimaging technique by developing a custom Convolutional Neural Network (CNN) model for detecting AD. This model is designed with optimized layers to enhance feature extraction from medical images. The experiment’s first phase involved the construction of the custom CNN structure with three max-pooling layers, three convolutional layers, two dense layers, and one flattened layer. The Adam optimizer and categorical cross-entropy were adopted to compile the model. The model’s training was carried out on 100 epochs with the patience set to 10 epochs. The second phase involved augmentation of the dataset images and adding a dropout layer to the custom CNN model. Moreover, fine-tuned hyperparameters and advanced regularization methods were integrated to prevent overfitting. A comparative analysis of the proposed model with conventional models was performed on the dataset both before and after the data augmentation. The results validate that the proposed custom CNN model significantly overtakes pre-existing models, achieving the highest validation accuracy of 99.53% after data augmentation while maintaining the lowest validation loss of 0.0238. Its precision, recall, and F1 score remained consistently high across all classes, with perfect scores for the Moderate Demented and Non-Demented categories after augmentation, indicating superior classification capability.

Yuzuki ENDO, Yohei MICHITSUJI, Itsuro ARAI et al.

Monitoring wheel-rail contact forces is essential for ensuring railway operational safety. The derailment coefficient, defined as the ratio of lateral force to wheel load, is a critical parameter for assessing the risk of flange climb derailment. The PQ monitoring bogie has been developed to monitor this coefficient, with wheel load estimation currently based on the vertical displacement of the primary suspension. However, this method does not account for factors such as lateral forces on the wheelset and the dynamic geometrical relationship between the wheelset and wheel-rail contact points, leading to estimation inaccuracies. These inaccuracies are particularly pronounced on sharp curves due to stronger lateral force effects. This study proposes an enhanced method for wheel load estimation in PQ monitoring bogies by utilizing the bogie’s measurement capabilities. The proposed method is formulated by solving the quasi-static equation of equilibrium on curved track sections, incorporating the effects of lateral forces and dynamic variations in the lateral distance between the wheelset and the wheel-rail contact points. Since some input variables required for the proposed method cannot be directly measured, estimation techniques using lookup tables referenced by the train’s position along the track are also introduced. The accuracy of both the conventional and proposed methods is evaluated through multi-body dynamics simulations and on-track testing. Overall, simulation and test results demonstrate that the proposed method significantly improves wheel load estimation accuracy, especially on sharp curves, compared to the conventional approach.

Abhik Roychoudhury, Corina Pasareanu, Michael Pradel et al.

Large Language Models (LLMs) have shown surprising proficiency in generating code snippets, promising to automate large parts of software engineering via artificial intelligence (AI). We argue that successfully deploying AI software engineers requires a level of trust equal to or even greater than the trust established by human-driven software engineering practices. The recent trend toward LLM agents offers a path toward integrating the power of LLMs to create new code with the power of analysis tools to increase trust in the code. This opinion piece comments on whether LLM agents could dominate software engineering workflows in the future and whether the focus of programming will shift from programming at scale to programming with trust.

Daniel N. Wilke

This paper introduces Design for Sensing and Digitalisation (DSD), a new engineering design paradigm that integrates sensor technology for digitisation and digitalisation from the earliest stages of the design process. Unlike traditional methodologies that treat sensing as an afterthought, DSD emphasises sensor integration, signal path optimisation, and real-time data utilisation as core design principles. The paper outlines DSD's key principles, discusses its role in enabling digital twin technology, and argues for its importance in modern engineering education. By adopting DSD, engineers can create more intelligent and adaptable systems that leverage real-time data for continuous design iteration, operational optimisation and data-driven predictive maintenance.

Muhammad Tayyab Khan, Zane Yong, Lequn Chen et al.

Accurate extraction of key information from 2D engineering drawings is crucial for high-precision manufacturing. Manual extraction is slow and labor-intensive, while traditional Optical Character Recognition (OCR) techniques often struggle with complex layouts and overlapping symbols, resulting in unstructured outputs. To address these challenges, this paper proposes a novel hybrid deep learning framework for structured information extraction by integrating an Oriented Bounding Box (OBB) detection model with a transformer-based document parsing model (Donut). An in-house annotated dataset is used to train YOLOv11 for detecting nine key categories: Geometric Dimensioning and Tolerancing (GD&T), General Tolerances, Measures, Materials, Notes, Radii, Surface Roughness, Threads, and Title Blocks. Detected OBBs are cropped into images and labeled to fine-tune Donut for structured JSON output. Fine-tuning strategies include a single model trained across all categories and category-specific models. Results show that the single model consistently outperforms category-specific ones across all evaluation metrics, achieving higher precision (94.77% for GD&T), recall (100% for most categories), and F1 score (97.3%), while reducing hallucinations (5.23%). The proposed framework improves accuracy, reduces manual effort, and supports scalable deployment in precision-driven industries.

Thiago Barradas, Aline Paes, Vânia de Oliveira Neves

The effective execution of tests for REST APIs remains a considerable challenge for development teams, driven by the inherent complexity of distributed systems, the multitude of possible scenarios, and the limited time available for test design. Exhaustive testing of all input combinations is impractical, often resulting in undetected failures, high manual effort, and limited test coverage. To address these issues, we introduce RestTSLLM, an approach that uses Test Specification Language (TSL) in conjunction with Large Language Models (LLMs) to automate the generation of test cases for REST APIs. The approach targets two core challenges: the creation of test scenarios and the definition of appropriate input data. The proposed solution integrates prompt engineering techniques with an automated pipeline to evaluate various LLMs on their ability to generate tests from OpenAPI specifications. The evaluation focused on metrics such as success rate, test coverage, and mutation score, enabling a systematic comparison of model performance. The results indicate that the best-performing LLMs - Claude 3.5 Sonnet (Anthropic), Deepseek R1 (Deepseek), Qwen 2.5 32b (Alibaba), and Sabia 3 (Maritaca) - consistently produced robust and contextually coherent REST API tests. Among them, Claude 3.5 Sonnet outperformed all other models across every metric, emerging in this study as the most suitable model for this task. These findings highlight the potential of LLMs to automate the generation of tests based on API specifications.

Pallav Jain, Yuvraj Agrawal, Ashutosh Nigam et al.

In modern, large-scale software development, engineering leaders face the significant challenge of gaining a holistic and data-driven view of team performance and system health. Data is often siloed across numerous disparate tools, making manual report generation time-consuming and prone to inconsistencies. This paper presents the architecture and implementation of a centralized framework designed to provide near-real-time visibility into developer experience (DevEx) and Key Performance Indicator (KPI) metrics for a software ecosystem. By aggregating data from various internal tools and platforms, the system computes and visualizes metrics across key areas such as Developer Productivity, Quality, and Operational Efficiency. The architecture features a cron-based data ingestion layer, a dual-schema data storage approach, a processing engine for metric pre-computation, a proactive alerting system, and utilizes the open-source BI tool Metabase for visualization, all secured with role-based access control (RBAC). The implementation resulted in a significant reduction in manual reporting efforts, saving an estimated 20 person-hours per week, and enabled faster, data-driven bottleneck identification. Finally, we evaluate the system's scalability and discuss its trade-offs, positioning it as a valuable contribution to engineering intelligence platforms.

Hana Pačaiová, Renata Turisová, Juraj Glatz et al.

Machine safety is not only a prerequisite for successful production, but also the foundation for sustainability and growth of any manufacturing organisation. The latest approaches in this rapidly developing field are the integration of effective risk management tools and strategies into occupational health and safety (OHS) systems. In this article, using a specific example from practice, we will show how using multi-criteria decision making (AHP) support Machinery Safety Decision Making (MSDM) from the point of reducing losses. Using Classification and Regression Tree Analysis (CART), we estimated the efficiency, cost-effectiveness and thus the sustainability level of the relevant safety measures. These were proposed risk reduction measures that typically raised uncertainty among managers regarding the estimation of cost-effectiveness. The advantage of application decision trees approach is possibility to identify and establish relatively homogeneous groups of undesirable events and their impact on the organisation's objectives. A comprehensive model has been developed to support management decision making in manufacturing organizations in implementing and improving safety measures in line with manufacturing sustainability goals.

Ruzimurod Sattorovich Jurayev, Bekzod Ravshan ugli Eshkulov, Navruzbek Toyir ugli Kakhkhorov

This article examines the process of digesting phosphorites in an acidic solution to create complicated and mixed fertilizers. This study focuses on improving the nutritional content of phosphorus fertilizers by utilizing mineral acids, such as phosphoric, nitric, and sulfuric acids. In particular, the research looks into how phosphate raw materials, such as poor-quality phosphorites from the Central Kyzylkum region, are treated to create fertilizers that are nitrogen-phosphorous (NPh), phosphorpotassium (PhP), and nitrogen-phosphorus-potassium (NPhP). Phosphorites are broken down by nitric acid in the process, yielding calcium nitrate salts and other byproducts that can be treated further. A scanning electron microscope was used in the investigation to examine the fertilizers’ surface microstructure. The findings emphasize how crucial it is to clean and neutralize phosphorus fertilizers in order to enhance product quality and lessen the amount of undesirable salts. The results offer insightful information about enhancing fertilizer output and raising agricultural productivity.

Liudmila Gerasimova-Meigal, Alexander Meigal, Vyacheslav Dimitrov et al.

The study aimed at obtaining a precise view of the modification of heart rate variability (HRV) and respiratory rate with the help of “smart clothes” (the Hexoskin Smart Shirt, Hexoskin Smart Sensors & AI, Montreal, QC, Canada) during a 45 min session of “dry” immersion (DI), which is considered a model of Earth-based weightlessness. Eight healthy subjects aged 19 to 21 years participated in the study. Hexoskin Smart Shirt provided a .wav sound file. For analysis, the ecg_peaks function of the neurokit2 library was applied. HRV parameters were calculated within 5 min segments with the help of the pyHRV toolbox. Time-domain (HR and SDNN) and frequency-domain (HF, LF, and VLF) HRV parameters, sample, and approximate entropy were calculated. Thus, the “smart cloth” technology appears as a reliable telemetric instrument to monitor cardiac and respiratory regulation during the DI session.

Claudia Angélica Rivera-Romero, Elvia Ruth Palacios-Hernández, Osbaldo Vite-Chávez et al.

Constant monitoring is necessary for powdery mildew prevention in field crops because, as a fungal disease, it modifies the green pigments of the leaves and is responsible for production losses. Therefore, there is a need for solutions that assure early disease detection to realize proactive control and management of the disease. The methodology currently used for the identification of powdery mildew disease uses RGB leaf images to detect damage levels. In the early stage of the disease, no symptoms are visible, but this is a point at which the disease can be controlled before the symptoms appear. This study proposes the implementation of a support vector machine to identify powdery mildew on cucurbit plants using RGB images and color transformations. First, we use an image dataset that provides photos covering five growing seasons in different locations and under natural light conditions. Twenty-two texture descriptors using the gray-level co-occurrence matrix result are calculated as the main features. The proposed damage levels are ’healthy leaves’, ’leaves in the fungal germination phase’, ’leaves with first symptoms’, and ’diseased leaves’. The implementation reveals that the accuracy in the L * a * b color space is higher than that when using the combined components, with an accuracy value of 94% and kappa Cohen of 0.7638.

Olivier Piller, Sylvan Elhay, Jochen W. Deuerlein et al.

First-order approximations have been used with some success for criticality analysis; sensitivity analysis of physical networks, such as water distribution systems; and uncertainty propagation of model parameters. Certain limitations have been reported regarding the accuracy of the results, particularly when non-linearity is dominant. In this paper, we show how to efficiently derive the first- and second-order sensitivities with respect to variation in their parameters. This makes it possible to improve the first-order estimate when necessary. The method is illustrated on a small example system.

Sheng Wu, Haotian Zhu, Enrui Bai et al.

The iron–chromium redox flow battery (ICRFB) has a wide range of applications in the field of new energy storage due to its low cost and environmental protection. Graphite felt (GF) is often used as the electrode. However, the hydrophilicity and electrochemical activity of GF are poor, and its reaction reversibility to Cr³⁺/Cr²⁺ is worse than Fe²⁺/Fe³⁺, which leads to the hydrogen evolution side reaction of the negative electrode and affects the efficiency of the battery. In this study, the optimal composite modified GF (Bi-Bio-GF-O) electrode was prepared by using the optimal pomelo peel powder modified GF (Bio-GF-O) as the matrix and further introducing Bi³⁺. The electrochemical performance and material characterization of the modified electrode were analyzed. In addition, using Bio-GF-O as the positive electrode and Bi-Bio-GF-O as the negative electrode, the high efficiency of ICRFB is realized, and the capacity attenuation is minimal. When the current density is 100 mA·cm⁻², after 100 cycles, the coulomb efficiency (CE), voltage efficiency (VE), and energy efficiency (EE) were 97.83%, 85.21%, and 83.36%, respectively. In this paper, the use of pomelo peel powder and Bi³⁺ composite modified GF not only promotes the electrochemical performance and reaction reversibility of the negative electrode but also improves the performance of ICRFB. Moreover, the cost of the method is controllable, and the process is simple.

Eric Raymond Rodrigues, Sergio Esteban-Romero, Manuel Gil-Martín et al.

This paper describes the development of a Human Activity Recognition (HAR) system based on deep learning for classifying full-body activities using inertial signals. The HAR system is divided into several modules: a preprocessing module for extracting relevant features from the inertial signals window-by-window, a machine learning algorithm for classifying the windows and a post-processing module for integrating the information along several windows. Regarding the preprocessing module, several transformations are implemented and evaluated. For the ML module, several algorithms are evaluated, including several deep learning architectures. This evaluation has been carried out over the HARTH dataset. This public dataset contains recordings from 22 participants wearing two 3-axial Axivity AX3 accelerometers for 2 h in a free-living setting. Not all the subjects completed the whole session. Sixteen different activities were recorded and annotated accordingly. This paper describes the fine-tuning process of several machine learning algorithms and analyses their performance with different sets of activities. The best results show an accuracy of 90% and 93% for 12 and nine activities, respectively. To the author’s knowledge, these analyses provide the best state-of-the-art results over this public dataset. Additionally, this paper includes several analyses of the confusion between the different activities.

Sari Diana Puspita, Hartini Sri, Azzahra Faradhina et al.

Environmental issues have become an important consideration to be included in business operations. One of the main environmental problems in the wood industry is the high production of wood waste and increasing scarcity and cost of raw materials. For this reason, companies need to utilize wood waste to reduce material costs and, at the same time, reduce the impact of waste on the environment. Converting wood waste into products that can be sold will increase its economic value. This research aims to identify the types of waste from a furniture company and reduce waste by designing various products made from wood waste. Wood chips are wood waste that have the potential to be reused. Waste wood chips from the materials station can be used to create bedside table products. The bedside table was chosen because of its high selling price, and the company could make it with its existing resources. Apart from that, the company still needs to expand its variety of bedside tables. The bedside table was designed using the TRIZEE method. TRIZEE is a method that combines eco-efficiency with 40 TRIZ principles, which can reduce environmental impacts in alignment with company goals. The design process resulted in 4 bedside table variations. Production capacity is estimated to produce 56 bedside tables per month. If scrap waste is successfully used as bedside table material. Apart from saving raw materials, the company will be able to reduce wood waste and gain greater profits from waste utilization.

Raghavarshith Bandreddi, Raziyeh Farmani

Leakage is a major issue faced by utilities across the world. Background leaks constitute a large component, and their small size makes it challenging to localize. This paper presents a hydraulic model-based approach to localize background leaks. The proposed methodology clusters nodes into leak groups using node-weighted spectral clustering and estimates background leakage in each leak group using optimization. The algorithm successfully localized 113 out of 118 background leaks (no leak size >0.28% of the bulk supply) and estimated the leakage amount using simulated data.

Egor Klimov, Muhammad Umair Ahmed, Nikolai Sviridov et al.

Bus factor (BF) is a metric that tracks knowledge distribution in a project. It is the minimal number of engineers that have to leave for a project to stall. Despite the fact that there are several algorithms for calculating the bus factor, only a few tools allow easy calculation of bus factor and convenient analysis of results for projects hosted on Git-based providers. We introduce Bus Factor Explorer, a web application that provides an interface and an API to compute, export, and explore the Bus Factor metric via treemap visualization, simulation mode, and chart editor. It supports repositories hosted on GitHub and enables functionality to search repositories in the interface and process many repositories at the same time. Our tool allows users to identify the files and subsystems at risk of stalling in the event of developer turnover by analyzing the VCS history. The application and its source code are publicly available on GitHub at https://github.com/JetBrains-Research/bus-factor-explorer. The demonstration video can be found on YouTube: https://youtu.be/uIoV79N14z8

Chung-Ho Tien, Xia-Na Ma, Zi-Hui Sun

The innovative thinking of artists highlights the influence of Bergson’s philosophy on modern art, and the perception of the relationship of the inner essence of “mind and matter” through observing and experiencing daily life helps artists design works according to the artists’ conception. The innovative thinking of learners is based on the creation of art, namely duration, movement, timeliness, and dynamics. We integrated the emotions of creators as the links of the creation of works with the “aesthetic duration” of the viewer, the “movement” rhythm of visual transformation of different “timeliness” provided by the workspace to evoke the “dynamics” of the viewers’ internal thoughts. In this article, the creative thinking of three works, namely Growth, Fisherman, and Virtuality and Reality, was analyzed for learners to discuss how the creators designed their works to connect and reflect their creative thinking and creation with the help of emotion. The results of this analysis of creative thinking helped students understand the process of artistic creation and have the creative characteristics of Bergerson’s philosophy. The emotional elements of the creator need to be integrated to evoke the deepest feelings and help viewers feel the beauty of works to the maximum.