Hasil untuk "Machine design and drawing"

Dandan Xia, Chen Chen, Yongzhu Hu et al.

Extreme events such as tropical cyclones frequently occur in coastal areas in China. With high wind speeds and rainfall during such extreme events, the vehicles on sea-crossing bridges may face severe instability problems. In this study, the dynamics of vehicles on a cross-sea bridge under the wind–rain coupling effect were analyzed based on field measurement data using computational fluid dynamics (CFD). Wind field parameters of the coastal area in China were obtained using wind speed data from measurement towers. Based on CFD, the sliding grid method was applied to establish an aerodynamic analysis model of a container truck moving on a bridge under wind and rain conditions. The discrete phase model based on the Euler–Lagrange method was used to investigate the influence of rain and obtain the aerodynamic characteristics of the truck under the coupled wind and rain effects. Based on the computational analysis results, considering the turbulence intensity, the yaw angle peaks of the tractor and trailer increased by 5.2% and 3.8%, respectively, and the lateral displacement of the truck’s center of mass increased by 9.8%. Rainfall may cause the vehicle to have a higher response, resulting in a high risk of skidding. The results show that skidding occurs for the considered container truck when rainfall is at 9.8%. These results can provide parameters for traffic control strategies under such extreme climate events in coastal areas.

Taimoor Ali Khan, Yaqin Qin

This study confronts the significant challenges inherent in Traffic State Estimation (TSE) for rural arterial networks, where sparse sensor coverage and complex, dynamic traffic flows complicate effective management and safety assurance. Traditional TSE methodologies, often dependent on single-source data streams, fail to accurately model the intricate spatiotemporal dependencies present in such environments. This fundamental limitation precipitates critical safety hazards, including pervasive over speeding and dangerous queue spillback phenomena at intersections. To address these deficiencies, we introduce a novel hybrid intelligence framework that synergistically combines a Graph Attention Temporal Convolutional Network (GAT-TCN) with advanced Kalman Filter variants, specifically the Extended, Unscented, and Sliding Window Kalman Filters. The GAT-TCN component is engineered to excel at learning complex, non-linear correlations across both space and time through multi-source data fusion. Empirical validation conducted on a real-world rural toll corridor demonstrates that our proposed model achieves a statistically significant superiority over conventional benchmarks, as rigorously quantified by substantial reductions in both Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). Beyond mere predictive accuracy, the framework delivers transformative safety enhancements by facilitating the proactive identification of hazardous events, enabling earlier detection of over speeding and queue spillback compared to existing methods. Consequently, this research provides a scalable and robust framework for proactive rural traffic management, fundamentally shifting the paradigm from achieving incremental predictive improvements to generating decisive, safety-actionable insights for infrastructure operators.

Gąbka Joanna, Przybyś Krzysztof

The article presents research focused on design, testing and evaluation of the Artificial Intelligence (AI) algorithms dedicated for Virtual Player (VP/bot) embedded in the Production Management Training Platform (TP). The innovative software enables complex teaching process in form of didactic games. The purpose of the study is to eliminate limitations of the prototype VP’s algorithmic structure which was primarily implemented in the Platform. The study comprise measurements aimed at comparing effectiveness and efficiency of the existing solution with the capabilities of the newly developed VP’s logic. The overview of the algorithmic concepts available for VPs in serious games was made indicating elements useful for the purpose of the analysed system. Considering drawbacks of the original bot’s engine architecture, the upgraded version was elaborated and tested in the simplified version of the game. The results of the verification show to prove dominance of the AI solution with Machine Learning over the existing hybrid approach. The training, evaluation and recruitment games offered by the Platform could successfully fill in the gap identified in the new paradigm of education for Industry 4.0. It assures teaching of multidiscipline knowledge as well as practical skills training in the competitive environment altogether with thorough evaluation procedure. The appropriate VP’s logic increases flexibility of the didactic game and enables to customize the learning process which is crucial for the successful education process aided with gaming tools.

Zizhen Shen, Rui Wang, Lianbo Wang et al.

Structure detection (SD) has emerged as a critical technology for ensuring the safety and longevity of infrastructure, particularly in housing and civil engineering. Traditional SD methods often rely on manual inspections, which are time-consuming, labor-intensive, and prone to human error, especially in complex environments such as dense urban settings or aging buildings with deteriorated materials. Recent advances in autonomous systems—such as Unmanned Aerial Vehicles (UAVs) and climbing robots—have shown promise in addressing these limitations by enabling efficient, real-time data collection. However, challenges persist in accurately detecting and analyzing structural defects (e.g., masonry cracks, concrete spalling) amidst cluttered backgrounds, hardware constraints, and the need for multi-scale feature integration. The integration of machine learning (ML) and deep learning (DL) has revolutionized SD by enabling automated feature extraction and robust defect recognition. For instance, RepConv architectures have been widely adopted for multi-scale object detection, while attention mechanisms like TAM (Technology Acceptance Model) have improved spatial feature fusion in complex scenes. Nevertheless, existing works often focus on singular sensing modalities (e.g., UAVs alone) or neglect the fusion of complementary data streams (e.g., ground-based robot imagery) to enhance detection accuracy. Furthermore, computational redundancy in multi-scale processing and inconsistent bounding box regression in detection frameworks remain underexplored. This study addresses these gaps by proposing a generalized safety inspection system that synergizes UAV and stair-climbing robot data. We introduce a novel multi-scale targeted feature extraction path (Rep-FasterNet TAM block) to unify automated RepConv-based feature refinement with dynamic-scale fusion, reducing computational overhead while preserving critical structural details. For detection, we combine traditional methods with remote sensor fusion to mitigate feature loss during image upsampling/downsampling, supported by a structural model GIOU [Mathematical Definition: GIOU = IOU − (C − U)/C] that enhances bounding box regression through shape/scale-aware constraints and real-time analysis. By siting our work within the context of recent reviews on ML/DL for SD, we demonstrate how our hybrid approach bridges the gap between autonomous inspection hardware and AI-driven defect analysis, offering a scalable solution for large-scale housing safety assessments. In response to challenges in detecting objects accurately during housing safety assessments—including large/dense objects, complex backgrounds, and hardware limitations—we propose a generalized inspection system leveraging data from UAVs and stair-climbing robots. To address multi-scale feature extraction inefficiencies, we design a Rep-FasterNet TAM block that integrates RepConv for automated feature refinement and a multi-scale attention module to enhance spatial feature consistency. For detection, we combine dynamic-scale remote feature fusion with traditional methods, supported by a structural GIOU model that improves bounding box regression through shape/scale constraints and real-time analysis. Experiments demonstrate that our system increases masonry/concrete assessment accuracy by 11.6% and 20.9%, respectively, while reducing manual drawing restoration workload by 16.54%. This validates the effectiveness of our hybrid approach in unifying autonomous inspection hardware with AI-driven analysis, offering a scalable solution for SD in housing infrastructure.

Sari Masri, Huthaifa I. Ashqar, Mohammed Elhenawy

This study introduces a novel approach for traffic control systems by using Large Language Models (LLMs) as traffic controllers. The study utilizes their logical reasoning, scene understanding, and decision-making capabilities to optimize throughput and provide feedback based on traffic conditions in real time. LLMs centralize traditionally disconnected traffic control processes and can integrate traffic data from diverse sources to provide context-aware decisions. LLMs can also deliver tailored outputs using various means such as wireless signals and visuals to drivers, infrastructures, and autonomous vehicles. To evaluate LLMs’ ability as traffic controllers, this study proposed a four-stage methodology. The methodology includes data creation and environment initialization, prompt engineering, conflict identification, and fine-tuning. We simulated multi-lane four-leg intersection scenarios and generated detailed datasets to enable conflict detection using LLMs and Python simulation as a ground truth. We used chain-of-thought prompts to lead LLMs in understanding the context, detecting conflicts, resolving them using traffic rules, and delivering context-sensitive traffic management solutions. We evaluated the performance of GPT-4o-mini, Gemini, and Llama as traffic controllers. Results showed that the fine-tuned GPT-mini achieved 83% accuracy and an F1-score of 0.84. The GPT-4o-mini model exhibited a promising performance in generating actionable traffic management insights, with high ROUGE-L scores across conflict identification of 0.95, decision making of 0.91, priority assignment of 0.94, and waiting time optimization of 0.92. This methodology confirmed LLMs’ benefits as a traffic controller in real-world applications. We demonstrated that LLMs can offer precise recommendations to drivers in real time including yielding, slowing, or stopping based on vehicle dynamics. This study demonstrates LLMs’ transformative potential for traffic control, enhancing efficiency and safety at intersections.

Lucas Joos, Gavin J. Mooney, Maximilian T. Fischer et al.

The visual analysis of graphs in 3D has become increasingly popular, accelerated by the rise of immersive technology, such as augmented and virtual reality. Unlike 2D drawings, 3D graph layouts are highly viewpoint-dependent, making perspective selection critical for revealing structural and relational patterns. Despite its importance, there is limited empirical evidence guiding what constitutes an effective or preferred viewpoint from the user's perspective. In this paper, we present a systematic investigation into user-preferred viewpoints in 3D graph visualisations. We conducted a controlled study with 23 participants in a virtual reality environment, where users selected their most and least preferred viewpoints for 36 different graphs varying in size and layout. From this data, enriched by qualitative feedback, we distil common strategies underlying viewpoint choice. We further analyse the alignment of user preferences with classical 2D aesthetic criteria (e.g., Crossings), 3D-specific measures (e.g., Node-Node Occlusion), and introduce a novel measure capturing the perceivability of a graph's principal axes (Isometric Viewpoint Deviation). Our data-driven analysis indicates that Stress, Crossings, Gabriel Ratio, Edge-Node Overlap, and Isometric Viewpoint Deviation are key indicators of viewpoint preference. Beyond our findings, we contribute a publicly available dataset consisting of the graphs and computed aesthetic measures, supporting further research and the development of viewpoint evaluation measures for 3D graph drawing.

Kalichak Mariia, Pylypenko Liubomyr, Sorokovyi Pavlo et al.

Economic analysis of the field of housing construction indicates a certain specificity of its functioning in Ukraine, which is primarily related to the lack of opportunities for developers to invest their own resources in this construction and the need to attract financing at the early stages of the construction of residential real estate objects. The results of the empirical analysis of the dynamics of housing construction financing indicate that the main source of this financing is public funds (from 55% to more than 73% of the total volume of housing construction investments, depending on the year of their implementation). The insufficient level of quantitative and qualitative provision of housing for Ukrainian citizens provokes a constant demand for residential real estate objects, which in turn stimulates the development of housing construction. An analysis of the dynamics of residential real estate commissioning volumes and the amount of capital investments in residential buildings indicates a steady growth of these indicators over the past 10 years, with the exception of the crisis years of 2014 and 2020, in which there was a general decline in the national economy (2014 ) or even the global (2020) economy, caused by extraordinary circumstances (the Revolution of Dignity and the coronavirus epidemic). However, in subsequent years after these crises, the amount of capital investment in residential construction continued to grow.

Xuzhe Zhao

As fifth-generation (5G) and upcoming sixth-generation (6G) communications exhibit tremendous demands in providing high data throughput with a relatively low latency, millimeter-wave (mmWave) technologies manifest themselves as the key enabling components to achieve the envisioned performance and tasks. In this context, mmWave integrated circuits (IC) have attracted significant research interests over the past few decades, ranging from individual block design to complex system design. However, the highly nonlinear properties and intricate trade-offs involved render the design of analog or RF circuits a complicated process. The rapid evolution of fabrication technology also results in an increasingly long time allocated in the design process due to more stringent requirements. In this thesis, 28-GHz transceiver circuits are first investigated with detailed schematics and associated performance metrics. In this case, two target systems comprising heterogeneous individual blocks are selected and demonstrated on both the transmitter and receiver sides. Subsequently, some conventional and large-scale machine learning (ML) approaches are integrated into the design pipeline of the chosen systems to predict circuit parameters based on desired specifications, thereby circumventing the typical time-consuming iterations found in traditional methods. Finally, some potential research directions are discussed from the perspectives of circuit design and ML algorithms.

Sascha Krysmon, Johannes Claßen, Stefan Pischinger et al.

The topics of climate change and pollutant emission reduction are dominating societal discussions in many areas. In automotive development, with the introduction of real driving emissions (RDE) testing and the upcoming EU7 legislation, there are endless boundary conditions and potential scenarios that need to be evaluated. In terms of vehicle calibration, this is leading to a strong focus on alternative approaches such as virtual calibration. Due to the flexibility of virtual test environments and the variety of RDE scenarios, the amount of data collected is rapidly increasing. Supporting the calibration engineers in using the available data and identifying relevant information and test scenarios requires efficient approaches to data analysis. This paper therefore discusses the potential of data clustering to support this process. Using a previously developed approach for event detection in emission calibration, a methodology for the automatic categorization of events is presented. Approaches to clustering algorithms (hierarchical, partitioning, and density-based) are discussed and applied to data of interest. Their suitability for different signals is investigated exemplarily, and the relevant inputs are analyzed for their usability in calibration procedures. It is shown which clustering approaches have the potential to be implemented in the vehicle calibration process to provide added value to data evaluation by calibration engineers.

Marc Timur Düzgün, Frank Dorscheidt, Sascha Krysmon et al.

In hybrid vehicle development, the operating strategy has a decisive role in meeting the development goals, such as compliance with emission standards and high energy efficiency. A considerable number of interactions and cross-influences on other topics, such as emissions, on-board diagnostics, or drivability, must be considered during the calibration process. In this context, the given time constraints pose further challenges. To overcome these, approaches for virtualization of the calibration process are an effective measure. For this purpose, in the current study, a real engine control unit is embedded into a virtual simulation environment on so-called hardware-in-the-loop (HiL) testbenches, which allow virtual calibration and validation of the complete target vehicle. In this context, the paper presents a novel method for virtual calibration of operating strategies for hybrid-electric propulsion systems. This includes an innovative multi-criterial approach that considers the requirements of several development tasks, such as emission and OBD calibration. Measurement data for this optimization is generated on a HiL testbench setup tailored for the described methodology, including both the electrical setup and the simulation environment. To validate the selection of modeling approaches and the parametrization, the simulation environment is operated in open loop. The results of the open loop validation show promising behavior regarding the proposed use case. Finally, the presented methodology is evaluated regarding time and cost savings compared to a conventional approach.

Edgar Bowlin, Mohammad S. Khan, Biju Bajracharya et al.

Current research with Vehicular Ad-hoc Networks (VANETs) has focused on adapting an efficient consensus mechanism and reducing the blockchain size while maintaining security. Care must be taken when implementing blockchains within VANET applications to leverage the chains’ strengths while mitigating their weaknesses. These chains can serve as distributed ledgers that provide storage for more than financial transactions. The security provided by longer blockchains constitutes a nearly immutable, decentralized data structure that can store any data relevant to the applications. However, these chains must be adapted to the ad-hoc, resource-constrained environments found in VANETs. In the absence of abundant resources and reliable network connections, chain operation and maintenance must address the challenges presented by highly mobile nodes in novel ways, including situations such as emergency messaging that require real-time responses. Researchers have included different mechanisms to realize lightweight blockchains, such as adding reputation to existing consensus mechanisms, condensing the consensus committees, using geographical information, and monitoring a nodes behavior in attempts to adapt blockchains to these domains. This paper analyzes the challenges and gives solutions for these different mechanisms to realize lightweight blockchains for VANETs.

Michael Hagmann, Shigehiko Schamoni, Stefan Riezler

We demonstrate a validity problem of machine learning in the vital application area of disease diagnosis in medicine. It arises when target labels in training data are determined by an indirect measurement, and the fundamental measurements needed to determine this indirect measurement are included in the input data representation. Machine learning models trained on this data will learn nothing else but to exactly reconstruct the known target definition. Such models show perfect performance on similarly constructed test data but will fail catastrophically on real-world examples where the defining fundamental measurements are not or only incompletely available. We present a general procedure allowing identification of problematic datasets and black-box machine learning models trained on them, and exemplify our detection procedure on the task of early prediction of sepsis.

Keunwoo Choi, Sangshin Oh, Minsung Kang et al.

"Foley"refers to sound effects that are added to multimedia during post-production to enhance its perceived acoustic properties, e.g., by simulating the sounds of footsteps, ambient environmental sounds, or visible objects on the screen. While foley is traditionally produced by foley artists, there is increasing interest in automatic or machine-assisted techniques building upon recent advances in sound synthesis and generative models. To foster more participation in this growing research area, we propose a challenge for automatic foley synthesis. Through case studies on successful previous challenges in audio and machine learning, we set the goals of the proposed challenge: rigorous, unified, and efficient evaluation of different foley synthesis systems, with an overarching goal of drawing active participation from the research community. We outline the details and design considerations of a foley sound synthesis challenge, including task definition, dataset requirements, and evaluation criteria.

Shruti Gulati

Purpose Space tourism is fairly neglected in academic research and requires further exploration. Public reaction on social media offers great insights to understand the patterns of behaviour but is often ignored as a potential data source. Thus, this study aims to fill the gap by add to the literature on space tourism, social media analytics and behaviour. Design/methodology/approach The study adopts a qualitative approach and uses Twitter data for drawing conclusions. An exploratory design is used by analysing 10,000 tweets through unsupervised machine learning and two sets of analysis were conducted. First, sentiment analysis is performed using NRC Emotion Lexicon, which classifies the data as per eight basic emotions and polarity as positive and negative. The findings are complemented with a comparison cloud. Second, LDA Topic modelling using Gibbs Method is used to find ten broad topics that are used for discussions in space tourism tweets. Data visualisation technique is used to depict results using R language on RStudio. Findings A total of 21,784 emotions have tapped using the NRC Emotion Lexicon. Results indicate the dominance of positive sentiments (25%) with it surpassing the negative sentiments by many folds. The top emotions include trust and anticipation. The LDA-based Topic modelling identified seven correlated topic models that have been grouped by the author as space tourism in media, aspirations, ethical issues, criticism, descriptive, symbolism and miscellaneous. Originality/value To the best of the author’s knowledge, no study has attempted to study the response of space tourism on social media by tapping discussions in the form of Tweets. Thus, this study adds extensively and acts as a preliminary investigation on the public sentiments of space tourism on social media.

Czerwińska Karolina, Pacana Andrzej

The economic progress of recent years has contributed to the fact that both the quality of products and services offered and ISO standardization have become priority criterion that determines the success of manufacturing enterprises. Therefore, the monitoring and supervision of processes carried out in manufacturing companies is a key issue. These aspects support the achievement of key economic and quality objectives. The paper presents the results of a study on manufacturing enterprises in the context of process monitoring maturity. The research objective of the study was to determine the level of maturity in the use of process monitoring techniques and methods in manufacturing enterprises. The subject of the research were the techniques and methods used by the surveyed enterprises in such areas as: production management, machinery park management, warehouse management, transport management, inventory and supply management and IT tools. In order to determine the level of maturity, the author’s model was used, according to which the level of maturity of a manufacturing enterprise in the area of process monitoring depends on the instrumentation that is used in it.

Redko Andriy, Dzhyoiev Rafael, Redko Igor et al.

This work presents the results of a numerical study of the working processes of burning lignite in a vortex furnace with swirling countercurrent flows. The results of computer simulation of the processes of burning lignite with a moisture content of 30%, an ash content of 20% and 35% and a higher calorific value of Qрв = 13.9 MJ/kg and 9.7 MJ/kg, respectively are given. The fields of temperature distribution, gas velocity and particle trajectory in the volume and at the outlet of the furnace are determined. The values of the swirling flow velocity near the exit from the furnace reach 150-170 m/s. Mechanical underburning is 3.7% and 9.4% depending on the ash content. The results of a numerical study have showed that the diameter of lignite particles affects their combustion process: coke particles with an initial diameter from 25 microns to 250 microns burn out by 96%. The furnace provides a complete combustion of pulverized coal particles - 99.8% and of volatiles - 100% at volumetric heat stress in the 2500 kW/m3 furnace. The afterburning of fuel particles containing carbon is ensured by their circulation

Christoph Weiss, Alexander Kirmas, Sören Lemcke et al.

The steady enhancement of driver assistance systems and the automation of driving functions are in need of advanced driver monitoring functionalities. To evaluate the driver state, several parameters must be acquired. A basic parameter is the position of the driver, which can be useful for comfort automation or medical applications. Acquiring the position through cameras can be used to provide multiple information at once. When using infrared cameras, not only the position information but also the thermal information is available. Head tracking in the infrared domain is still a challenging task. The low resolution of affordable sensors makes it especially difficult to achieve high robustness due the lack of detailed images. In this paper, we present a novel approach for robust head tracking based on template matching and optical flow. The method has been tested on various sets of subjects containing different head shapes. The evaluation does not only include the original sensor size, but also downscaled images to simulate low resolution sensors. A comparison with the ground truth is performed for X- and Y-coordinate separately for each downscaled resolution.

Philip T. Roundy

Purpose – Entrepreneurs are increasingly relying on artificial intelligence (AI) to assist in creating and scaling new ventures. Research on entrepreneurs’ use of AI algorithms (machine learning, natural language processing, artificial neural networks) has focused on the intra-organizational implications of AI. The purpose of this paper is to explore how entrepreneurs’ adoption of AI influences their inter- and meta-organizational relationships. Design/methodology/approach – To address the limited understanding of the consequences of AI for communities of entrepreneurs, this paper develops a theory to explain how AI algorithms influence the micro (entrepreneur) and macro (system) dynamics of entrepreneurial ecosystems. Findings – The theory’s main insight is that substituting AI for entrepreneurial ecosystem interactions influences not only entrepreneurs’ pursuit of opportunities but also the coordination of their local entrepreneurial ecosystems. Originality/value – The theory contributes by drawing attention to the inter-organizational implications of AI, explaining how the decision to substitute AI for human interactions is a micro-foundation of ecosystems, and motivating a research agenda at the intersection of AI and entrepreneurial ecosystems.

Ahan Mishra, Ke Chen, Subhadipto Poddar et al.

Road safety has always been a crucial priority for municipalities, as vehicle accidents claim lives every day. Recent rapid improvements in video collection and processing technologies enable traffic researchers to identify and alleviate potentially dangerous situations. This paper illustrates cutting-edge methods by which conflict hotspots can be detected in various situations and conditions. Both pedestrian–vehicle and vehicle–vehicle conflict hotspots can be discovered, and we present an original technique for including more information in the graphs with shapes. Conflict hotspot detection, volume hotspot detection, and intersection-service evaluation allow us to understand the safety and performance issues and test countermeasures comprehensively. The selection of appropriate countermeasures is demonstrated by extensive analysis and discussion of two intersections in Gainesville, Florida, USA. Just as important is the evaluation of the efficacy of countermeasures. This paper advocates for selection from a menu of countermeasures at the municipal level, with safety as the top priority. Performance is also considered, and we present a novel concept of a performance–safety trade-off at intersections.

Murphy M. Peksen

The rapid conversion of conventional powertrain technologies to climate-neutral new energy vehicles requires the ramping of electrification. The popularity of fuel cell electric vehicles with improved fuel economy has raised great attention for many years. Their use of green hydrogen is proposed to be a promising clean way to fill the energy gap and maintain a zero-emission ecosystem. Their complex architecture is influenced by complex multiphysics interactions, driving patterns, and environmental conditions that put a multitude of power requirements and boundary conditions around the vehicle subsystems, including the fuel cell system, the electric motor, battery, and the vehicle itself. Understanding its optimal fuel economy requires a systematic assessment of these interactions. Artificial intelligence-based machine learning methods have been emerging technologies showing great potential for accelerated data analysis and aid in a thorough understanding of complex systems. The present study investigates the fuel economy peaks during an NEDC in fuel cell electric vehicles. An innovative approach combining traditional multiphysics analyses, design of experiments, and machine learning is an effective blend for accelerated data supply and analysis that accurately predicts the fuel consumption peaks in fuel cell electric vehicles. The trained and validated models show very accurate results with less than 1% error.