Hasil untuk "Machine design and drawing"

Qian Yang, Aaron Steinfeld, J. Zimmerman

Clinical decision support tools (DST) promise improved healthcare outcomes by offering data-driven insights. While effective in lab settings, almost all DSTs have failed in practice. Empirical research diagnosed poor contextual fit as the cause. This paper describes the design and field evaluation of a radically new form of DST. It automatically generates slides for clinicians' decision meetings with subtly embedded machine prognostics. This design took inspiration from the notion of Unremarkable Computing, that by augmenting the users' routines technology/AI can have significant importance for the users yet remain unobtrusive. Our field evaluation suggests clinicians are more likely to encounter and embrace such a DST. Drawing on their responses, we discuss the importance and intricacies of finding the right level of unremarkableness in DST design, and share lessons learned in prototyping critical AI systems as a situated experience.

Moses Gladson Selvamuthu, Kazuki Abe, Kenjiro Tadakuma et al.

Abstract Multi-degree of freedom (DOF) robotic systems, particularly those with seven or more DOFs similar to the human arm, have the potential to significantly expand the functional range and versatility of robotic manipulators. The spherical gear mechanism, known as Active Ball Engagement Mechanics (ABENICS), serves as a novel joint element that enables the integration of multiple rotational axes at a single point, resulting in a more compact structure with increased degrees of freedom. This study focuses on the design and validation of a miniaturized spherical gear mechanism, featuring a spherical gear with a module of 1.5 mm and an outer diameter of 51 mm. The study discusses its mechanical design, operational performance, and manipulability-based motion control strategy for effective singularity avoidance. Furthermore, a driving gear-based angular feedback system utilizing hall-effect sensors is introduced for homing, demonstrating improved performance and reliability compared to the previously implemented IMU-based homing approach. Experiments were conducted to assess the mechanism’s motion range, positional error, singularity avoidance, and homing performance, all of which were successfully validated. The results confirm the potential of this miniaturized mechanism to enable more compact, efficient, and functional robotic systems. Finally, the study demonstrates the application of the developed mechanism as a wrist joint attached to a robotic arm, capable of carrying a 250 g payload during a pick-and-place task.

Qiang Yang, Yudan Wang, Qin Wang et al.

Social media influencers strategically design the auditory and visual features of short videos to enhance consumer engagement. Among these, auditory emotional arousal and visual variation play crucial roles, yet their interactive effects remain underexplored. Drawing on multichannel integration theory, this study applies multimodal machine learning to analyze 12,842 short videos from Douyin, integrating text analysis, sound recognition, and image processing. The results reveal an inverted U-shaped relationship between auditory emotional arousal and consumer engagement, where moderate arousal maximizes interaction while excessively high or low arousal reduces engagement. Visual variation, however, exhibits a positive linear effect, with greater variation driving higher engagement. Notably, audiovisual congruence significantly enhances engagement, as high alignment between arousal and visual variation optimizes consumer information processing. These findings advance short video marketing research by uncovering the multisensory interplay in consumer engagement. They also provide practical guidance for influencers in optimizing voice and visual design strategies to enhance content effectiveness.

A. S. Akintola, Michael Akintayo, Temitope Kadri et al.

The integration of Adaptive Artificial Intelligence (AI) systems in educational settings has emerged as a transformative approach, offering tailored learning experiences that dynamically adapt to individual learners' needs, preferences and skill trajectories. This study explores the design, implementation and impact of AI-driven personalised learning pathways, focusing on their role in fostering skill development and improving educational outcomes. Drawing from advancements in adaptive learning platforms and intelligent tutoring systems, we analysed their mechanisms for real-time feedback, dynamic content delivery and personalised assessment. These systems utilise machine learning algorithms and natural language processing to identify gaps in understanding, recommend optimised learning pathways and adjust instructional strategies, thereby creating a highly responsive and student-centred learning environment. This research highlights key implementations, including the use of AI-enabled learning analytics to predict and address dropout risks, enhance engagement and support diverse learning styles. Notable examples, such as Knewton and DreamBox, illustrate the potential of adaptive learning to bridge educational disparities and promote equity by providing learners with customised resources and feedback. Furthermore, this paper addresses critical challenges, including ethical considerations, data privacy and algorithmic biases and offers a framework for the ethical deployment of AI in educational settings. By aligning adaptive AI systems with pedagogical principles, this study underscores their capacity to augment human instruction, enabling educators to focus on fostering higher-order cognitive skills and critical thinking. This exploration contributes to the growing discourse on AI in education and provides actionable insights for educators, technologists and policymakers. It emphasises the transformative potential of adaptive AI systems in preparing learners for the demands of a rapidly evolving digital economy, while fostering inclusivity and lifelong learning. The findings underscore the urgency of advancing these systems to effectively meet global educational challenges.

Nikoletta-Anna Kapogianni, Angeliki Sideraki, Christos-Nikolaos Anagnostopoulos

This systematic review explores the role of smartwatches in stress management, mental health monitoring, and overall well-being. Drawing from 61 peer-reviewed studies published between 2016 and 2025, this review synthesizes empirical findings across diverse methodologies, including biometric data collection, machine learning algorithms, and user-centered design evaluations. Smartwatches, equipped with sensors for physiological signals such as heart rate, heart rate variability, electrodermal activity, and skin temperature, have demonstrated promise in detecting and predicting stress and mood fluctuations in both clinical and everyday contexts. This review emphasizes the need for interdisciplinary collaboration to advance technological precision, ethical data handling, and user experience design. Moreover, it highlights how different algorithms—such as Support Vector Machines (SVMs), Random Forests, Deep Neural Networks, and Boosting methods—perform across various physiological signals (e.g., HRV, EDA, skin temperature). Furthermore, it identifies performance trends and challenges across lab-based vs. real-world deployments, emphasizing the trade-off between generalizability and personalization in model design.

tshingombe tshitadi

Peigang Li, Lu Wang, Caihao Lan et al.

The straightness of rail joints is one of the critical factors affecting passenger comfort in high-speed railways, and investigating its influence on the dynamic performance of the vehicle–track system and riding comfort is of great significance. In this study, long-term field measurements were conducted at a turnout joint of a newly constructed high-speed railway in China, combined with multibody dynamics simulations, to systematically analyze the long-term evolution of rail joint straightness under various conditions, including pre- and post-grinding, joint commissioning, official operation, and extreme weather. Based on normalized data processing, the root mean square (RMS) index of joint straightness was extracted for feature quantification. Together with vertical acceleration and the Sperling index obtained from vehicle–track coupled dynamics simulations, a quantitative relationship between straightness and comfort was established. The results indicate that the cubic polynomial fitting method can effectively characterize the nonlinear mapping between the RMS of joint straightness and the Sperling index, further revealing a critical threshold at approximately 0.4 mm RMS beyond which vehicle running stability deteriorates and ride comfort significantly worsens. This study provides a reliable theoretical basis and engineering reference for the evaluation of rail joint quality and the optimization of maintenance strategies.

Marcelo Cueva, Sebastián Valle, Alfredo Cevallos et al.

In the present investigation, carbon dioxide (CO₂), carbon monoxide (CO), hydrocarbons (HC), nitric oxides (NO_X), particulate matter (PM), and fuel consumption were measured in a compression ignition internal combustion engine on a road route cycle in Quito, Ecuador. We used premium diesel and a mixture of diesel and cerium oxide at a concentration of 250 ppm. This research aimed to investigate the impact of cerium oxide on fossil fuels in terms of CO₂, CO, HC, NOx, PM, and fuel consumption. Five repetitions were performed for each fuel, and the results obtained were statistically analyzed using control charts. The experimental results showed a 27.1% reduction in PM, a 24.9% increase in NOx, and a 24.2% increase in HC, along with a 1% decrease in fuel consumption compared to the premium diesel case. We observed that the reduction in PM was due to the catalytic action of CeO₂, which enhances carbon oxidation. On the other hand, the increase in NOx was related to the higher temperature in the combustion chamber resulting from the improved thermal efficiency of the engine. This study provides guidelines for controlling air pollutants originating from vehicle emissions in high-altitude (over 2000 masl) road operations using cerium oxide as an additive.

Akira Kanazawa, Hiroshi Ito, Hiroyuki Yamada

Abstract To expand the use of robots to assist and replace workers in tasks, the robot needs to deal with not only repetitive and simple tasks but also complex and delicate tasks with high speed and high accuracy. In recent years, imitation learning has been used in several studies to enable robots to learn complex human-like motion with little learning cost. However, in the imitation learning framework, it is difficult to make teaching data that takes into account optimal acceleration/deceleration, force, and constraints of the robot from a control perspective. In this paper, we propose a control scheme to track a fast and smooth imitation motion by implementing a model predictive control (MPC) scheme. To accelerate and smooth human teaching motions, we designed an MPC that follows a reference trajectory output from a motion generator learned by using deep predictive learning (DPL). By adopting this approach, it is possible to suppress excessive accelerations and decelerations while maintaining the ability to follow the target imitation motion. This allows for an increase in the robot’s motion speed while preserving the task success rate. Through simulations of an object grasping task and actual environments of a door-opening task, we evaluated the effectiveness of the proposed control scheme.

Kassem Danach, Hassan Harb, Semaan Amine et al.

This paper introduces a novel neuromorphic-inspired hyper-heuristic framework (NeuHH) for solving the Capacitated Single-Allocation p-Hub Location Routing Problem (CSAp-HLRP), a challenging combinatorial optimization problem that jointly addresses hub location decisions, capacity constraints, and vehicle routing. The proposed framework employs Spiking Neural Networks (SNNs) as the decision-making core, leveraging their temporal dynamics and spike-timing-dependent plasticity (STDP) to guide the real-time selection and adaptation of low-level heuristics. Unlike conventional learning-based hyper-heuristics, NeuHH provides biologically plausible, event-driven learning with improved scalability and interpretability. Experimental results on benchmark instances demonstrate that NeuHH outperforms classical metaheuristics, Lagrangian relaxation methods, and reinforcement learning-based hyper-heuristics. Specifically, NeuHH achieves superior performance in total cost minimization (up to 13.6% reduction), load balance improvement (achieving a load balance factor of as low as 1.04), and heuristic adaptability (reflected by higher heuristic switching frequency). These results highlight the framework’s potential for real-time and energy-efficient logistics optimization in large-scale dynamic networks.

Mingke Hou, Francis Assadian

Physics-assisted machine learning is a powerful framework that enhances data efficiency by integrating the strengths of conventional machine learning with physical knowledge. This paper applies this concept and focuses on the design of a driver evaluator using physics-assisted unsupervised learning, which serves as a virtual reference generator that provides different driving modes for vehicles equipped with active actuators. A strategy that applies sensitivity analysis regarding the vehicle handling performance, aiming to reduce the computational workload of the clustering algorithms, is proposed. First, a bicycle model with nonlinear Pacejka’s tire models is established for the analysis of lateral dynamics. Next, mathematical interpretations of sensitivity analysis are derived to evaluate the contribution of physical parameters to the system response and build the reduced parameters set. Then, Gaussian mixture models are fitted to a database generated with the full parameters set and another with the reduced set, respectively. Finally, step-steer and constant radius tests are performed to assess the handling performance with respect to the two validated centroids. Comparisons of lateral dynamics and understeer characteristics indicate that the proposed method can accurately distinguish driving modes in a much faster manner compared to traditional machine learning. This methodology has significant potential for practical applications with large databases and more complex systems.

Giordano Andreola, Susanna Caroppo, Giuseppe Di Battista et al.

Several algorithms for the construction of orthogonal drawings of graphs, including those based on the Topology-Shape-Metrics (TSM) paradigm, tend to prioritize the minimization of crossings. This emphasis has two notable side effects: some edges are drawn with unnecessarily long sequences of segments and bends, and the overall drawing area may become excessively large. As a result, the produced drawings often lack geometric uniformity. Moreover, orthogonal crossings are known to have a limited impact on readability, suggesting that crossing minimization may not always be the optimal goal. In this paper, we introduce a methodology that 'subverts' the traditional TSM pipeline by focusing on minimizing bends. Given a graph $G$, we ideally seek to construct a rectilinear drawing of $G$, that is, an orthogonal drawing with no bends. When not possible, we incrementally subdivide the edges of $G$ by introducing dummy vertices that will (possibly) correspond to bends in the final drawing. This process continues until a rectilinear drawing of a subdivision of the graph is found, after which the final coordinates are computed. We tackle the (NP-complete) rectilinear drawability problem by encoding it as a SAT formula and solving it with state-of-the-art SAT solvers. If the SAT formula is unsatisfiable, we use the solver's proof to determine which edge to subdivide. Our implementation, DOMUS, which is fairly simple, is evaluated through extensive experiments on small- to medium-sized graphs. The results show that it consistently outperforms OGDF's TSM-based approach across most standard graph drawing metrics.

Wei Sun, Lili Nurliynana Abdullah, Puteri Suhaiza Sulaiman et al.

This study aims to improve the accuracy of predicting the severity of traffic accidents by developing an innovative traffic accident risk prediction model—StackTrafficRiskPrediction. The model combines multidimensional data analysis including environmental factors, human factors, roadway characteristics, and accident-related meta-features. In the model comparison, the StackTrafficRiskPrediction model achieves an accuracy of 0.9613, 0.9069, and 0.7508 in predicting fatal, serious, and minor accidents, respectively, which significantly outperforms the traditional logistic regression model. In the experimental part, we analyzed the severity of traffic accidents under different age groups of drivers, driving experience, road conditions, light and weather conditions. The results showed that drivers between 31 and 50 years of age with 2 to 5 years of driving experience were more likely to be involved in serious crashes. In addition, it was found that drivers tend to adopt a more cautious driving style in poor road and weather conditions, which increases the margin of safety. In terms of model evaluation, the StackTrafficRiskPrediction model performs best in terms of accuracy, recall, and ROC–AUC values, but performs poorly in predicting small-sample categories. Our study also revealed limitations of the current methodology, such as the sample imbalance problem and the limitations of environmental and human factors in the study. Future research can overcome these limitations by collecting more diverse data, exploring a wider range of influencing factors, and applying more advanced data analysis techniques.

Y. Sultan Abylkairov, Matthew C. Edwards, Daniil Orel et al.

We investigate the potential of using gravitational wave (GW) signals from rotating core-collapse supernovae to probe the equation of state (EOS) of nuclear matter. By generating GW signals from simulations with various EOSs, we train machine learning models to classify them and evaluate their performance. Our study builds on previous work by examining how different machine learning models, parameters, and data preprocessing techniques impact classification accuracy. We test convolutional and recurrent neural networks, as well as six classical algorithms: random forest, support vector machines, naïve Bayes, logistic regression, $k$-nearest neighbors, and eXtreme gradient boosting. All models, except naïve Bayes, achieve over 90 per cent accuracy on our dataset. Additionally, we assess the impact of approximating the GW signal using the general relativistic effective potential (GREP) on EOS classification. We find that models trained on GREP data exhibit low classification accuracy. However, normalizing time by the peak signal frequency, which partially compensates for the absence of the time dilation effect in GREP, leads to a notable improvement in accuracy. Despite this, the accuracy does not exceed 70 per cent, suggesting that GREP lacks the precision necessary for EOS classification. Finally, our study has several limitations, including the omission of detector noise and the focus on a single progenitor mass model, which will be addressed in future works.

Su Man Nam, Jieun Park, Chaeyeon Sagong et al.

Computer vehicle simulators are used to model real-world situations to overcome time and cost limitations. The vehicle simulators provide virtual scenarios for real-world driving. Although the existing simulators precisely observe movement on the basis of good-quality graphics, they focus on a few driving vehicles instead of accident simulation. In addition, it is difficult to represent vehicle collisions. We propose a vehicle crash simulator with simulation and animation components. The proposed simulator synthesizes and simulates models of vehicles and environments. The simulator animates corresponding to the simulation through the execution results. The simulation results validate that the proposed simulator provides collision and non-collision results according to the speed of two vehicles at an intersection.

Marcos Moreno-Gonzalez, Antonio Artuñedo, Jorge Villagra et al.

One of the challenges of autonomous driving is to increase the number of situations in which an intelligent vehicle can continue to operate without human intervention. This requires path-tracking control to keep the vehicle stable while following the road, regardless of the shape of the road or the longitudinal speed at which it is moving. In this work, a control strategy framed in the Model-Free Control paradigm is presented to control the lateral vehicle dynamics in a decoupled control architecture. This strategy is designed to guide the vehicle through trajectories with diverse dynamic constraints and over a wide speed range. A design method for this control strategy is proposed, and metrics for trajectory tracking quality, system stability, and passenger comfort are applied to evaluate the controller’s performance. Finally, simulation and real-world tests show that the developed strategy is able to track realistic trajectories with a high degree of accuracy, safety, and comfort.

Binyang Song, Scarlett R. Miller, Faez Ahmed

Measuring design creativity is an indispensable component of innovation in engineering design. Properly assessing the creativity of a design requires a rigorous evaluation of the outputs. Traditional methods to evaluate designs are slow, expensive, and difficult to scale because they rely on human expert input. An alternative approach is to use computational methods to evaluate designs. However, most existing methods have limited utility because they are constrained to unimodal design representations (e.g., texts or sketches) and small datasets. To overcome these limitations, we propose a multimodal transfer learning-based machine learning model to predict five design metrics: drawing quality, uniqueness, elegance, usefulness, and creativity. The proposed model utilizes knowledge from large external datasets through transfer learning and simultaneously processes text and sketch data from early-phase concepts through multi-modal learning. Through six unimodal models using only texts or sketches, we show that transfer learning improves the predictive validity of text learning and sketch learning by 2%–18% and 9%–24%, respectively, for design metric evaluation. By comparing our multimodal model with the best unimodal models, we demonstrate that joining unimodal text and sketch learning models further increases the predictive validity of the approach by 4%–10%. The proposed models are generalizable to many application contexts beyond design concepts. Our findings highlight the importance of analyzing designs from multiple perspectives for design assessment. Finally, we discuss the challenges and opportunities in developing AI models for design metric evaluation.

Kucęba Robert

In the paper the author has attempted to achieve two convergent objectives: cognitive and empirical ones. The cognitive goal constituted an analysis of the definitions of virtual organi-sations and their adaptation while defining Virtual Power Plants (VPPs). When discussing the discourse in the area of virtual organisations, the author has attempted to justify the fact that the terminology pertaining to virtual organisations should constitute the foundations for defining Virtual Power Plants. With such an assumption, a vital importance has been assigned to co-sharing of “soft” resources – key competencies, and also organisational (managerial) integration. In the context of the adopted definitions, the distributed structure of virtual power plant has been em-bedded into four layers of Smart Grid: Customer Technology, Operational Technology, Smart Metering, Energy Management System. A measurable value of the conducted discourse has been aggregation of management functions of VPP, carried out in the four-layer structure of Smart Grid. In turn, the empirical objective was to determine and distinguish, based on the conducted expert research, the factors that determine the development of small-scale energy sector, including re-newable energy sources and prosumer installations – simultaneously determining the inclination of distributed electricity producers to mutual integration in the structures of virtual power plants. Assuming, in accordance with the definitions and discourse included in the first part of the paper, that the determined factors, among others, creating virtual power plants are not only of techno-logical nature, the author has developed four portfolios of these factors. They include the following ones: technological, economic (including micro- and macro-economic), environmental, and social. The experts participating in the research could select 5 factors from each of the developed portfolio which in their opinion determined the inclination of distributed electricity producers to integrate their sources in the structures of virtual power plants. A measurable value of the empirical part has been aggregating the determinants generated and distinguished in the research process.

Giandomenico Caruso, Mohammad Kia Yousefi, Lorenzo Mussone

The driving behaviour of Connected and Automated Vehicles (CAVs) may influence the final acceptance of this technology. Developing a driving style suitable for most people implies the evaluation of alternatives that must be validated. Intelligent Virtual Drivers (IVDs), whose behaviour is controlled by a program, can test different driving styles along a specific route. However, multiple combinations of IVD settings may lead to similar outcomes due to their high variability. The paper proposes a method to identify the IVD settings that can be used as a reference for a given route. The method is based on the cluster analysis of vehicular data produced by a group of IVDs with different settings driving along a virtual road scenario. Vehicular data are clustered to find IVDs representing a driving style to classify human drivers who previously drove on the same route with a driving simulator. The classification is based on the distances between the different vehicular signals calculated for the IVD and recorded for human drivers. The paper includes a case study showing the practical use of the method applied on an actual road circuit. The case study demonstrated that the proposed method allowed identifying three IVDs, among 29 simulated, which have been subsequently used as a reference to cluster 26 human driving styles. These representative IVDs, which ideally replicate the driving style of human drivers, can be used to support the development of CAVs control logic that better fits human expectations. A closing discussion about the flexibility of the method in terms of the different natures of data collection, allowed for depicting future applications and perspectives.

Karthik Karur, Nitin Sharma, Chinmay Dharmatti et al.

Path planning algorithms are used by mobile robots, unmanned aerial vehicles, and autonomous cars in order to identify safe, efficient, collision-free, and least-cost travel paths from an origin to a destination. Choosing an appropriate path planning algorithm helps to ensure safe and effective point-to-point navigation, and the optimal algorithm depends on the robot geometry as well as the computing constraints, including static/holonomic and dynamic/non-holonomically-constrained systems, and requires a comprehensive understanding of contemporary solutions. The goal of this paper is to help novice practitioners gain an awareness of the classes of path planning algorithms used today and to understand their potential use cases—particularly within automated or unmanned systems. To that end, we provide broad, rather than deep, coverage of key and foundational algorithms, with popular algorithms and variants considered in the context of different robotic systems. The definitions, summaries, and comparisons are relevant to novice robotics engineers and embedded system developers seeking a primer of available algorithms.