Hasil untuk "Machine design and drawing"

Xin Geng, Jixing Wang, Shengying Guo et al.

In wireless power transfer (WPT) systems, magnetically coupled wireless power transfer has become a major research focus due to its advantages such as long transmission distance, strong tolerance to misalignment, and high power transfer capability. It is also widely applied in vehicle wireless power transfer systems. From the perspective of practical engineering applications, this paper investigates the problem of system parameter variations caused by changes in inductance and load, in combination with magnetically coupled structures. During actual system operation, misalignment of the coupling mechanism leads to variations in mutual inductance, while the load resistance may also fluctuate. These parameter changes result in alterations to the overall output characteristics of the system, which are detrimental to stable system operation. Moreover, adopting a dual-side communication control strategy is susceptible to interference from the system’s power circuitry. To address these issues, this paper proposes a novel state variable modeling method and designs a state observer based on the extended Kalman filter (EKF) algorithm to estimate the secondary-side parameters, thereby enabling observation of the voltage across the load at the receiver side. The state observer is configured with two operating modes to monitor variations in mutual inductance and load resistance. The observer outputs are compared with the actual load-side voltage, and the effectiveness of the proposed state observer is verified.

Kotekar Annapoorna Prabhu, Andrew Gan, Zahra Ghodsi

Machine learning relies on randomness as a fundamental component in various steps such as data sampling, data augmentation, weight initialization, and optimization. Most machine learning frameworks use pseudorandom number generators as the source of randomness. However, variations in design choices and implementations across different frameworks, software dependencies, and hardware backends along with the lack of statistical validation can lead to previously unexplored attack vectors on machine learning systems. Such attacks on randomness sources can be extremely covert, and have a history of exploitation in real-world systems. In this work, we examine the role of randomness in the machine learning development pipeline from an adversarial point of view, and analyze the implementations of PRNGs in major machine learning frameworks. We present RNGGuard to help machine learning engineers secure their systems with low effort. RNGGuard statically analyzes a target library's source code and identifies instances of random functions and modules that use them. At runtime, RNGGuard enforces secure execution of random functions by replacing insecure function calls with RNGGuard's implementations that meet security specifications. Our evaluations show that RNGGuard presents a practical approach to close existing gaps in securing randomness sources in machine learning systems.

Rakesh Gangadharaiah, Johnell Brooks, Lisa Boor et al.

Pooled ridesharing offers on-demand, one-way, cost-effective transportation for passengers traveling in similar directions via a shared vehicle ride with others they do not know. Despite its potential benefits, the adoption of pooled rideshare remains low in the United States. This exploratory study aims to evaluate potential service improvements and features that may increase users’ willingness to adopt the service. The study analyzed transportation behaviors, rideshare preferences, and willingness to adopt pooled rideshare services among 8296 U.S. participants in 2025, building on findings from a 2021 nationwide survey of 5385 U.S. participants. The study incorporated 77 actionable items developed from the results of the 2021 survey to assess whether addressing specific user-generated topics such as safety, reliability, convenience, and privacy can improve pooled rideshare use. A side-by-side comparison of the 2021 and 2025 data revealed shifts in transportation behavior, with personal rideshare usage increasing from 22% to 28%, public transportation from 21% to 27%, and pooled rideshare from 6% to 8%, while personal vehicle (79%) use remained dominant. Participants rated features such as driver verification (94%), vehicle information (93%), peak time reliability (93%), and saving time and money (92–93%) as most important for improving rideshare services. A pre-to-post analysis of willingness to use pooled rideshare utilizing the actionable items as per respondents’ preferences showed improvement: “definitely will” increased from 15.9% to 20.1% and “probably will” rose from 35.6% to 47.7%. These results suggest that well-targeted service improvements may meaningfully enhance pooled rideshare acceptance. This study offers practical guidance for Transportation Network Companies (TNCs) and policymakers aiming to improve pooled rideshare as well as potential future research opportunities.

Tomáš Gajdošík, Igor Gajdáč, Rudolf Madaj et al.

Electrification and modularity are emerging as key trends in off-road vehicle development, prompting the need for innovative solutions in steering and modular coupling. This study presents an electromechanical connection and steering joint, conceived to replace traditional hydraulic systems and offer enhanced steering precision, modular adaptability, and system efficiency. By eliminating hydraulic components, the design reduces fluid leakage risks, lowers maintenance requirements, and improves energy integration with the vehicle’s electric drivetrain. The joint enables independent module articulation, including steering and controlled tilting, to optimize vehicle stability across diverse terrains. A prototype was built and tested under real-world conditions, assessing functional reliability, ease of integration, and operational performance. The findings demonstrate that electromechanical steering substantially boosts system flexibility compared to conventional hydraulic setups.

Erickson Senkondo, Deo Chimba, Masanja Madalo et al.

Railroad-highway grade crossings (RHGCs) are critical points of conflict between roadway and rail systems, contributing to over 2000 crashes and 250 fatalities annually in the United States. This study applied machine learning methods (ML) techniques to model and predict crash frequency at RHGCs, using a comprehensive dataset from the Federal Railroad Administration (FRA) and Tennessee Department of Transportation (TDOT). The dataset included 807 validated crossings, incorporating roadway geometry, traffic volumes, rail characteristics, and control features. Five ML models—Random Forest, XGBoost, PSO-Elastic Net, Transformer-CNN, and Autoencoder-MLP—were developed and compared to a traditional Negative Binomial (NB) regression model. Results showed that ML models significantly outperformed the NB model in predictive accuracy, with the Transformer-CNN achieving the lowest Mean Squared Error (21.4) and Mean Absolute Error (3.2). Feature importance analysis using SHAP values consistently identified Annual Average Daily Traffic (AADT), Truck Traffic Percentage, and Number of Lanes as the most influential predictors, findings that were underrepresented or statistically insignificant in the NB model. Notably, the NB model failed to detect the nonlinear relationships and interaction effects that ML algorithms captured effectively. While only three variables were statistically significant in the NB model, ML models revealed a broader spectrum of critical crash determinants, offering deeper interpretability and higher sensitivity. These findings emphasize the superiority of machine learning approaches in modeling RHGC safety and highlight their potential to support data-driven interventions and policy decisions for reducing crash risks at grade crossings.

Samoichuk Kyrylo, Kovalyov Alexandr, Palianychka Nadiia et al.

The modern global milk processing industry involves the use of innovations and optimization of existing industry management methods, which contributes to the realization of sustainable development and energy efficiency. Increasing the energy efficiency of dispersing and homogenizing milk and dairy products can contribute to the practical implementation of the philosophy of the “European Green Deal”. The jet-slot milk homogenizer is one of the most energy-efficient among all types of homogenizers in the dairy industry. The principle of its operation is based on the creation of a maximum speed difference between the fat balls of cream and the flow of skimmed milk. This makes it possible to obtain a high degree of dispersion with high energy efficiency of the process. Reducing the specific energy consumption and finding the optimal parameters of the homogenizer were based on the results of both theoretical and experimental studies and were carried out graphically. The optimization criteria (decreasing specific energy consumption while maintaining high homogenization quality) were chosen to achieve a dispersion of 0.8 μm with minimal energy consumption. The diameter of the confusor is optimized at the point of greatest narrowing. The obtained results indicate that to increase the energy efficiency of homogenization, the parameter values should be within 3.5–4.0 mm. The parameters of the width of the ring gap, the fat content and the speed of the cream are optimized. The results showed that it is possible to reduce the specific energy intensity of the process to values of 0.88–0.92 kWh/t when using cream with a fat content of 33–43%, which should be fed through an annular gap with a width of 0.6–0.8 mm. Optimum values of the cream feed speed were found, which should be equal to 7–11 m/s. The research results are of high practical value for the further development of an energy-efficient industrial model of a jet-slot homogenizer.

Yong Peng, Aizhen Ma, Dennis Z. Yu et al.

Urban transportation systems evolve toward greater diversification, scalability, and complexity. To address the escalating issue of urban traffic congestion, leveraging modern information technologies to enhance the integration of multiple transportation modes and maximize overall efficiency has emerged as a promising strategy. This study focuses on the decision making problem of urban multimodal transportation travel paths, integrating the time-varying characteristics of public transportation schedules and networks. We consider passengers’ diverse needs and systematically investigate how to optimize travel paths to minimize travel time while adhering to constraints, such as the number of interchanges and travel costs. To address this NP-hard problem, we propose and implement two optimization algorithms: a variable-length coding genetic algorithm (V-GA) and a full permutation coding genetic algorithm (F-GA). Detailed numerical analysis validates the effectiveness of both algorithms, with the V-GA demonstrating significant advantages over the F-GA in terms of solution efficiency. Our findings provide novel perspectives and methodologies for optimizing urban multimodal transportation travel paths, offering robust theoretical foundations and practical tools for enhancing urban traffic planning and travel service efficiency.

Benjamin J. Choi

Brain-computer interfaces (BCIs) offer transformative potential, but decoding neural signals presents significant challenges. The core premise of this paper is built around demonstrating methods to elucidate the underlying low-dimensional geometric structure present in high-dimensional brainwave data in order to assist in downstream BCI-related neural classification tasks. We demonstrate two pipelines related to electroencephalography (EEG) signal processing: (1) a preliminary pipeline removing noise from individual EEG channels, and (2) a downstream manifold learning pipeline uncovering geometric structure across networks of EEG channels. We conduct preliminary validation using two EEG datasets and situate our demonstration in the context of the BCI-relevant imagined digit decoding problem. Our preliminary pipeline uses an attention-based EEG filtration network to extract clean signal from individual EEG channels. Our primary pipeline uses a fast Fourier transform, a Laplacian eigenmap, a discrete analog of Ricci flow via Ollivier's notion of Ricci curvature, and a graph convolutional network to perform dimensionality reduction on high-dimensional multi-channel EEG data in order to enable regularizable downstream classification. Our system achieves competitive performance with existing signal processing and classification benchmarks; we demonstrate a mean test correlation coefficient of >0.95 at 2 dB on semi-synthetic neural denoising and a downstream EEG-based classification accuracy of 0.97 on distinguishing digit- versus non-digit- thoughts. Results are preliminary and our geometric machine learning pipeline should be validated by more extensive follow-up studies; generalizing these results to larger inter-subject sample sizes, different hardware systems, and broader use cases will be crucial.

Ying-Kuan Tsai, Vispi Karkaria, Yi-Ping Chen et al.

Control Co-Design (CCD) integrates physical and control system design to improve the performance of dynamic and autonomous systems. Despite advances in uncertainty-aware CCD methods, real-world uncertainties remain highly unpredictable. Multi-generation design addresses this challenge by considering the full lifecycle of a product: data collected from each generation informs the design of subsequent generations, enabling progressive improvements in robustness and efficiency. Digital Twin (DT) technology further strengthens this paradigm by creating virtual representations that evolve over the lifecycle through real-time sensing, model updating, and adaptive re-optimization. This paper presents a DT-enabled CCD framework that integrates Deep Reinforcement Learning (DRL) to jointly optimize physical design and controller. DRL accelerates real-time decision-making by allowing controllers to continuously learn from data and adapt to uncertain environments. Extending this approach, the framework employs a multi-generation paradigm, where each cycle of deployment, operation, and redesign uses collected data to refine DT models, improve uncertainty quantification through quantile regression, and inform next-generation designs of both physical components and controllers. The framework is demonstrated on an active suspension system, where DT-enabled learning from road conditions and driving behaviors yields smoother and more stable control trajectories. Results show that the method significantly enhances dynamic performance, robustness, and efficiency. Contributions of this work include: (1) extending CCD into a lifecycle-oriented multi-generation framework, (2) leveraging DTs for continuous model updating and informed design, and (3) employing DRL to accelerate adaptive real-time decision-making.

Valentino F. Foit, David W. Hogg, Soledad Villar

Many machine learning tasks in the natural sciences are precisely equivariant to particular symmetries. Nonetheless, equivariant methods are often not employed, perhaps because training is perceived to be challenging, or the symmetry is expected to be learned, or equivariant implementations are seen as hard to build. Group averaging is an available technique for these situations. It happens at test time; it can make any trained model precisely equivariant at a (often small) cost proportional to the size of the group; it places no requirements on model structure or training. It is known that, under mild conditions, the group-averaged model will have a provably better prediction accuracy than the original model. Here we show that an inexpensive group averaging can improve accuracy in practice. We take well-established benchmark machine learning models of differential equations in which certain symmetries ought to be obeyed. At evaluation time, we average the models over a small group of symmetries. Our experiments show that this procedure always decreases the average evaluation loss, with improvements of up to 37\% in terms of the VRMSE. The averaging produces visually better predictions for continuous dynamics. This short paper shows that, under certain common circumstances, there are no disadvantages to imposing exact symmetries; the ML4PS community should consider group averaging as a cheap and simple way to improve model accuracy.

Valerio Mangeruga, Dario Cusati, Francesco Raimondi et al.

Reducing CO₂ emissions is becoming a particularly important goal for motorcycle manufacturers. A fully electric transition still seems far away, given the difficulties in creating an electric motorcycle with an acceptable range and mass. This opens up opportunities for the application of hybrid powertrains in motorcycles. Managing mass, cost, and volume is a challenging issue for motorcycles; therefore, an MHEV architecture represents an interesting opportunity, as it is a low-complexity and low-cost solution. Firstly, in this work, an adequate sizing of the powertrain components is studied for the maximum reduction in fuel consumption. This is performed by analyzing many different system configurations with different hybridization ratios. A 1D simulation of the motorcycle traveling along the homologation cycle (WMTC) is performed, and the powerunit use strategy is optimized for each configuration using the Dynamic Programming technique. The results are analyzed in order to highlight the impact of kinetic energy recovery and engine load-point shifting on fuel consumption reduction. The results show the applicability of MHEV technology to road motorcycles, thus providing a useful tool to analyze the cost/benefit ratio of this technology. The developed methodology is also suitable for different vehicles once a specific test cycle is known.

Jing Gong, Amod Raut, Marcel Pelzer et al.

The emergence of automotive-grade LiDARs has given rise to new potential methods to develop novel advanced driver assistance systems (ADAS). However, accurate and reliable parking slot detection (PSD) remains a challenge, especially in the low-light conditions typical of indoor car parks. Existing camera-based approaches struggle with these conditions and require sensor fusion to determine parking slot occupancy. This paper proposes a parking slot detection (PSD) algorithm which utilizes the intensity of a LiDAR point cloud to detect the markings of perpendicular parking slots. LiDAR-based approaches offer robustness in low-light environments and can directly determine occupancy status using 3D information. The proposed PSD algorithm first segments the ground plane from the LiDAR point cloud and detects the main axis along the driving direction using a random sample consensus algorithm (RANSAC). The remaining ground point cloud is filtered by a dynamic Otsu’s threshold, and the markings of parking slots are detected in multiple windows along the driving direction separately. Hypotheses of parking slots are generated between the markings, which are cross-checked with a non-ground point cloud to determine the occupancy status. Test results showed that the proposed algorithm is robust in detecting perpendicular parking slots in well-marked car parks with high precision, low width error, and low variance. The proposed algorithm is designed in such a way that future adoption for parallel parking slots and combination with free-space-based detection approaches is possible. This solution addresses the limitations of camera-based systems and enhances PSD accuracy and reliability in challenging lighting conditions.

Jorge I. Hernandez-Martinez, Andres Mendez-Vazquez, Gerardo Rodriguez-Hernandez et al.

We propose a data-driven approach using a Restricted Boltzmann Machine (RBM) to solve the Schrödinger equation in configuration space. Traditional Configuration Interaction (CI) methods construct the wavefunction as a linear combination of Slater determinants, but this becomes computationally expensive due to the factorial growth in the number of configurations. Our approach extends the use of a generative model such as the RBM by incorporating a taboo list strategy to enhance efficiency and convergence. The RBM is used to efficiently identify and sample the most significant determinants, thus accelerating convergence and substantially reducing computational cost. This method achieves up to 99.99% of the correlation energy while using up to four orders of magnitude fewer determinants compared to full CI calculations and up to two orders of magnitude fewer than previous state of the art methods. Beyond efficiency, our analysis reveals that the RBM learns electron distributions over molecular orbitals by capturing quantum patterns that resemble Radial Distribution Functions (RDFs) linked to molecular bonding. This suggests that the learned pattern is interpretable, highlighting the potential of machine learning for explainable quantum chemistry

Hector A. Gonzalez, Jiaxin Huang, Florian Kelber et al.

The joint progress of artificial neural networks (ANNs) and domain specific hardware accelerators such as GPUs and TPUs took over many domains of machine learning research. This development is accompanied by a rapid growth of the required computational demands for larger models and more data. Concurrently, emerging properties of foundation models such as in-context learning drive new opportunities for machine learning applications. However, the computational cost of such applications is a limiting factor of the technology in data centers, and more importantly in mobile devices and edge systems. To mediate the energy footprint and non-trivial latency of contemporary systems, neuromorphic computing systems deeply integrate computational principles of neurobiological systems by leveraging low-power analog and digital technologies. SpiNNaker2 is a digital neuromorphic chip developed for scalable machine learning. The event-based and asynchronous design of SpiNNaker2 allows the composition of large-scale systems involving thousands of chips. This work features the operating principles of SpiNNaker2 systems, outlining the prototype of novel machine learning applications. These applications range from ANNs over bio-inspired spiking neural networks to generalized event-based neural networks. With the successful development and deployment of SpiNNaker2, we aim to facilitate the advancement of event-based and asynchronous algorithms for future generations of machine learning systems.

Radek Norbert

Properties of WC-Co coatings with Al2O3 addition on the C45 mild steel surface in acidic chloride solution were examined. The WC-Co-Al2O3 coatings on steel surfaces were deposited by an electro-spark (ESD) technique. The anti-corrosion properties of the coatings were mainly investigated by electrochemical methods. Moreover, the scanning electron microscope (SEM) was employed for the observation of the surface of materials. The structure of coatings depended on the composition of electrospark electrodes. In the WC80-Co5-Al2O315 coating, the largest corrosion resistance was shown. The corrosion rate of the specimen was approximately eight times smaller than the coating without of Al2O3 addition. The aim of the research was to obtain, by adding alumina, an improvement in the functional properties of WC-Co coatings produced by the ESD method. Due to the original features of ESD coatings, they can be used in sliding friction pairs and as anti-wear coatings on cutting tools.

Murray Z. Frank, Jing Gao, Keer Yang

Standard forecast efficiency tests interpret violations as evidence of behavioral bias. We show theoretically and empirically that rational forecasters using optimal regularization systematically violate these tests. Machine learning forecasts show near zero bias at one year horizon, but strong overreaction at two years, consistent with predictions from a model of regularization and measurement noise. We provide three complementary tests: experimental variation in regularization parameters, cross-sectional heterogeneity in firm signal quality, and quasi-experimental evidence from ML adoption around 2013. Technically trained analysts shift sharply toward overreaction post-2013. Our findings suggest reported violations may reflect statistical sophistication rather than cognitive failure.

Jonayet Miah, Muntasir Mamun, Md Minhazur Rahman et al.

Mobile phones and other electronic gadgets or devices have aided in collecting data without the need for data entry. This paper will specifically focus on Mobile health data. Mobile health data use mobile devices to gather clinical health data and track patient vitals in real-time. Our study is aimed to give decisions for small or big sports teams on whether one athlete good fit or not for a particular game with the compare several machine learning algorithms to predict human behavior and health using the data collected from mobile devices and sensors placed on patients. In this study, we have obtained the dataset from a similar study done on mhealth. The dataset contains vital signs recordings of ten volunteers from different backgrounds. They had to perform several physical activities with a sensor placed on their bodies. Our study used 5 machine learning algorithms (XGBoost, Naive Bayes, Decision Tree, Random Forest, and Logistic Regression) to analyze and predict human health behavior. XGBoost performed better compared to the other machine learning algorithms and achieved 95.2% accuracy, 99.5% in sensitivity, 99.5% in specificity, and 99.66% in F1 score. Our research indicated a promising future in mhealth being used to predict human behavior and further research and exploration need to be done for it to be available for commercial use specifically in the sports industry.

Hannah Blocher, Georg Schollmeyer, Christoph Jansen et al.

We propose a framework for descriptively analyzing sets of partial orders based on the concept of depth functions. Despite intensive studies of depth functions in linear and metric spaces, there is very little discussion on depth functions for non-standard data types such as partial orders. We introduce an adaptation of the well-known simplicial depth to the set of all partial orders, the union-free generic (ufg) depth. Moreover, we utilize our ufg depth for a comparison of machine learning algorithms based on multidimensional performance measures. Concretely, we analyze the distribution of different classifier performances over a sample of standard benchmark data sets. Our results promisingly demonstrate that our approach differs substantially from existing benchmarking approaches and, therefore, adds a new perspective to the vivid debate on the comparison of classifiers.

Javier Duarte, Nhan Tran, Ben Hawks et al.

Applications of machine learning (ML) are growing by the day for many unique and challenging scientific applications. However, a crucial challenge facing these applications is their need for ultra low-latency and on-detector ML capabilities. Given the slowdown in Moore's law and Dennard scaling, coupled with the rapid advances in scientific instrumentation that is resulting in growing data rates, there is a need for ultra-fast ML at the extreme edge. Fast ML at the edge is essential for reducing and filtering scientific data in real-time to accelerate science experimentation and enable more profound insights. To accelerate real-time scientific edge ML hardware and software solutions, we need well-constrained benchmark tasks with enough specifications to be generically applicable and accessible. These benchmarks can guide the design of future edge ML hardware for scientific applications capable of meeting the nanosecond and microsecond level latency requirements. To this end, we present an initial set of scientific ML benchmarks, covering a variety of ML and embedded system techniques.

Philipp Rosenthal, Oliver Niggemann

Artificial Intelligence (AI) has significant potential for product design: AI can check technical and non-technical constraints on products, it can support a quick design of new product variants and new AI methods may also support creativity. But currently product design and AI are separate communities fostering different terms and theories. This makes a mapping of AI approaches to product design needs difficult and prevents new solutions. As a solution, this paper first clarifies important terms and concepts for the interdisciplinary domain of AI methods in product design. A key contribution of this paper is a new classification of design problems using the four characteristics decomposability, inter-dependencies, innovation and creativity. Definitions of these concepts are given where they are lacking. Early mappings of these concepts to AI solutions are sketched and verified using design examples. The importance of creativity in product design and a corresponding gap in AI is pointed out for future research.