Hasil untuk "Machine design and drawing"

Poushali Das, Parham Khoshbakht Marvi, Sayan Ganguly et al.

MXenes, a new family of 2D nanomaterials, have been drawing notable attention due to their high electrical conductivity, processability, mechanical robustness and chemical tunability. Flexible sensors based on MXene-polymer composites are highly prospective for next-generation wearable electronics used in human–machine interfaces. With our article, we intend to fortify the bond between flexible matrices and MXenes thus promoting the swift advancement of flexible MXene-sensors for wearable technologies. MXenes, a new family of 2D nanomaterials, have been drawing notable attention due to their high electrical conductivity, processability, mechanical robustness and chemical tunability. Flexible sensors based on MXene-polymer composites are highly prospective for next-generation wearable electronics used in human–machine interfaces. With our article, we intend to fortify the bond between flexible matrices and MXenes thus promoting the swift advancement of flexible MXene-sensors for wearable technologies. Flexible sensors based on MXene-polymer composites are highly prospective for next-generation wearable electronics used in human–machine interfaces. One of the motivating factors behind the progress of flexible sensors is the steady arrival of new conductive materials. MXenes, a new family of 2D nanomaterials, have been drawing attention since the last decade due to their high electronic conductivity, processability, mechanical robustness and chemical tunability. In this review, we encompass the fabrication of MXene-based polymeric nanocomposites, their structure–property relationship, and applications in the flexible sensor domain. Moreover, our discussion is not only limited to sensor design, their mechanism, and various modes of sensing platform, but also their future perspective and market throughout the world. With our article, we intend to fortify the bond between flexible matrices and MXenes thus promoting the swift advancement of flexible MXene-sensors for wearable technologies.

Xiaoqi Zhou, P. Shi

ABSTRACT The twenty-first century is the century of underground space. The development of underground construction has made it necessary to establish an accurate and high-resolution subsurface model, which is fundamental to optimising engineering design and ensuring construction safety. Traditional stratigraphic methods, such as manual drawing, is time-consuming while geostatistical and probabilistic methods require extensive computational cost. With the prosperity of artificial intelligence and its successful application in a broad range of realms, Machine Learning (ML) has offered a powerful tool for intelligent and high-resolution subsurface modelling. Recently, substantial research papers focused on ML-based subsurface stratigraphy, most of which lay emphasis on the probabilistic methods but lack sufficient and deep insight into ML or DL-based methods. This paper proposed a clear and logical framework to sort out all literature related to this area, which reorganised the scattered past papers and holistically categorised the research topics into three types according to the relative relationships among multiple streams within the existing literature. The future agenda is fully discussed, including emerging opportunities and challenges in the context of ML-based subsurface modelling. Hopefully, this paper could provide a unified governance framework that guides how to properly apply ML in different sub-tasks of intelligent subsurface modelling.

Yating Chang, Yi Yang, Xiaoxi Cai et al.

Against the backdrop of growing concerns over university students’ mental health worldwide, campus environments play a crucial role not only in shaping spatial experiences but also in influencing psychological well-being. However, the psychosocial mechanisms through which campus landscapes affect well-being remain insufficiently theorized. Drawing on survey data from 500 students across two Chinese universities, this study employs structural equation modeling (SEM) and interpretable machine learning techniques (XGBoost-SHAP) to systematically examine the interrelations among landscape perception, place attachment, perceived social acceptance, school belonging, and psychological well-being. The results reveal the following: (1) campus landscapes serve as the primary catalyst for fostering emotional identification (place attachment) and social connectedness (perceived social acceptance and school belonging), thereby indirectly influencing psychological well-being through these psychosocial pathways; (2) landscape perception emerges as the strongest predictor of well-being, followed by school belonging. Although behavioral variables such as the green space maintenance quality, visit frequency, and duration of stay contribute consistently, their predictive power remains comparatively limited; (3) significant nonlinear associations are observed between core variables and well-being. While the positive effects of landscape perception, place attachment, and school belonging exhibit diminishing returns beyond certain thresholds, high levels of perceived social acceptance continue to generate sustained improvements in well-being. This study advances environmental psychology by highlighting the central role of campus landscapes in promoting mental health and provides actionable strategies for campus planning. It advocates for the design of balanced, diverse, and socially engaging landscape environments to maximize psychological benefits.

Christian Sivertsen, Guido Salimbeni, A. Løvlie et al.

Ongoing efforts to turn Machine Learning (ML) into a design material have encountered limited success. This paper examines the burgeoning area of AI art to understand how artists incorporate ML in their creative work. Drawing upon related HCI theories, we investigate how artists create ambiguity by analyzing nine AI artworks that use computer vision and image synthesis. Our analysis shows that, in addition to the established types of ambiguity, artists worked closely with the ML process (dataset curation, model training, and application) and developed various techniques to evoke the ambiguity of processes. Our finding indicates that the current conceptualization of ML as a design material needs to reframe the ML process as design elements, instead of technical details. Finally, this paper offers reflections on commonly held assumptions in HCI about ML uncertainty, dependability, and explainability, and advocates to supplement the artifact-centered design perspective of ML with a process-centered one.

Stefania Druga, Amy J. Ko

Children are increasingly surrounded by AI technologies but can overestimate smart devices’ abilities due to their lack of transparency. Drawing on the sense-making theory, this study explores how children come to see machine intelligence after training custom machine learning models and creating smart programs that use them. Through a 4-week observational study in after-school programs with 52 children (7 to 12 years old), we found that children engage in the scientific method while training, coding and testing their smart programs. We also found that children became more skeptical of certain abilities of smart devices as they shifted their attribution of agency from the devices to the people who program them. These changes in perception happened both through individual interactions with agents and prompted debates with peers. Based on these results, we conclude with discussions on strategies for promoting children’s sense-making practices and sense of agency in the age of machine learning.

Melissa Mccradden, Oluwadara Odusi, Shalmali Joshi et al.

The problem of algorithmic bias represents an ethical threat to the fair treatment of patients when their care involves machine learning (ML) models informing clinical decision-making. The design, development, testing, and integration of ML models therefore require a lifecycle approach to bias identification and mitigation efforts. Presently, most work focuses on the ML tool alone, neglecting the larger sociotechnical context in which these models operate. Moreover, the narrow focus on technical definitions of fairness must be integrated within the larger context of medical ethics in order to facilitate equitable care with ML. Drawing from principles of medical ethics, research ethics, feminist philosophy of science, and justice-based theories, we describe the Justice, Equity, Fairness, and Anti-Bias (JustEFAB) guideline intended to support the design, testing, validation, and clinical evaluation of ML models with respect to algorithmic fairness. This paper describes JustEFAB's development and vetting through multiple advisory groups and the lifecycle approach to addressing fairness in clinical ML tools. We present an ethical decision-making framework to support design and development, adjudication between ethical values as design choices, silent trial evaluation, and prospective clinical evaluation guided by medical ethics and social justice principles. We provide some preliminary considerations for oversight and safety to support ongoing attention to fairness issues. We envision this guideline as useful to many stakeholders, including ML developers, healthcare decision-makers, research ethics committees, regulators, and other parties who have interest in the fair and judicious use of clinical ML tools.

Katarzyna Stawarz, Dmitri S. Katz, Amid Ayobi et al.

Type 1 Diabetes (T1D) self-management requires hundreds of daily decisions. Diabetes technologies that use machine learning have significant potential to simplify this process and provide better decision support, but often rely on cumbersome data logging and cognitively demanding reflection on collected data. We set out to use co-design to identify opportunities for machine learning to support diabetes self-management in everyday settings. However, over nine months of interviews and design workshops with 15 people with T1D, we had to re-assess our assumptions about user needs. Our participants reported confidence in their personal knowledge and rejected machine learning based decision support when coping with routine situations, but highlighted the need for technological support in the context of unfamiliar or unexpected situations (holidays, illness, etc.). However, these are the situations where prior data are often lacking and drawing data-driven conclusions is challenging. Reflecting this challenge, we provide suggestions on how machine learning and other artificial intelligence approaches, e.g., expert systems, could enable decision-making support in both routine and unexpected situations.

R. Baki, Mouneeta Rahman, Nawreen Anan Khandakar et al.

Children need assistance to learn basic drawing in school. However, it may not always be possible for a teacher to assist every individual separately, especially in a school with a large number of students in each class. This research aims to design and develop a robotic system to help children learn how to draw basic shapes. While the use of robotic arms has been explored in various fields such as industry and biomedicine, little attention has been given to assisting children in drawing basic shapes. To achieve this objective, a system was developed that consists of an android-based mobile application and a robotic arm. The application allows users to upload a picture of a shape or alphabet, convert it into line art, and then send the necessary instructions to the robotic arm. Based on these instructions, the robotic arm demonstrates the drawing steps to help children learn. The application also has the ability to evaluate the accuracy of the user's drawing. Finally, the effectiveness of the system's features was tested with a group of children in a laboratory environment, and it was found that the proposed system effectively supports children in basic sketching.

Tossaporn Udomsap, Sakda Chinchouryrang, Siwat Liampipat et al.

Abstract In this paper, a 3-PRS (prismatic, revolute, and spherical) parallel manipulator for platform stabilization is designed. The main purpose of this device is to stabilize visual equipment, which is placed on top of a car to inspect electrical transmission cables, as part of routine maintenance. Due to the bulky and heavy infrared cameras used during inspections, a stabilizer platform has been designed to handle the weight of camera equipment up to 10 kg. This device consists of two major mechanisms. The first mechanism is able to adjust the angle of the camera. Thus, the user can focus the camera along the electric transmission lines. The second mechanism is stabilization. The mechanism serves to stabilize the orientation and position of the camera in the roll, pitch, and heave directions. To test the performance of the stabilization mechanism, the device is fed with the known value of the angle with regard to the input. As such, the device is trying to compensate for the change in angle. The results show that the errors between the input angles and compensated angles are in the range of 0.4–3%. Errors are seen to be within an acceptable range. It is significant that the resultant errors do not affect the orientation of the camera.

Abel Ortego, Sofia Russo, Marta Iglesias-Émbil et al.

Light-duty vehicles are increasingly incorporating plastic materials to reduce production costs and achieve lightweight designs. On average, a conventional car utilizes over 200 kg of plastic, comprising more than 23 different types, which often present challenges for recycling due to their incompatibility. Consequently, the focus on plastic recycling in end-of-life vehicles has intensified. This study aims to analyze critical car parts based on the plastics used, employing a novel thermodynamic approach that examines the embodied exergy (EE) of different plastics. Six vehicles from various segments, years, and equipment levels were assessed to understand their plastic compositions. The findings reveal that, on average, a vehicle contains 222 kg of plastic, accounting for 17.7% of its total weight. Among these plastics, 47.5% (105 kg) are utilized in car parts weighing over 1 kg, with plastics comprising over 80% of the part’s weight. The identified critical car parts include the front door trim panel, front and rear covers, fuel tank, floor covering, front lighting, dashboard, rear door trim panel, plastic front end, backrest pad, door trim panel pocket, plastic foam rear seat, rear lighting, window guide, molded headliner, bulkhead sound insulation, foam seat part, and wheel trim. Regarding their contribution to EE, the plastics with the highest shares are polypropylene—PP (24.5%), polypropylene and ethylene blends—E/P (20.3%), and polyurethane- PU (15.3%). Understanding the criticality of these car parts and their associated plastics enables targeted efforts in design, material selection, and end-of-life management to enhance recycling and promote circularity within the automotive industry.

Ute Schultheiß, Rita Zapf, Jan Brinkmann et al.

Tierhalter sollen das Wohlergehen ihrer Tiere regelmäßig und systematisch durch die Erfassung von Tierschutzindikatoren im Rahmen einer betrieblichen Eigenkontrolle überprüfen (§ 11 Absatz 8 TierSchG). Hierdurch können mögliche Tierwohlprobleme frühzeitig erkannt und Verbesserungsmaßnahmen eingeleitet werden. Für eine Vergleichbarkeit der Ergebnisse einer betrieblichen Eigenkontrolle ist eine standardisierte Erhebung der Tierschutzindikatoren Voraussetzung. Ziel der Arbeiten war es, für die betriebliche Eigenkontrolle vorgeschlagene Indikatoren für Rind, Schwein und Geflügel in der landwirtschaftlichen Praxis auf ihre Praktikabilität zu überprüfen. Zum Erlernen der Anwendung der Indikatoren wurden eine Vor-Ort- und eine Online-Schulung für Tierhalter erarbeitet und getestet. Zur Unterstützung der Erhebung im Stall wurden Erhebungsbögen und eine Excel®-Anwendung erstellt. Weiterhin wurde unter Einbeziehung zahlreicher Experten in einem mehrstufigen Prozess (Delphi-Befragung, Literaturauswertung, Fachgespräche, Praxiserhebungen) ein Orientierungsrahmen mit Ziel- und Alarmwerten abgestimmt, mit dem Tierhalter ihre Ergebnisse vergleichen und einordnen können. Mittels abschließend durchgeführter Interviews wurden alle Werkzeuge evaluiert.

Mehnaz Tabassum, Felipe Henrique Bastos, Aurenice Oliveira et al.

The Third Generation Partnership Project (3GPP) has specified Cellular Vehicle-to-Everything (C-V2X) radio access technology in Releases 15–17, with an emphasis on facilitating direct communication between vehicles through the interface, sidelink PC5. This interface provides end-to-end network slicing functionality together with a stable cloud-native core network. The performance of direct vehicle-to-vehicle (V2V) communications has been improved by using the sidelink interface, which allows for a network infrastructure bypass. Sidelink transmissions make use of orthogonal resources that are either centrally allocated (Mode 1, Release 14) or chosen by the vehicles themselves (Mode 2, Release 14). With growing interest in connected and autonomous vehicles, the advancement in radio access technologies that facilitate dependable and low-latency vehicular communications is becoming more significant. This is especially necessary when there are heavy traffic conditions and patterns. We thoroughly examined the New Radio (NR) sidelink’s performance based on 3GPP Releases 15–17 under various vehicle densities, speeds, and distance settings. Thus, by evaluating sidelink’s strengths and drawbacks, we are able to optimize resource allocation to obtain maximum coverage in urban areas. The performance evaluation was conducted on Network Simulator 3 (NS3.34/5G-LENA) utilizing various network metrics such as average packet reception rate, throughput, and latency.

Ermioni Qafzezi, Kevin Bylykbashi, Shunya Higashi et al.

Vehicular Ad Hoc Networks (VANETs) have gained significant attention due to their potential to enhance road safety, traffic efficiency, and passenger comfort through vehicle-to-vehicle and vehicle-to-infrastructure communication. However, VANETs face resource management challenges due to the dynamic and resource constrained nature of vehicular environments. Integrating cloud-fog-edge computing and Software-Defined Networking (SDN) with VANETs can harness the computational capabilities and resources available at different tiers to efficiently process and manage vehicular data. In this work, we used this paradigm and proposed an intelligent approach based on Fuzzy Logic (FL) to evaluate the processing and storage capability of vehicles for helping other vehicles in need of additional resources. The effectiveness of the proposed system is evaluated through extensive simulations and a testbed. Performance analysis between the simulation results and the testbed offers a comprehensive understanding of the proposed system and its performance and feasibility.

Petr Hliněný, Tomáš Masařík

In this paper, we introduce the following new concept in graph drawing. Our task is to find a small collection of drawings such that they all together satisfy some property that is useful for graph visualization. We propose investigating a property where each edge is not crossed in at least one drawing in the collection. We call such collection uncrossed. This property is motivated by a quintessential problem of the crossing number, where one asks for a drawing where the number of edge crossings is minimum. Indeed, if we are allowed to visualize only one drawing, then the one which minimizes the number of crossings is probably the neatest for the first orientation. However, a collection of drawings where each highlights a different aspect of a graph without any crossings could shed even more light on the graph's structure. We propose two definitions. First, the uncrossed number, minimizes the number of graph drawings in a collection, satisfying the uncrossed property. Second, the uncrossed crossing number, minimizes the total number of crossings in the collection that satisfy the uncrossed property. For both definitions, we establish initial results. We prove that the uncrossed crossing number is NP-hard, but there is an FPT algorithm parameterized by the solution size.

Carla Binucci, Henry Förster, Julia Katheder et al.

Partial edge drawings (PED) of graphs avoid edge crossings by subdividing each edge into three parts and representing only its stubs, i.e., the parts incident to the end-nodes. The morphing edge drawing model (MED) extends the PED drawing style by animations that smoothly morph each edge between its representation as stubs and the one as a fully drawn segment while avoiding new crossings. Participants of a previous study on MED (Misue and Akasaka, GD19) reported eye straining caused by the animation. We conducted a user study to evaluate how this effect is influenced by varying animation speed and animation dynamic by considering an easing technique that is commonly used in web design. Our results provide indications that the easing technique may help users in executing topology-based tasks accurately. The participants also expressed appreciation for the easing and a preference for a slow animation speed.

Jonathan Klawitter, Johannes Zink

Our goal is to visualize an additional data dimension of a tree with multifaceted data through superimposition on vertical strips, which we call columns. Specifically, we extend upward drawings of unordered rooted trees where vertices have assigned heights by mapping each vertex to a column. Under an orthogonal drawing style and with every subtree within a column drawn planar, we consider different natural variants concerning the arrangement of subtrees within a column. We show that minimizing the number of crossings in such a drawing can be achieved in fixed-parameter tractable (FPT) time in the maximum vertex degree $Δ$ for the most restrictive variant, while becoming NP-hard (even to approximate) already for a slightly relaxed variant. However, we provide an FPT algorithm in the number of crossings plus $Δ$, and an FPT-approximation algorithm in $Δ$ via a reduction to feedback arc set.

G. N, S. M, Sargurunathan R et al.

The CNC (Computer Numerical Control) machine is an advanced technology that has an automated system that controls multiple machine tools using a computer. Computer Numerical Control revolutionized manufacturing, or it’s apt to say that it has taken manufacturing to a new phase. This work presents the demonstration of a low-cost Human Machine Interface for a 3- axis CNC machine. The Work that seemed impossible and took a lot of time to complete now can be accomplished with minimal effort quick and accurate manner, and as it is computerized the margin of error is diminished. The programming language for CNCs is done using G-code. Our paper focuses on fabricating a desktop-size CNC machine using the X, Y, and Z axes for performing/carrying out various functions like drawing and light-duty cutting for PCB using a microcontroller. The machine is fabricated and tested experimentally to enhance its working, robustness, and accuracy in diverse conditions. By utilizing the advanced voice-controlled CNC, the proposed study has cut down the time consumed for these processes. The input is given using software or voice control components. The methods involve the unrestricted Domain for analyzing and recognizing input.

Hujun Peng, Jianxiang Li, Kai Deng et al.

In this work, a machine learning-based energy management system is developed using a long short-term memory (LSTM) network for fuel cell hybrid buses. The neural network implicitly learns the complex relationship between various factors and the optimal power control from massive data. The selection of the neural network inputs is inspired by the adaptive Pontryagin’s minimum principle (APMP) strategy. Since an estimated value of the global average fuel cell power is required in the machine learning-based energy management strategy (EMS), some global features of driving cycles are extracted and then applied in a feedforward neural network to predict the average fuel cell power appropriately. The effectiveness of the machine learning-based energy management, with the integration of the mechanism of estimating the average fuel cell power based on the forward neural network, is tested under two different driving cycles from the training environment, with comparisons to a commercially used rule-based strategy. Based on the simulation results, the learning-based strategy outperforms the rule-based strategy regarding the charge-sustaining mode conditions and fuel economy. Moreover, compared to the best offline hydrogen consumption, the machine learning-based strategy consumed 0.58% and 0.36% more than the best offline results for both driving cycles. In contrast, the rule-based strategy consumed 1.80% and 0.96% more than optimal offline results for the two driving cycles, respectively. Finally, simulations under battery and fuel cell aging conditions show that the fuel economy of the machine learning-based strategy experiences no performance degradation under components aging compared to offline strategies.

Frederic Jacquelin, Jungyun Bae, Bo Chen et al.

The real-time application of powertrain-based predictive energy management (PrEM) brings the prospect of additional energy savings for hybrid powertrains. Torque split optimal control methodologies have been a focus in the automotive industry and academia for many years. Their real-time application in modern vehicles is, however, still lagging behind. While conventional exact and non-exact optimal control techniques such as Dynamic Programming and Model Predictive Control have been demonstrated, they suffer from the curse of dimensionality and quickly display limitations with high system complexity and highly stochastic environment operation. This paper demonstrates that Neuroevolution associated drive cycle classification algorithms can infer optimal control strategies for any system complexity and environment, hence streamlining and speeding up the control development process. Neuroevolution also circumvents the integration of low fidelity online plant models, further avoiding prohibitive embedded computing requirements and fidelity loss. This brings the prospect of optimal control to complex multi-physics system applications. The methodology presented here covers the development of the drive cycles used to train and validate the neurocontrollers and classifiers, as well as the application of the Neuroevolution process.

Tzu-Hsuan Hsia, Shogo Okamoto, Yasuhiro Akiyama et al.

Abstract Hum-noise-based touch sensors (HumTouch) are capable of recognizing human touch on semiconductive materials using the current leaking from the finger to the surface. Thus far, calibration for these hum-noise-based touch sensors has been performed for individual users because of the individual differences in hum-driven electric currents in human bodies. However, for applications designed for unknown users, time-consuming calibration for individual users is not preferred, and a new user should be able to use the sensor immediately. For this purpose, we propose a new calibration method for HumTouch. In this method, learning datasets collected from multiple people and a few extra samples from a new user are collectively used to establish a touch localization estimator. The estimator is computed using the kernel regression method with weighted samples from the new user. For a 20 $$\times $$ × 18 cm $$^2$$ 2 paper, the mean localization error is reduced from 1.24 cm to 0.90 cm with only one sample from the new user. Hence, a new user can establish a semipersonalized localization estimator by touching only one point on the surface. This method improves the localization performance of HumTouch sensors in an easy-to-access manner.