Hasil untuk "Machine design and drawing"

Muhammad Shoaib Hanif, Zubair Nawaz, Muhammad Kamran Malik

Intelligent transportation systems (ITSs) are crucial for modern traffic management and law enforcement. This paper addresses the challenge of monitoring and managing extensive vehicle traffic in large cities like Lahore, Pakistan. We propose a deep learning based ITS utilizing Vision Transformers combined with convolutional feature extraction to accurately identify vehicle type, color, make/model, and license plates. Experiments were conducted on a comprehensive dataset collected from multiple checkpoints across Lahore under varying environmental conditions. Our proposed model achieved high accuracy rates: 98.0% for vehicle type classification, 96.0% for color detection, 95.0% for make/model identification, and 89.0% for license plate recognition. These results demonstrate the system’s potential to significantly enhance traffic management and road safety and support law enforcement operations in developing urban environments.

P. W. C. Prasad, Md Shohel Sayeed, Duc-Man Nguyen et al.

The rapid growth of the Internet and the increasing reliance on digital systems have significantly expanded the global digital footprint, creating new challenges for cybersecurity. Artificial Intelligence (AI) technologies, particularly Machine Learning (ML) and Deep Learning (DL), have become central to addressing these challenges by enabling the automation of complex and data-intensive tasks across antivirus solutions, intrusion prevention systems, threat intelligence platforms, and email security tools. While these technologies provide high levels of accuracy in detecting anomalies, malware, and other forms of malicious activity, they are often criticized for operating as “black-box” systems. The lack of interpretability in their decision-making processes limits the ability of cybersecurity professionals to fully understand, validate, and trust the outcomes of AI-driven models, thereby restricting their practical adoption in high-stakes environments. To mitigate these limitations, Explainable Artificial Intelligence (XAI) has emerged as a promising paradigm that aims to make AI outputs transparent, interpretable, and actionable. By providing human-understandable explanations of automated decisions, XAI can bridge the gap between technical performance and practitioner usability, enabling analysts to make informed decisions, improve incident response, and strengthen organizational resilience against both known and emerging threats. This paper reviews recent state-of-the-art developments in XAI for cybersecurity, with a particular emphasis on anomaly detection a critical area for identifying insider threats, zero-day exploits, and atypical system behavior. The review follows a structured literature analysis of peer-reviewed studies published between 2018 and 2025, identified through systematic searches in major academic databases including IEEE Xplore, Scopus, Web of Science, and ACM Digital Library. After applying predefined inclusion and exclusion criteria focused on XAI applications in cybersecurity, 53 relevant studies were analysed to synthesize methodological trends, application domains, and evaluation practices. Drawing on these findings, the paper consolidates fragmented research contributions, identifies current gaps, and provides recommendations for advancing the design and adoption of explainable, trustworthy AI systems in cybersecurity. The analysis further highlights a critical deployment challenge: the integration of explainability mechanisms often introduces trade-offs between predictive accuracy, computational efficiency, and real-time scalability factors that are essential in operational cybersecurity environments.

Pan Li, Yuwei Wang, Xiaoxian He et al.

Endowing flexible and adaptable fiber devices with light-emitting capabilities has the potential to revolutionize the current design philosophy of intelligent, wearable interactive devices. However, significant challenges remain in developing fiber devices when it comes to achieving uniform and customizable light effects while utilizing lightweight hardware. Here, we introduce a mass-produced, wearable, and interactive photochromic fiber that provides uniform multicolored light control. We designed independent waveguides inside the fiber to maintain total internal reflection of light as it traverses the fiber. The impact of excessive light leakage on the overall illuminance can be reduced by utilizing the saturable absorption effect of fluorescent materials to ensure light emission uniformity along the transmission direction. In addition, we coupled various fluorescent composite materials inside the fiber to achieve artificially controllable spectral radiation of multiple color systems in a single fiber. We prepared fibers on mass-produced kilometer-long using the thermal drawing method. The fibers can be directly integrated into daily wearable devices or clothing in various patterns and combined with other signal input components to control and display patterns as needed. This work provides a new perspective and inspiration to the existing field of fiber display interaction, paving the way for future human–machine integration.

Stefanos Laskaridis, Kleomenis Katevas, Lorenzo Minto et al.

Transformers have recently revolutionized the machine learning (ML) landscape, gradually making their way into everyday tasks and equipping our computers with "sparks of intelligence". However, their runtime requirements have prevented them from being broadly deployed on mobile. As personal devices become increasingly powerful at the consumer edge and prompt privacy becomes an ever more pressing issue, we explore the current state of mobile execution of Large Language Models (LLMs). To achieve this, we have created our own automation infrastructure, MELT, which supports the headless execution and benchmarking of LLMs on device, supporting different models, devices and frameworks, including Android, iOS and Nvidia Jetson devices. We evaluate popular instruction fine-tuned LLMs and leverage different frameworks to measure their end-to-end and granular performance, tracing their memory and energy requirements along the way. Our analysis is the first systematic study of on-device LLM execution, quantifying performance, energy efficiency and accuracy across various state-of-the-art models and showcases the state of on-device intelligence in the era of hyperscale models. Results highlight the performance heterogeneity across targets and corroborates that LLM inference is largely memory-bound. Quantization drastically reduces memory requirements and renders execution viable, but at a non-negligible accuracy cost. Drawing from its energy footprint and thermal behavior, the continuous execution of LLMs remains elusive, as both factors negatively affect user experience. Last, our experience shows that the ecosystem is still in its infancy, and algorithmic as well as hardware break-throughs can significantly shift the execution cost. We expect NPU acceleration, and framework-hardware co-design to be the biggest bet towards efficient standalone execution, with the alternative of offloading tailored towards edge deployments.

Warmhold Jan Thomas Mollema

The development and deployment of machine learning and AI engender 'AI colonialism', a term that conceptually overlaps with 'data colonialism', as a form of injustice. AI colonialism is in need of decolonization for three reasons. Politically, because it enforces digital capitalism's hegemony. Ecologically, as it negatively impacts the environment and intensifies the extraction of natural resources and consumption of energy. Epistemically, since the social systems within which AI is embedded reinforce Western universalism by imposing Western colonial values on the global South when these manifest in the digital realm is a form of digital capitalism. These reasons require a new conceptualization of AI decolonization. First this paper draws from the historical debates on the concepts of colonialism and decolonization. Secondly it retrieves Achille Mbembe's notion of decolonization as disenclosure to argue that the decolonization of AI will have to be the abolishment of political, ecological and epistemic borders erected and reinforced in the phases of its design, production, development of AI in the West and drawing from the knowledge from the global South. In conclusion, it is discussed how conceiving of decolonial AI as form of disenclosure opens up new ways to think about and intervene in colonial instantiations of AI development and deployment, in order to empower 'the wretched of AI', re-ecologise the unsustainable ecologies AI depends on and to counter the colonial power structures unreflective AI deployment risks to reinforce.

Suyog H. Chandramouli, Danqing Shi, Aini Putkonen et al.

Computational rationality explains human behavior as arising due to the maximization of expected utility under the constraints imposed by the environment and limited cognitive resources. This simple assumption, when instantiated via partially observable Markov decision processes (POMDPs), gives rise to a powerful approach for modeling human adaptive behavior, within which a variety of internal models of cognition can be embedded. In particular, such an instantiation enables the use of methods from reinforcement learning (RL) to approximate the optimal policy solution to the sequential decision-making problems posed to the cognitive system in any given setting; this stands in contrast to requiring ad hoc hand-crafted rules for capturing adaptive behavior in more traditional cognitive architectures. However, despite their successes and promise for modeling human adaptive behavior across everyday tasks, computationally rational models that use RL are not easy to build. Being a hybrid of theoretical cognitive models and machine learning (ML) necessitates that model building take into account appropriate practices from both cognitive science and ML. The design of psychological assumptions and machine learning decisions concerning reward specification, policy optimization, parameter inference, and model selection are all tangled processes rife with pitfalls that can hinder the development of valid and effective models. Drawing from a decade of work on this approach, a workflow is outlined for tackling this challenge and is accompanied by a detailed discussion of the pros and cons at key decision points.

Ilia Panfilov, Dmitry Tikhonenko, Kirill Kravtsov et al.

This article discusses the principles of modeling the casting process for casting a part - a "flywheel" made of cast iron SCH20. A detailed overview of the casting drawing is provided, as well as the designed 3D model according to this drawing. The values of allowances for the machining of the part are analyzed. The characteristic of the obtained alloy is presented, on the basis of which the calculation of the technological yield of the suitable one is made. At the end of the article, the result of the output of a suitable casting is given.

Tania Elizabeth Sandoval-Valencia, Gerardo Hurtado-Hurtado, Eric Leonardo Huerta-Manzanilla et al.

The presence of contaminants influences braking efficiency in the railway system because it alters the adhesion at the wheel–rail interface. It is essential to study this phenomenon, as contaminants reduce the friction between wheels and rails, which impacts braking and transport safety. In addition, these contaminants increase the risk of derailments. The objective of the research was to determine the impact of different contaminants and operating speeds on the critical braking system’s responses. Using the 3^k full factorial experimental design methodology, with analysis of variance (ANOVA) and linear and quadratic regressions, visualized using surface graphs, the effects of three operating conditions were studied: clean rails, with sand and sawdust, and driving the train at three operating speeds. These conditions gave rise to variations in braking distances, maximum creep, wheel slip times, and maximum peaks of electric current when braking in each experiment. The tests were carried out on the straight section of a β-shaped track and a railway vehicle, designed at a scale of 1:20. The analysis reveals that the braking distance increases significantly with surface roughness (clean track < sawdust < sand). At 0.75 m/s, the sawdust track reduces braking distance by 21% compared with the clean track; at 1.00 m/s, the reduction is 19%; and at 1.30 m/s, it is 35%.

Kai-Chao Yao, Ya-Nan Chang, Li-Yun Chen et al.

This study investigates the innovative design of a bicycle saddle by incorporating sustainable ergonomics, universal design principles, and systematic innovation methods. Initially, the literature related to bicycle saddle design and its impact on the human body during riding was analyzed. The TRIZ contradiction matrix was then used to identify relevant invention principles, which served as references for the innovative design of the bicycle saddle. Biomechanics and the human–machine system analysis within human factors engineering were applied to ensure the innovative design is ergonomic and user-friendly. The design features a horizontally expandable and foldable bicycle saddle, enhancing its adaptability and sustainability. Universal design principles were applied to make the innovative design more accessible to the general public, and the prototype was simulated using Inventor drawing software. The research results include: (1) An innovative bicycle saddle design with horizontal expansion and folding functions is proposed. This design divides the saddle into three components, enabling the left and right parts to expand or retract based on user preferences. (2) A bicycle backrest design featuring vertical adjustability is introduced. It incorporates a quick-release adjustment mechanism at the junction of the backrest and saddle, allowing users to freely adjust the backrest height. (3) A quick-operation bicycle saddle design is presented, utilizing quick-release screws to facilitate the swift operation of the horizontal expansion and folding mechanisms. This validation method confirmed that the innovative design meets both sustainable ergonomic standards and user expectations. The systematic innovation approach used in this study can serve as a valuable reference for future research and design applications.

Vaishali Mahipal, Srija Ghosh, I. Sanusi et al.

To introduce middle school students to key concepts in image recognition, we created an interactive web application that performs sketch recognition and an afterschool curriculum for its use. Our app, called DoodleIt, was inspired by Google’s Quick, Draw!, and makes use of its accompanying open-source sketch library. With DoodleIt, students make simple line drawings on a canvas area and a previously-trained convolutional neural network (CNN) identifies the object drawn. The application dynamically visualizes the different layers that are involved in the process of CNNs, including a display of kernels, the resulting feature maps, and the percentage of match at output neurons. We used DoodleIt in an 18-hour curriculum to introduce middle school students to artificial intelligence, machine learning, and data science. Four hours of content were related to image recognition and the ethics of using AI. Here, we describe the design of the DoodleIt application, the approach we used to introduce the associated ideas to the students, and how we assessed student learning. Qualitative data collected from students are presented and discussed. Our findings indicate that students were able to understand the functionality of the kernels and feature maps involved in the CNN to perform rudimentary image recognition.

Han Tu, Yichao Shi, Meng Xu

P. Helm, G. Bella, G. Koch et al.

It is well known that AI-based language technology -- large language models, machine translation systems, multilingual dictionaries, and corpora -- is currently limited to 2 to 3 percent of the world's most widely spoken and/or financially and politically best supported languages. In response, recent research efforts have sought to extend the reach of AI technology to ``underserved languages.'' In this paper, we show that many of these attempts produce flawed solutions that adhere to a hard-wired representational preference for certain languages, which we call techno-linguistic bias. Techno-linguistic bias is distinct from the well-established phenomenon of linguistic bias as it does not concern the languages represented but rather the design of the technologies. As we show through the paper, techno-linguistic bias can result in systems that can only express concepts that are part of the language and culture of dominant powers, unable to correctly represent concepts from other communities. We argue that at the root of this problem lies a systematic tendency of technology developer communities to apply a simplistic understanding of diversity which does not do justice to the more profound differences that languages, and ultimately the communities that speak them, embody. Drawing on the concept of epistemic injustice, we point to the broader sociopolitical consequences of the bias we identify and show how it can lead not only to a disregard for valuable aspects of diversity but also to an under-representation of the needs and diverse worldviews of marginalized language communities.

Zongren Zou, Xuhui Meng, Apostolos F. Psaros et al.

Uncertainty quantification (UQ) in machine learning is currently drawing increasing research interest, driven by the rapid deployment of deep neural networks across different fields, such as computer vision, natural language processing, and the need for reliable tools in risk-sensitive applications. Recently, various machine learning models have also been developed to tackle problems in the field of scientific computing with applications to computational science and engineering (CSE). Physics-informed neural networks and deep operator networks are two such models for solving partial differential equations and learning operator mappings, respectively. In this regard, a comprehensive study of UQ methods tailored specifically for scientific machine learning (SciML) models has been provided in [45]. Nevertheless, and despite their theoretical merit, implementations of these methods are not straightforward, especially in large-scale CSE applications, hindering their broad adoption in both research and industry settings. In this paper, we present an open-source Python library (https://github.com/Crunch-UQ4MI), termed NeuralUQ and accompanied by an educational tutorial, for employing UQ methods for SciML in a convenient and structured manner. The library, designed for both educational and research purposes, supports multiple modern UQ methods and SciML models. It is based on a succinct workflow and facilitates flexible employment and easy extensions by the users. We first present a tutorial of NeuralUQ and subsequently demonstrate its applicability and efficiency in four diverse examples, involving dynamical systems and high-dimensional parametric and time-dependent PDEs.

Yuri Nakao, Simone Stumpf, Subeida Ahmed et al.

Tengxiang Zhang, Zitong Lan, Chenren Xu et al.

Spontaneous selection of IoT devices from the head-mounted device is key for user-centered pervasive interaction. BLEselect enables users to select an unmodified Bluetooth 5.1 compatible IoT device by nodding at, pointing at, or drawing a circle in the air around it. We designed a compact antenna array that fits on a pair of smart glasses to estimate the Angle of Arrival (AoA) of IoT and wrist-worn devices' advertising signals. We then developed a sensing pipeline that supports all three selection gestures with lightweight machine learning models, which are trained in real-time for both hand gestures. Extensive characterizations and evaluations show that our system is accurate, natural, low-power, and privacy-preserving. Despite the small effective size of the antenna array, our system achieves a higher than 90% selection accuracy within a 3 meters distance in front of the user. In a user study that mimics real-life usage cases, the overall selection accuracy is 96.7% for a diverse set of 22 participants in terms of age, technology savviness, and body structures.

Zhenyu Wang, Gen Endo, Hideharu Takahashi et al.

Abstract In order to improve spatial awareness for future investigations of reactor No. 2 at the Fukushima nuclear power plant, it is necessary first to acquire the environment model through reconstruction. To gather images for this task, we have developed a flexible, compact, and lightweight manipulator called the Bundled Wire Drive robot. However, due to mechanism’ shortcomings, the feasibility of using this robot is limited by potential degradations of image quality, including odometry deviation and motion blur. Based on the motion characteristics of the robot, we have proposed a dataset creation and selection method to mitigate the impact of these degradations. The effectiveness of this method was verified through experiments with a hardware prototype robot, which demonstrates that it is possible to avoid the influence of matched joint movement deviation by using overlapping simple trajectories; and pre-filtering out blurry images, which usually concentrate on the beginning and stopping periods. Additionally, we conducted a robustness study of mainstream reconstruction methods under limited illumination conditions to quantitively study the performance degradation in a more realistic environment.

Lena Guinot, Kozo Ando, Shota Takahashi et al.

Abstract Body language is an essential component of communication. The amount of unspoken information it transmits during interpersonal interactions is an invaluable complement to simple speech and makes the process smoother and more sustainable. On the contrary, existing approaches to human–machine collaboration and communication are not as intuitive. This is an issue that needs to be addressed if we aim to continue using artificial intelligence and machines to increase our cognitive or even physical capabilities. In this study, we analyse the potential of an intuitive communication method between biological and artificial agents, based on machines understanding and learning the subtle unspoken and involuntary cues found in human motion during the interaction process. Our work was divided into two stages: the first, analysing whether a machine using these implicit cues would produce the same positive effect as when they are manifested in interpersonal communication; the second, evaluating whether a machine could identify the cues manifested in human motion and learn (through the use of Long-Short Term Memory Networks) to associate them with the appropriate command intended from its user. Promising results were gathered, showing an improved work performance and reduced cognitive load on the user side when relying on the proposed method, hinting to the potential of more intuitive, human to human inspired, communication methods in human–machine interaction.

Konstantinos Kouretas, Konstantinos Kepaptsoglou

Using Unmanned Aerial Vehicles (UAVs), commonly referred to as “drones”, as a supplementary mode for last-mile deliveries has been a research focus for some years now. Motivation lies in the reduced dependency on Conventional Vehicles (CVs) and fossil fuels and in serving remote areas and underprivileged populations. We are building a flexible, modular framework for integrated CV-UAV parcel delivery operations planning that is responsive to infrastructure and demand and offers an open and practical tool for future adaptations. The entire model and solution methodology are practical tools for decision making and strategic planning, with novelties such as the variable Launch Site types for Launch and Recovery Operations (LAROs), the tailored Assignment and Routing Optimization nested GA, the consideration of airspace restrictions of any shape and size, the inclusion of GIS tools in the process, the modularity of the platform, and most importantly, the inclusion of all the above in a single, comprehensive, and holistic approach. Because of the need for safe UAV deployment sites and the high presence of restricted airspace zones in urban environments, the intended field of application is assumed to be the delivery of small packages in rural and under-connected areas, the execution of inter-city deliveries, and the expansion of a city’s original service range. A single CV is equipped onboard with UAVs, while special locations, such as Remote Depots (RDs) with UAVs and Virtual Hubs (VHs) for UAV deployment facilitation, are introduced. The framework considers the presence of Restricted Zones (RZs) for UAV flights. Part of the methodology is implemented in a GIS environment, taking advantage of modern tools for spatial analysis and optimal path planning. We have designed a tailored nested GA method for solving the occurring mode assignment and vehicle routing optimization problems and have implemented our workflow on a devised case study with benchmark characteristics. Our model responds well to unfavorable network types and demand locations, while the presence of RZs notably affects the expected solution and should be considered in the decision-making process.

Priyanka Ramasamy, Enrique Calderon-Sastre, Gunarajulu Renganathan et al.

Abstract Dexterity training helps improve our motor skills while engaging in precision tasks such as surgery in the medical field and playing musical instruments. In addition, post-stroke recovery also requires extensive dexterity training to recover the original motor skills associated with the affected portion of the body. Recent years have seen a rise in the usage of soft-type actuators to perform such training, giving higher levels of comfort, compliance, portability, and adaptability. Their capabilities of performing high dexterity and safety enhancement make them specific biomedical applications and serve as a sensitive tools for physical interaction. The scope of this article discusses the soft actuator types, characterization, sensing, and control based on the interaction modes and the 5 most relevant articles that touch upon the skill improvement models and interfacing nature of the task and the precision it demands. This review attempts to report the latest developments that prioritize soft materials over hard interfaces for dexterity training and prospects of end-user satisfaction.

Yuri Nakao, Simone Stumpf, Subeida Ahmed et al.

Ensuring fairness in artificial intelligence (AI) is important to counteract bias and discrimination in far-reaching applications. Recent work has started to investigate how humans judge fairness and how to support machine learning (ML) experts in making their AI models fairer. Drawing inspiration from an Explainable AI (XAI) approach called \emph{explanatory debugging} used in interactive machine learning, our work explores designing interpretable and interactive human-in-the-loop interfaces that allow ordinary end-users without any technical or domain background to identify potential fairness issues and possibly fix them in the context of loan decisions. Through workshops with end-users, we co-designed and implemented a prototype system that allowed end-users to see why predictions were made, and then to change weights on features to"debug"fairness issues. We evaluated the use of this prototype system through an online study. To investigate the implications of diverse human values about fairness around the globe, we also explored how cultural dimensions might play a role in using this prototype. Our results contribute to the design of interfaces to allow end-users to be involved in judging and addressing AI fairness through a human-in-the-loop approach.