Hasil untuk "Machine design and drawing"

Anny Isabella Díaz-Molina, Sergio Ivvan Valdez, Eusebio E. Hernández

This work addresses the challenges of airline planning, which requires the integration of flight scheduling, aircraft availability, and maintenance to ensure both airworthiness and profitability. Current solutions, often developed by human experts, are susceptible to bias and may yield suboptimal results due to the inherent complexity of the problem. Furthermore, existing state-of-the-art approaches often inadequately address critical factors, such as maintenance, variable flight numbers, discrete time slots, and potential flight repetition. This paper presents a novel approach to aircraft routing optimization using a model that incorporates critical constraints, including path connectivity, flight duration, maintenance requirements, turnaround times, and closed routes. The proposed solution employs a simulated annealing algorithm enhanced with specialized perturbation operators and constraint-handling techniques. The main contributions are twofold: the development of an optimization model tailored to small airlines and the design of operators capable of efficiently solving large-scale, realistic scenarios. The method is validated using established benchmarks from the literature and a real case study from a Mexican commercial airline, demonstrating its ability to generate feasible and competitive routing configurations.

Anu Agarwal, Mihir Pamnani, Dilek Hakkani-Tur

The undesired memorization of sensitive information by Large Language Models (LLMs) has emphasized the need for safety mechanisms that can regulate model behavior. This has led to the development of machine unlearning techniques that enable models to precisely forget sensitive and unwanted information. For machine unlearning, first-order and second-order optimizer-based methods have shown significant progress in enabling LLMs to forget targeted information. However, in doing so, these approaches often compromise the model's original capabilities, resulting in unlearned models that struggle to retain their prior knowledge and overall utility. To address this, we propose Selective Influence Machine Unlearning (SIMU), a two-step framework that enhances second-order optimizer-based unlearning by selectively updating only the critical neurons responsible for encoding the forget-set. By constraining updates to these targeted neurons, SIMU achieves comparable unlearning efficacy while substantially outperforming current methods in retaining the model's original knowledge.

Luca Franceschi, Michele Donini, Valerio Perrone et al.

Hyperparameters are configuration variables controlling the behavior of machine learning algorithms. They are ubiquitous in machine learning and artificial intelligence and the choice of their values determines the effectiveness of systems based on these technologies. Manual hyperparameter search is often time-consuming and becomes infeasible when the number of hyperparameters is large. Automating the search is an important step towards advancing, streamlining, and systematizing machine learning, freeing researchers and practitioners alike from the burden of finding a good set of hyperparameters by trial and error. In this survey, we present a unified treatment of hyperparameter optimization, providing the reader with examples, insights into the state-of-the-art, and numerous links to further reading. We cover the main families of techniques to automate hyperparameter search, often referred to as hyperparameter optimization or tuning, including random and quasi-random search, bandit-, model-, population-, and gradient-based approaches. We further discuss extensions, including online, constrained, and multi-objective formulations, touch upon connections with other fields, such as meta-learning and neural architecture search, and conclude with open questions and future research directions.

Edward Berman, Jacob Ginesin

Julia has been heralded as a potential successor to Python for scientific machine learning and numerical computing, boasting ergonomic and performance improvements. Since Julia's inception in 2012 and declaration of language goals in 2017, its ecosystem and language-level features have grown tremendously. In this paper, we take a modern look at Julia's features and ecosystem, assess the current state of the language, and discuss its viability and pitfalls as a replacement for Python as the de-facto scientific machine learning language. We call for the community to address Julia's language-level issues that are preventing further adoption.

Jesher Joshua M, Ragav V, Syed Ibrahim S P

The maintenance, archiving and usage of the design drawings is cumbersome in physical form in different industries for longer period. It is hard to extract information by simple scanning of drawing sheets. Converting them to their digital formats such as Computer-Aided Design (CAD), with needed knowledge extraction can solve this problem. The conversion of these machine drawings to its digital form is a crucial challenge which requires advanced techniques. This research proposes an innovative methodology utilizing Deep Learning methods. The approach employs object detection model, such as Yolov7, Faster R-CNN, to detect physical drawing objects present in the images followed by, edge detection algorithms such as canny filter to extract and refine the identified lines from the drawing region and curve detection techniques to detect circle. Also ornaments (complex shapes) within the drawings are extracted. To ensure comprehensive conversion, an Optical Character Recognition (OCR) tool is integrated to identify and extract the text elements from the drawings. The extracted data which includes the lines, shapes and text is consolidated and stored in a structured comma separated values(.csv) file format. The accuracy and the efficiency of conversion is evaluated. Through this, conversion can be automated to help organizations enhance their productivity, facilitate seamless collaborations and preserve valuable design information in a digital format easily accessible. Overall, this study contributes to the advancement of CAD conversions, providing accurate results from the translating process. Future research can focus on handling diverse drawing types, enhanced accuracy in shape and line detection and extraction.

Lucas Koch, Dennis Roeser, Kevin Badalian et al.

Automotive control functions are becoming increasingly complex and their development is becoming more and more elaborate, leading to a strong need for automated solutions within the development process. Here, reinforcement learning offers a significant potential for function development to generate optimized control functions in an automated manner. Despite its successful deployment in a variety of control tasks, there is still a lack of standard tooling solutions for function development based on reinforcement learning in the automotive industry. To address this gap, we present a flexible framework that couples the conventional development process with an open-source reinforcement learning library. It features modular, physical models for relevant vehicle components, a co-simulation with a microscopic traffic simulation to generate realistic scenarios, and enables distributed and parallelized training. We demonstrate the effectiveness of our proposed method in a feasibility study to learn a control function for automated longitudinal control of an electric vehicle in an urban traffic scenario. The evolved control strategy produces a smooth trajectory with energy savings of up to 14%. The results highlight the great potential of reinforcement learning for automated control function development and prove the effectiveness of the proposed framework.

El Santty Mohamed Ibrahim, Zaher Hegazy Mohamed, Saeid Naglaa Ragaa

Measuring the organization’s performance is essential for continuous improvement and operational excellence. Appropriate organizational measures include multiple dimensions. The relative importance of the multiple dimensions varies depending on the organization’s context and the management team’s visions. The vagueness and ambiguity in the management team’s perspective toward the dimensions and associated sub-indicators show fuzzy property. This paper aims to synthesize the overall organization performance in one aggregated index, engage the management team through index formulation, deal with ambiguity and vagueness in the management team perspective using fuzzy mathematics, and use the synthesized index in monitoring and controlling the organization’s performance to achieve operational excellence. The proposed approach is implemented in manufacturing organizations to prove practicality. The implementation of the proposed method shows a positive impact on the organization’s performance monitoring as the management team focused on one measure. Furthermore, it has engaged the management team in selecting and weighing the leading group and associated KPIs. The R programming and Minitab 19 are used in the collected data processing.

Csete Mária Szalmáné, Baranyi Tímea

Cities across the globe perceive their opportunities for digital transition pathways. This paper presents a project and strategy-based assessment of smart city ambitions in the light of sustainable urban development pathways in the European Union capitals considering the programming period 2014-2020. The purpose of the research is to understand better the smart city trends in Europe and identify any correlation between smart city and sustainability ambitions through the European capitals. The basis of the research was the official project result platforms of European funds with priorities related to smart cities. The collected best practices of transnational smart city projects provide statistics from the previous programming period and draw attention to the developing trends of smart city functions and the activity level of European capitals in the digital transition. Results show that between 2014 and 2020 nearly half of the capitals owned a specific smart city strategic document. Evaluating the smart urban performance of the capitals, it can be stated that most smart solutions were implemented related to mobility and environment in the previous period. Furthermore, it was also considered whether smart city projects could facilitate the shift toward sustainability. Based on the assessment of their planning strategies, a complex image of the European capitals has been revealed in their smart city development concepts; their strategic-level planning can be understood better, which is essential for policymaking in the era of digitalisation, identifying synergies with sustainable urban development ambitions, and monitoring the reached targets at the city level.

Masahiro Inagawa, Tomohito Kawabe, Toshinobu Takei et al.

Abstract The construction industry faces a labor shortage problem, so construction vehicles need to be automated. For automation, a position estimation method is expected that is independent of the work environment and can accurately estimate the position of targets. This paper aims to develop a position estimation method for multiple construction vehicles using 3D LiDAR installed in a work environment. By focusing on the shape of construction vehicles, this method can estimate the location of construction vehicles in places where conventional methods cannot be used, such as valleys or roofs. Because the shape of the construction vehicle changes depending on the work equipment and steering operation, each joint angle was obtained, and the 3D model used for estimation was updated. As a result of the experiment, it was verified that the position and orientation of multiple construction vehicles can be estimated with an accuracy that satisfies the required accuracy.

Davide Cacciarelli, Murat Kulahci

Online active learning is a paradigm in machine learning that aims to select the most informative data points to label from a data stream. The problem of minimizing the cost associated with collecting labeled observations has gained a lot of attention in recent years, particularly in real-world applications where data is only available in an unlabeled form. Annotating each observation can be time-consuming and costly, making it difficult to obtain large amounts of labeled data. To overcome this issue, many active learning strategies have been proposed in the last decades, aiming to select the most informative observations for labeling in order to improve the performance of machine learning models. These approaches can be broadly divided into two categories: static pool-based and stream-based active learning. Pool-based active learning involves selecting a subset of observations from a closed pool of unlabeled data, and it has been the focus of many surveys and literature reviews. However, the growing availability of data streams has led to an increase in the number of approaches that focus on online active learning, which involves continuously selecting and labeling observations as they arrive in a stream. This work aims to provide an overview of the most recently proposed approaches for selecting the most informative observations from data streams in real time. We review the various techniques that have been proposed and discuss their strengths and limitations, as well as the challenges and opportunities that exist in this area of research.

Itay Grinberg, Alexandra Bremers, Louisa Pancoast et al.

In this demonstration, we exhibit the initial results of an ongoing body of exploratory work, investigating the potential for creative machines to communicate and collaborate with people through movement as a form of implicit interaction. The paper describes a Wizard-of-Oz demo, where a hidden wizard controls an AxiDraw drawing robot while a participant collaborates with it to draw a custom postcard. This demonstration aims to gather perspectives from the computational fabrication community regarding how practitioners of fabrication with machines experience interacting with a mixed-initiative collaborative machine.

Mathias Thor, P. Manoonpong

Legged robots have significant potential to operate in unstructured environments. The design of locomotion control is, however, still challenging. Currently, controllers must be manually designed for specific robots and tasks, or automatically designed via machine learning methods that require long training times and yield large opaque controllers. Drawing inspiration from animal locomotion, we propose a simple yet versatile modular neural control structure with fast learning. The key advantages of our approach are that behaviour-specific control modules can be added incrementally to obtain increasingly complex emergent locomotion behaviours, and that neural connections can be quickly and automatically learned. In a series of experiments, we show how eight modules can be quickly learned and added to a base control module to obtain emergent adaptive behaviours allowing a hexapod robot to navigate in complex environments. We also show that modules can be added and removed during operation without affecting the functionality of the remaining controller. Finally, the controller is successfully demonstrated on a physical robot. Taken together, our study reveals a significant step towards fast automatic design of versatile neural locomotion control. Controllers for robotic locomotion patterns deal with complex interactions and need to be carefully designed or extensively trained. Thor and Manoonpong present a modular approach for neural pattern generators that allows incremental and fast learning.

Rupesh Kumar Jha, Abhay Kumar, Satya Prakash et al.

Wireless power transfer (WPT) is a power transfer technique widely used in many industrial applications, medical applications, and electric vehicles (EVs). This paper deals with the dynamic modeling of the resonant inverter employed in the WPT systems for EVs. To this end, the Generalized State-Space Averaging and the Laplace Phasor Transform techniques have been the flagship methods employed so far. In this paper, the modeling of the resonant inverter is accomplished by using the novel Modulated Variable Laplace Transform (MVLT) method. Firstly, the MVLT technique is discussed in detail, and then it is applied to model a study-case resonant inverter. Finally, a study-case resonant inverter is developed and utilized to validate the theoretical results with MATLAB/Simulink.

Kumar Vijay Mishra, Ahmet M. Elbir, Amir I. Zaghloul

Metasurfaces (MTSs) are increasingly emerging as enabling technologies to meet the demands for multi-functional, small form-factor, efficient, reconfigurable, tunable, and low-cost radio-frequency (RF) components because of their ability to manipulate waves in a sub-wavelength thickness through modified boundary conditions. They enable the design of reconfigurable intelligent surfaces (RISs) for adaptable wireless channels and smart radio environments, wherein the inherently stochastic nature of the wireless environment is transformed into a programmable propagation channel. In particular, space-limited RF applications, such as communications and radar, that have strict radiation requirements are currently being investigated for potential RIS deployment. The RIS comprises sub-wavelength units or meta-atoms, which are independently controlled and whose geometry and material determine the spectral response of the RIS. Conventionally, designing RIS to yield the desired EM response requires trial and error by iteratively investigating a large possibility of various geometries and materials through thousands of full-wave EM simulations. In this context, machine/deep learning (ML/DL) techniques are proving critical in reducing the computational cost and time of RIS inverse design. Instead of explicitly solving Maxwell's equations, DL models learn physics-based relationships through supervised training data. The ML/DL techniques also aid in RIS deployment for numerous wireless applications, which requires dealing with multiple channel links between the base station (BS) and the users. As a result, the BS and RIS beamformers require a joint design, wherein the RIS elements must be rapidly reconfigured. This chapter provides a synopsis of DL techniques for both inverse RIS design and RIS-assisted wireless systems.

Mark Sendak, Gaurav Sirdeshmukh, Timothy Ochoa et al.

The approaches by which the machine learning and clinical research communities utilize real world data (RWD), including data captured in the electronic health record (EHR), vary dramatically. While clinical researchers cautiously use RWD for clinical investigations, ML for healthcare teams consume public datasets with minimal scrutiny to develop new algorithms. This study bridges this gap by developing and validating ML-DQA, a data quality assurance framework grounded in RWD best practices. The ML-DQA framework is applied to five ML projects across two geographies, different medical conditions, and different cohorts. A total of 2,999 quality checks and 24 quality reports were generated on RWD gathered on 247,536 patients across the five projects. Five generalizable practices emerge: all projects used a similar method to group redundant data element representations; all projects used automated utilities to build diagnosis and medication data elements; all projects used a common library of rules-based transformations; all projects used a unified approach to assign data quality checks to data elements; and all projects used a similar approach to clinical adjudication. An average of 5.8 individuals, including clinicians, data scientists, and trainees, were involved in implementing ML-DQA for each project and an average of 23.4 data elements per project were either transformed or removed in response to ML-DQA. This study demonstrates the importance role of ML-DQA in healthcare projects and provides teams a framework to conduct these essential activities.

Kara J Emery, Marina Zannoli, James Warren et al.

We present OpenNEEDS, the first large-scale, high frame rate, comprehensive, and open-source dataset of Non-Eye (head, hand, and scene) and Eye (3D gaze vectors) data captured for 44 participants as they freely explored two virtual environments with many potential tasks (i.e., reading, drawing, shooting, object manipulation, etc.). With this dataset, we aim to enable research on the relationship between head, hand, scene, and gaze spatiotemporal statistics and its applications to gaze estimation. To demonstrate the power of OpenNEEDS, we show that gaze estimation models using individual non-eye sensors and an early fusion model combining all non-eye sensors outperform all baseline gaze estimation models considered, suggesting the possibility of considering non-eye sensors in the design of robust eye trackers. We anticipate that this dataset will support research progress in many areas and applications such as gaze estimation and prediction, sensor fusion, human-computer interaction, intent prediction, perceptuo-motor control, and machine learning.

Yanmin Xie, Lin Du, Jiangbo Zhao et al.

J. Piri, B. Pirzadeh, B. Keshtegar et al.

Abstract The reliability of pumping stations is of great importance for the robust design of wastewater networks. In order to strike a balance between safe design and energy consumption of the pumping system, a complex performance function using multiple-failure mode under various uncertainties is required. In the present research to evaluate the failure probability of wastewater pumping station, a hybrid reliability analysis framework using artificial neural network (ANN) coupled by moment methods is proposed. Drawing upon genetic algorithm (GA), ANN model is trained to approximate the failure domain of the pump. The ANN is approximated input variables captured by the optimal condition of the rotational speed of the pump in turn it is obtained by GA. The main strength of the reliability method is to diminish the computational burden with accurate predictions of safety margin in the pumping systems of Zabol. The machine learning-based backpropagation (BP) for training feedforward neural networks using GA and gradient methods are compared for the regressed process of ANN models. This hybrid reliability framework involves three main levels including i) the pump rotational speed is minimized using GA as optimal hydraulic parameters such as inlet flow, static head, pumping head and outlet flow rate, ii) the limit sate function is approximated using ANN for optimal rotating speed pumps and iii) reliability analysis is disused using MCS and method of the moment for sewage pumping stations located at Zabol (Iran) station. Given the results, the machine learning-based GA for training ANN model provides accurate predictions compared to the ANN-based gradient method. Three moments of reliability method is an efficient and accurate approach to evaluate the reliable conditions of the pumping system.

Kelly B. Wagman, Lisa Parks

Machines, from artificially intelligent digital assistants to embodied robots, are becoming more pervasive in everyday life. Drawing on feminist science and technology studies (STS) perspectives, we demonstrate how machine designers are not just crafting neutral objects, but relationships between machines and humans that are entangled in human social issues such as gender and power dynamics. Thus, in order to create a more ethical and just future, the dominant assumptions currently underpinning the design of these human-machine relations must be challenged and reoriented toward relations of justice and inclusivity. This paper contributes the "social machine" as a model for technology designers who seek to recognize the importance, diversity and complexity of the social in their work, and to engage with the agential power of machines. In our model, the social machine is imagined as a potentially equitable relationship partner that has agency and as an "other" that is distinct from, yet related to, humans, objects, and animals. We critically examine and contrast our model with tendencies in robotics that consider robots as tools, human companions, animals or creatures, and/or slaves. In doing so, we demonstrate ingrained dominant assumptions about human-machine relations and reveal the challenges of radical thinking in the social machine design space. Finally, we present two design challenges based on non-anthropomorphic figuration and mutuality, and call for experimentation, unlearning dominant tendencies, and reimagining of sociotechnical futures.

Steffen Roth

Abstract This article outlines the basic design of digitally transformed social theory. We show that any digital world is created by the drawing and cross-tabling of binary distinctions. As any theory is supposed to be concerned with truth, we introduce to and insist on the distinction between true and false distinctions. We demonstrate how flexible matrix-shaped theory architectures based on true distinctions allow for the reduction and unfolding of the entire complexity of analogue social theories. The result of our demonstrations is the idea of a theoretical Supervacuus. The social equivalent of a universal Turing machine, this supervacuous social theory is virtually empty as it is based on only one proper theoretical premise (the idea of distinction [between true and false distinctions]), and therefore able to simulate all other social theory programmes. We conclude that our digitally transformed social theory design is particularly useful for observations of a digitally transformed society.