检索结果-内蒙古大学图书馆

23rd International Symposium on computers in Education, SIIE 2021

作者： Mamani, Nibeth Mena Garcia-Penalvo, Francisco Jose Conde, Miguel A. Goncalves, Jose InterAction and eLearning of Salamanca University GRIAL Research Group Salamanca Spain GRIAL Research Group InterAction and eLearning of Salamanca University Computer Science Department Salamanca Spain University of Leon Leon Spain Instituto Politécnico de Bragança Bragança Portugal

ISBN: (纸本)9781665440240

In recent years and after the strong impact of the last global health emergency (COVID-19) information and communication technologies have had a great impact on society but particular in the teaching-learning process. Education has been impacted at all its levels. Therefore, education models have been to be adapted to this new challenging paradigm by using different tools such as videoconferences, simulations, on-line interactive applications, virtual and remote laboratories, robots, *** objective of this work is to elaborate a systematic mapping to know what scientific from its beginning to 2020, identifying the most literature exists regarding simulators, remote and virtual laboratories focused on STEM/STEAM skills development in the educational context. To do so, bibliographical data gathered of four of the most popular and complete electronic databases (ACM, IEEE, Scopus and Web of science). At the begging we selected 1232 articles after applying the acceptance criteria defined as part of the search and select strategy, we had 61 articles that help us to answer some questions like what are the most popular virtual and remote labs? or what are the current trends and issues of these tools? and the future ones? © 2021 IEEE.

关键词： Mapping

Maximum and leaky maximum propagation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Fuhl, Wolfgang Department of Human Computer Interaction University Tübingen Tübingen72076 Germany

In this work, we present an alternative to conventional residual connections, which is inspired by maxout nets. This means that instead of the addition in residual connections, our approach only propagates the maximum value or, in the leaky formulation, propagates a percentage of both. In our evaluation, we show on different public data sets that the presented approaches are comparable to the residual connections and have other interesting properties, such as better generalization with a constant batch normalization, faster learning, and also the possibility to generalize without additional activation functions. In addition, the proposed approaches work very well if ensembles together with residual networks are formed. Code link: https://***/seafile/d/8e2ab8c3fdd444e1a135/?p=%2FMaximumPropagation&mode=list. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

Enhancing Consumer Electronics Security in Smart Homes with t-SNE Feature Selection and Seagull Optimized Deep Learning Model

学校读者我要写书评

暂无评论

Enhancing Consumer Electronics Security in Smart Homes with ...

IEEE International Conference on Consumer Electronics (ICCE)

作者： Akshat Gaurav Brij B. Gupta Kwok Tai Chui Ronin Institute Montclair NJ USA Department of Computer Science and Information Engineering Asia University Taichung 413 Taiwan & University of Economics and Human Science Warsaw Poland Hong Kong Metropolitan University (HKMU) Hong Kong

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

This work presents a t-SNE-based feature selection and Seagull Optimized Deep Learning Model to improve consumer electronics security in smart homes. Optimized using the Seagull Optimization Algorithm (SOA), the suggested Convolutional Neural Network (CNN) model showed exceptional performance with an accuracy of 92% in identifying cyber risks. The model routinely exceeded in both accuracy and loss measures when tested against conventional machine learning and deep learning models. T-SNE helped to choose important criteria that provide strong identification of harmful activity. Our method presents a major development in smart home security and a dependable instrument for reducing cybersecurity threats in a linked world.

关键词： Deep learning Accuracy Machine learning algorithms Smart homes Feature extraction Loss measurement Convolutional neural networks computer security Consumer electronics Optimization

Mixture Encoder for Joint Speech Separation and Recognition

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Berger, Simon Vieting, Peter Boeddeker, Christoph Schlüter, Ralf Haeb-Umbach, Reinhold Machine Learning and Human Language Technology Computer Science Department RWTH Aachen University Germany AppTek GmbH Germany Paderborn University Germany

Multi-speaker automatic speech recognition (ASR) is crucial for many real-world applications, but it requires dedicated modeling techniques. Existing approaches can be divided into modular and end-to-end methods. Modular approaches separate speakers and recognize each of them with a single-speaker ASR system. End-to-end models process overlapped speech directly in a single, powerful neural network. This work proposes a middle-ground approach that leverages explicit speech separation similarly to the modular approach but also incorporates mixture speech information directly into the ASR module in order to mitigate the propagation of errors made by the speech separator. We also explore a way to exchange cross-speaker context information through a layer that combines information of the individual speakers. Our system is optimized through separate and joint training stages and achieves a relative improvement of 7% in word error rate over a purely modular setup on the SMS-WSJ task. Copyright © 2023, The Authors. All rights reserved.

关键词： Speech recognition

Autonomous Drone-Chasing System: A Comprehensive Solution for Reducing the Risk of Mitigation Failure

学校读者我要写书评

暂无评论

Autonomous Drone-Chasing System: A Comprehensive Solution fo...

IEEE International Conference on Robotic Computing (IRC)

作者： Seungchol Cho Uk Jang Youngseo Chang William Choi Nicole Hornbrook Justin Allange Mia Y. Wang Eric T. Matson Human Centered Artificial Intelligence Sangmyung University Seoul Republic of Korea Department of Computer Engineering Jeju National University Jeju-si Republic of Korea Computer Science and Engineering Kyonggi University Suwon-si Republic of Korea Department of Business Administration Kyonggi University Suwon-si Republic of Korea Computer and Information Technology Purdue University West Lafayette IN USA Department of Computer Science College of Charleston Charleston SC USA

With the rapid advancement of unmanned aerial vehicles (UAVs) in various fields, the development of anti-drone systems has become increasingly important. Even though current research on anti-drone systems suggests means of mitigating malicious UAVs, some mitigation techniques overlook its risks when they fail to mitigate them. Therefore, we propose a system that lowers the risks of mitigation failure, which is implemented with a self-driving defensive drone capable of predicting and chasing the future position of detected malicious drones.

关键词：

Tensor normalization and full distribution training

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Fuhl, Wolfgang Department of Human Computer Interaction University Tübingen Tübingen72076 Germany

In this work, we introduce pixel wise tensor normalization, which is inserted after rectifier linear units and, together with batch normalization, provides a significant improvement in the accuracy of modern deep neural networks. In addition, this work deals with the robustness of networks. We show that the factorized superposition of images from the training set and the reformulation of the multi class problem into a multi-label problem yields significantly more robust networks. The reformulation and the adjustment of the multi class log loss also improves the results compared to the overlay with only one class as label. Copyright © 2021, The Authors. All rights reserved.

关键词： Tensors

Dynamic Localisation of Spatial-Temporal Graph Neural Network

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Duan, Wenying Guo, Shujun Zhou, Zimu Huang, Wei Rao, Hong He, Xiaoxi Jiangxi Provincial Key Laboratory of Intelligent Systems and Human-Machine Interaction Nanchang University Nanchang China School of Mathematics and Computer Sciences Nanchang University Nanchang China School of Data Science City University of Hong Kong Hong Kong School of Software Nanchang University Nanchang China Faculty of Science and Technology University of Macau China

Spatial-temporal data, fundamental to many intelligent applications, reveals dependencies indicating causal links between present measurements at specific locations and historical data at the same or other locations. Within this context, adaptive spatial-temporal graph neural networks (ASTGNNs) have emerged as valuable tools for modelling these dependencies, especially through a data-driven approach rather than pre-defined spatial graphs. While this approach offers higher accuracy, it presents increased computational demands. Addressing this challenge, this paper delves into the concept of localisation within ASTGNNs, introducing an innovative perspective that spatial dependencies should be dynamically evolving over time. We introduce DynAGS, a localised ASTGNN framework aimed at maximising efficiency and accuracy in distributed deployment. This framework integrates dynamic localisation, time-evolving spatial graphs, and personalised localisation, all orchestrated around the Dynamic Graph Generator, a light-weighted central module leveraging cross attention. The central module can integrate historical information in a node-independent manner to enhance the feature representation of nodes at the current moment. This improved feature representation is then used to generate a dynamic sparse graph without the need for costly data exchanges, and it supports personalised localisation. Performance assessments across two core ASTGNN architectures and nine real-world datasets from various applications reveal that DynAGS outshines current benchmarks, underscoring that the dynamic modelling of spatial dependencies can drastically improve model expressibility, flexibility, and system efficiency, especially in distributed settings. © 2025, CC BY-NC-ND.

关键词： Spatio-temporal data

ON ACCELERATING EDGE AI: OPTIMIZING RESOURCE-CONSTRAINED ENVIRONMENTS

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Sander, Jacob Cohen, Achraf Dasari, Venkat R. Venable, Brent Jalaian, Brian Department of Computer Science University of West Florida PensacolaFL United States Department of Mathematics and Statistics University of West Florida PensacolaFL United States DEVCOM Army Research Laboratory Aberdeen Proving Ground MD United States Department of Intelligent Systems and Robotics University of West Florida Institute for Human & Machine Cognition PensacolaFL United States Department of Computer Science Department of Intelligent Systems and Robotics University of West Florida Institute for Human & Machine Cognition PensacolaFL United States

Resource-constrained edge deployments demand AI solutions that balance high performance with stringent compute, memory, and energy limitations. In this survey, we present a comprehensive overview of the primary strategies for accelerating deep learning models under such constraints. First, we examine model compression techniques-pruning, quantization, tensor decomposition, and knowledge distillation-that streamline large models into smaller, faster, and more efficient variants. Next, we explore Neural Architecture Search (NAS), a class of automated methods that discover architectures inherently optimized for particular tasks and hardware budgets. We then discuss compiler and deployment frameworks, such as TVM, TensorRT, and OpenVINO, which provide hardware-tailored optimizations at inference time. By integrating these three pillars into unified pipelines, practitioners can achieve multi-objective goals, including latency reduction, memory savings, and energy efficiency-all while maintaining competitive accuracy. We also highlight emerging frontiers in hierarchical NAS, neurosymbolic approaches, and advanced distillation tailored to large language models, underscoring open challenges like pre-training pruning for massive networks. Our survey offers practical insights, identifies current research gaps, and outlines promising directions for building scalable, platform-independent frameworks to accelerate deep learning models at the edge. © 2025, CC BY.

关键词： Budget control

Equitable and Fair Performance Evaluation of Whale Optimization Algorithm

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Hassan, Bryar A. Rashid, Tarik A. Ahmed, Aram Qader, Shko M. Majidpour, Jaffer Abdalla, Mohmad Hussein Tayfor, Noor Hamarashid, Hozan K. Sidqi, Haval Noori, Kaniaw A. Ramadhan, Awf Abdulrahmam Department of Computer Science College of Science Charmo University Chamchamal KRI Sulaimani46023 Iraq Department of Computer Science and Engineering University of Kurdistan Hewler KRI Iraq Department of Information Technology College of Science and Technology University of Human Development Sulaimani Iraq Computer Science Institute Sulaimani Polytechnic University Information Technology Department Sulaimani Iraq The Department of Computer Science Kurdistan Technical Institute Sulaimani Iraq Department of Computer Science University of Raparin Sulaimani Iraq Department of Information Technology Kurdistan Technical Institute Sulaimani Iraq Information Technology Department Computer Science Institute Sulaimani Polytechnic University Sulaimani46001 Iraq Technical College of informatics Sulaimani Polytechnic University Sulaimani46001 Iraq Department of Database Technology Technical College of Informatics Sulaimani Polytechnic University Sulaimani Iraq Public Health Department College of Health and Medical Techniques - Shekhan Duhok Polytechnic University Duhok Iraq

It is essential that all algorithms are exhaustively, somewhat, and intelligently evaluated. Nonetheless, evaluating the effectiveness of optimization algorithms equitably and fairly is not an easy process for various reasons. Choosing and initializing essential parameters, such as the size issues of the search area for each method and the number of iterations required to reduce the issues, might be particularly challenging. As a result, this chapter aims to contrast the Whale Optimization Algorithm (WOA) with the most recent algorithms on a selected set of benchmark problems with varying benchmark function hardness scores and initial control parameters comparable problem dimensions and search space. When solving a wide range of numerical optimization problems with varying difficulty scores, dimensions, and search areas, the experimental findings suggest that WOA may be statistically superior or inferior to the preceding algorithms referencing convergence speed, running time, and memory utilization. © 2023, CC BY.

关键词： Benchmarking

Suicidal Tendency and Depression Diagnosing Medical Agent Using fNIRS and VFT

学校读者我要写书评

暂无评论

Suicidal Tendency and Depression Diagnosing Medical Agent Us...

IEEE International Conference on Agents (ICA)

作者： Joo Hun Yoo Harim Jeong Ji Hyun An Hong Jin Jeon Tai-Myoung Chung Department of Artificial Intelligence Sungkyunkwan University Suwon Republic of Korea Department of Interaction Science Sungkyunkwan University Seoul Republic of Korea Department of Psychiatry Sungkyunkwan University School of Medicine Seoul Republic of Korea Department of Computer Science and Engineering Sungkyunkwan University Suwon Republic of Korea

Functional Near-Infrared Spectroscopy (fNIRS) is a technique for measuring blood flow in the brain, specifically focusing on changes in the frontal lobe. It has found valuable applications in psychiatry, particularly in diagnostic processes. This study explores the potential of fNIRS data and verbal fluency test (VFT) data, both collected during fNIRS measurements, as tools for diagnosing the severity of major depressive disorder, a significant mental health condition. Beyond merely detecting depression, our research introduces a medical support agent model to identify signs of suicidal tendencies in individuals with severe depression. By integrating data collection, preprocessing techniques, feature extraction, and multimodal classification methods for fNIRS and VFT data, our study suggests these artificial intelligence-based medical agents could enhance diagnostic accuracy and provide valuable support in clinical judgments.

关键词：