检索结果-内蒙古大学图书馆

IEEE International Conference on Automation Science and engineering (CASE)

作者： Giuseppe D’Aniello Giancarlo Fortino Matteo Gaeta Zia Ur Rehman Dept. Information and Electrical Engineering and Applied Mathematics University of Salerno Fisciano Italy Dept. Computer Engineering Modeling Electronics and Systems University of Calabria Rende Italy

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

A situation-aware wearable computing system is defined as a wearable device with the capability to perceive, comprehend, and project the situations occurring in the environment in order to adapt its behavior accordingly. For this kind of devices, the identification of complex situations related to the activities performed by users in various contexts is of great interest. This requires the capability to identify context states. A well-known technique for this task is the Context Space Theory (CST), which provides a multidimensional space representing contexts. Although powerful and lightweight, this technique has the drawback of requiring manual definition of such a space, a time-consuming process that involves domain experts. To address this issue, this work proposes a data-driven approach for defining context spaces in CST using kernel density estimation. This approach is compared with a state-of-theart expert-based CST technique and a fuzzy inference system for context representation, demonstrating superior performance on the Extrasensory dataset.

关键词： Performance evaluation Fuzzy logic computer aided software engineering Estimation Manuals computer architecture Feature extraction Object recognition Wearable devices Kernel

来源：评论

学校读者我要写书评

暂无评论

Driver Assistance System, Based on the Convolutional Neural Network

Driver Assistance System, Based on the Convolutional Neural ...

引用

Electrical engineering Faculty Conference (BulEF)

作者： Simona Filipova-Petrakieva Petar Yanev dept. Fundamentals of Electrical Engineering Technical University of Sofia Sofia Bulgaria dept. Computer Systems Technical University of Sofia Sofia Bulgaria

ISBN: (数字)9798350391671

ISBN: (纸本)9798350391688

The continuously rising number of deaths due to car accidents on the roads is a critical problem nowadays. To reduce the number of risky situations on the road, it is necessary to increase the attention of drivers when driving motor vehicles. In this context, an advisory system to assist driving is proposed in this paper. The mathematical model uses a convolutional neural network to recognize traffic signs and detect real road situations. It is implemented using Python in the Jupyter Notebook environment. The following libraries were used: Tensorflow (Tensors and Keras libraries, for machine learning and deep learning, respectively), Tkinter (GUI library), Pillow (image processing library), matplotlib (data visualization library), NumPy (library for performing complex computations), and Pandas (data analysis and processing library). The developed application is installed on the onboard vehicle computer. The detected sign is displayed in an appropriate form on the automobile dashboard. Simulations of real traffic situations are implemented in the system. All this will facilitate driving and help drivers with less experience acquire the necessary driving reactions.

关键词： Tensors Roads Image processing Neural networks Libraries Mathematical models Convolutional neural networks Automobiles Vehicles Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Drug Response Prediction with Gene Expression Data

Deep Learning for Drug Response Prediction with Gene Express...

引用

International Conference on Information Networking

作者： Sardar Jaffar Ali Muhammad Omer Duc Tai Le Syed M. Raza Hyunseung Choo Dept. of AI Systems Engineering Sungkyunkwan University Suwon South Korea Dept. of Computer Science and Engineering Sungkyunkwan University Suwon South Korea Dept. of Electrical and Computer Engineering Sungkyunkwan University Suwon South Korea James Watt School of Engineering University of Glasgow Glasgow United Kingdom

ISBN: (数字)9798331506940

ISBN: (纸本)9798331506957

Accurately predicting drug responses based on individual patient profiles is a critical challenge in personalized medicine, primarily due to the complex biological variability involved. This paper presents a deep learning framework for predicting changes in gene expression, providing insights into how drugs impact cells at the molecular level. Using data from the Kaggle competition, several models have been evaluated, including LSTM, GRU, Transformer, and Autoencoder architectures. Among these, the 3 -stacked GRU with Attention demonstrated superior performance, achieving the highest sign accuracy of 79% and the lowest mean absolute error across diverse biological conditions. The robust performance of the model highlights the effectiveness of attention mechanisms in capturing critical patterns in gene expression data.

关键词： Drugs Deep learning Attention mechanisms Precision medicine Biological system modeling Autoencoders Transformers Data models Gene expression Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Inception: Efficiently Computable Misinformation Attacks on Markov Games

arXiv

引用

arXiv 2024年

作者： McMahan, Jeremy Wu, Young Chen, Yudong Zhu, Xiaojin Xie, Qiaomin Dept. of Computer Sciences University of Wisconsin-Madison United States Dept. of Industrial and Systems Engineering University of Wisconsin-Madison United States

We study security threats to Markov games due to information asymmetry and misinformation. We consider an attacker player who can spread misinformation about its reward function to influence the robust victim player's behavior. Given a fixed fake reward function, we derive the victim's policy under worst-case rationality and present polynomial-time algorithms to compute the attacker's optimal worst-case policy based on linear programming and backward induction. Then, we provide an efficient inception ("planting an idea in someone's mind") attack algorithm to find the optimal fake reward function within a restricted set of reward functions with dominant strategies. Importantly, our methods exploit the universal assumption of rationality to compute attacks efficiently. Thus, our work exposes a security vulnerability arising from standard game assumptions under misinformation. © 2024, CC BY.

关键词： Linear programming

来源：评论

学校读者我要写书评

暂无评论

LIDS: Lightweight Dynamic Scheduling Technique for 6G-enabled Massive LoRa based IoT systems

LIDS: Lightweight Dynamic Scheduling Technique for 6G-enable...

引用

2022 IEEE GLOBECOM Workshops, GC Wkshps 2022

作者： Kumbam, Akshitha Choudhury, Nikumani Nasralla, Moustafa M. Birla Institute of Technology & Science Dept. of Computer Science & Information Systems Pilani Hyderabad India Prince Sultan University Dept. of Communications & Networks Engineering Riyadh Saudi Arabia

ISBN: (纸本)9781665459754

The sixth-generation (6G) wireless communication networks are envisioned to deliver improved Quality of Services (QoS) such as data-rate, latency, localization, etc., compared to 5G services. This demand will mainly arise due to the massive Internet of Things (IoT) connections among billions of embedded devices. It is worth noting that these IoT devices are constrained in nature in terms of memory, computation and most importantly power. Low-power wireless computing necessitates a link-layer technology that considers the aforementioned IoT device requirements such as low-power, low data-rate, long-range and energy efficient reliable communications. Long Range Radio (LoRa) technology has recently become widely popular to facilitate low-power, long-range communication, while other similar technologies struggle to achieve long-range transmissions. The LoRA standard defines several PHY and MAC sub-layer specifications for Low-Power Wide Area Networks (LPWAN) that can be used to build several IoT applications. With 6G communications, an IoT application is expected to consist of hundreds of devices connected at a time, and this will need a proper scheduling mechanism among these devices for optimal performance. The LoRa standard does not define any scheduling mechanism and leaves it to the research community to explore. In this paper, we propose a distributed scheduling mechanism under the supervision of a common LoRa gateway. The proposed mechanism focuses on a Lightweight DynamicScheduling (LIDS) scheme to minimize loss in data transmissions through collisions. The proposed mechanism optimizes the power consumption to achieve the desired level of QoS requirements such as throughput and latency. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Computational Thinking and AI Literacy: A Gender-Based Analysis Among Early Learners

Computational Thinking and AI Literacy: A Gender-Based Analy...

引用

IEEE Education engineering (EDUCON)

作者： Andrea E. Cotino-Arbelo Jezabel Molina-Gil Carina S. González-González Dept. of Computer and Systems Engineering Women Research Studies Institute (of the University of La Laguna) La Laguna Spain

ISBN: (数字)9798331539498

ISBN: (纸本)9798331539504

While women remain underrepresented in STEM fields, our study reveals insights from an overlooked frontier: preschool classrooms. Despite decades of global initiatives aimed at increasing female participation in technology fields, gender-interest stereotypes continue to discourage girls from pursuing computer science careers. Our research challenges these barriers by implementing an innovative educational program integrating Computational Thinking (CT) and Artificial Intelligence (AI) literacy. Using a quasi-experimental pretest-posttest design with $N=114$ preschoolers, we assessed the impact of hands-on activities in algorithms, debugging, and control structures through the TechCheck questionnaire. Our findings challenge prevailing assumptions: while initial CT skills showed no gender disparity (boys M=58.8, girls M=53.95, p=,445), post-intervention results revealed girls significantly outperforming boys (girls M=66.11, boys M=51.61, $p=,022$ ). On the contrary, AI literacy assessments showed complete gender parity (p=,995). These results suggest that early childhood education could be the key to dismantling gender barriers in computer science, demonstrating that when learning environments are equitable, girls not only match but can exceed traditional performance expectations. This study opens new pathways for understanding how early educational interventions can reshape the future of gender equity in STEM fields, beginning with our youngest learners.

关键词： computer science Visualization Educational programs Gender equity engineering profession computer architecture Cultural differences Reliability Artificial intelligence engineering education

来源：评论

学校读者我要写书评

暂无评论

An Ising Machine-Based Hybrid Optimization Method Using Constraint Conversion and Correction

An Ising Machine-Based Hybrid Optimization Method Using Cons...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Kinya Iwata Masashi Tawada Nozomu Togawa Dept. of Computer Science and Communications Engineering Waseda University Green Computing Systems Research Organization Waseda University

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

This paper proposes an Ising machine-based hy-brid optimization method to solve combinatorial optimization problems, which consists of an approximate formulation process, an annealing process with an Ising machine, and a correction process. The approximate formulation and correction aim to improve the performance of the Ising machine. Computational experiments were conducted on the multi-dimensional knapsack problem (MKP) using an Ising machine. We compare the results with those of the proposed method and the conventional method and demonstrate the effectiveness of the proposed approach.

关键词： Annealing Optimization methods Consumer electronics

来源：评论

学校读者我要写书评

暂无评论

A Variable Step-Size Hybrid Adaptive Nonlinear Filter for Solar Radiation Prediction

A Variable Step-Size Hybrid Adaptive Nonlinear Filter for So...

引用

International Conference on systems and Informatics (ICSAI)

作者： Y. Xiao L. Ma K. Khorasani Dept. of Management & Information Systems Prefectural University of Hiroshima Hiroshima Japan Dept. of Electrical & Computer Engineering Concordia University Montreal Canada

ISBN: (数字)9798331510138

ISBN: (纸本)9798331510145

In this paper, a new hybrid adaptive nonlinear filter (HANF) scheme with variable step sizes (VSS) is proposed for solar radiation prediction. Our methodology consists of a Volterra filter and a functional link artificial neural network (FLANN) filter. The Volterra filter with the first- and second-order kernels is included, that is capable of expressing both linearity and nonlinearity. The FLANN filter can handle the nonlinearity that may be expressed by higher-order exponential terms that the Volterra filter with a limited number of kernels is unable to deal with. The VSSs are introduced in the two filters to allow the HANF to enjoy desirable tracking capability such that the time-varying nonlinearity underlying the nonlinear phenomena can be detected and tracked. The proposed VSS-HANF is applied to a real hourly solar radiation time sequence to confirm its improved prediction performance as compared to its counterpart with fixed step sizes.

关键词： Accuracy Finite impulse response filters Adaptive filters Weather forecasting Linearity Nonlinear filters Artificial neural networks Solar radiation Kernel Informatics

来源：评论

学校读者我要写书评

暂无评论

Robust Active and Reactive Power Control by using Single-Phase Grid connected H-Bridge Inverter

Robust Active and Reactive Power Control by using Single-Pha...

引用

International Smart Grid Workshop and Certificate program (ISGWCP)

作者： Resul Coteli Korhan Kayisli Ruhi Zafer Caglayan Dept. of Energy Systems Engineering Technology Faculty Firat University Elazig Turkiye Dept. of Electrical- Electronic Engineering Engineering Faculty Gazi University Ankara Turkiye Dept. of Computer Engineering Engineering Faculty TED University Ankara Turkiye

ISBN: (数字)9798350361612

ISBN: (纸本)9798350361629

In a single-phase power network, inverters can be used to control the active and reactive power between sources. This task can be achieved by proper control of the current of the single-phase inverter. The current controllers using dq-frame components have a wide application area because of their superior features such as zero steady-state error and using the DC quantities. In this study, the active and reactive power between sources in a single-phase power system consisting of an AC voltage source and a DC voltage source are controlled via dq-frame based super twisting sliding mode (ST-SMC) current controller. For this aim, a Matlab/Simulink model is constructed. The model includes single phase H-bridge inverter, DC voltage source, AC voltage source, AC load, LCL filter and control unit. Two super twisting sliding mode controllers are used to control d and q-axis currents. Decoupling terms are added to output of each controller for independent control of active and reactive power. The simulation studies are performed to demonstrate the controller's ability to provide/absorb active and reactive power. To demonstrate the ability to provide/absorb active power, the d-axis current command is set to 10 A up to 2 s from the start of the simulation, and then, it is set to – 10 A between 2 s to 4 s. To demonstrate the ability to provide/absorb reactive power, the q-axis current command is set to 10 A up to 2 s from the start of the simulation, and then, it is set to – 10 A between 2 s to 4 s. The simulation results show that the controller provides/absorbs the desired active and reactive power quickly and without steady-state error.

关键词： Reactive power Reactive power control Simulation Inverters Mathematical models Steady-state Smart grids

来源：评论

学校读者我要写书评

暂无评论

Multi-Point Positional Insertion Tuning for Small Object Detection

arXiv

引用

arXiv 2024年

作者： Goto, Kanoko Karasawa, Takumi Hirose, Takumi Kawakami, Rei Inoue, Nakamasa Dept. of Computer Science Institute of Science Tokyo Tokyo Japan Dept. of Systems and Control Engineering Institute of Science Tokyo Tokyo Japan

Small object detection aims to localize and classify small objects within images. With recent advances in large-scale vision-language pretraining, finetuning pretrained object detection models has emerged as a promising approach. However, finetuning large models is computationally and memory expensive. To address this issue, this paper introduces multi-point positional insertion (MPI) tuning, a parameter-efficient finetuning (PEFT) method for small object detection. Specifically, MPI incorporates multiple positional embeddings into a frozen pretrained model, enabling the efficient detection of small objects by providing precise positional information to latent features. Through experiments, we demonstrated the effectiveness of the proposed method on the SODA-D dataset. MPI performed comparably to conventional PEFT methods, including CoOp and VPT, while significantly reducing the number of parameters that need to be tuned. Copyright © 2024, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：