检索结果-内蒙古大学图书馆

1st International Conference on Information and Communications Technology, ICOIACT 2018

作者： Shinoda, Hokuto Hattori, Motonobu Interdisciplinary Graduate School of Medicine and Engineering University of Yamanashi Kofu Yamanashi Japan Department of Computer Science and Engineering Faculty of Interdisciplinary Research University of Yamanashi Kofu Yamanashi Japan

ISBN: (纸本)9781538609545

In this paper, we propose complex-valued support vector machines (CVSVMs) which are a new type of support vector machines (SVMs) based on multi-valued neurons (MVNs). An MVN which is a type of complex-valued neurons is a component of the proposed CVSVM. The features of the proposed CVSVM are: 1) it has a multi-valued complex output;2) it provides the generalization ability by a decision boundary with the maximal margin;3) it can deal with non-linear classification by using a kernel function. Experimental results for some famous benchmark problems show the effectiveness of the proposed CVSVM. © 2018 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Food Volume Prediction and Classification using Multi-Task Learning 6

Food Volume Prediction and Classification using Multi-Task L...

引用

6th World Symposium on Artificial Intelligence, WSAI 2024

作者： Sari, Yuita Arum Nakazawa, Atsushi Gofuku, Akio Graduate School of Interdisciplinary Science and Engineering in Health Systems Okayama University Okayama Japan Brawijaya University Faculty of Computer Science Malang Indonesia

ISBN: (纸本)9798350374162

Food volume prediction is critical for calculating calories in food analysis and nutritional evaluation. However, obtaining data and measuring volume from the 3D sensor camera concurrently is time-consuming. Additionally, high computing power is necessary to compute the volume. Therefore, machine learning techniques are employed to extract specific data collected from the data collection process for learning purposes to save time. In this study, we employ Multi-Task Learning to predict volume and categorize food due to their interdependence simultaneously. We evaluate several backbones and find that ResNet50 attains the best performance with an MAE of 4.87 for volume prediction and 100% food classification accuracy. Our proposed method showcases outstanding results, aided by an efficient volume measurement methodology © 2024 IEEE.

关键词： food volume prediction machine learning multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Vehicles congestion control in transport networks using an adaptive weight model

Vehicles congestion control in transport networks using an a...

引用

1st International Conference on Internet of Vehicles, IOV 2014

作者： Jiang, Bin Xu, Xiao Yang, Chao Li, Renfa Terano, Takao College of Computer Science and Electronic Engineering Hunan University China Department of Computational Intelligence and Systems Science Interdisciplinary Graduate School of Science and Engineering Tokyo Institute of Technology Japan

ISBN: (纸本)9783319111667

This paper proposed an adaptive weight congestion control model in a vehicle transport network. Our focus was to construct a quantitative index series to describe the network congestion distribution, and to shunt vehicles on seriously congested links based on such index sequence. We achieved this goal by combing both feedback and iteration strategy in the congestion control field. First, we developed an agent based model which captured the nonlinear feedback mechanism between the vehicle routing behavior and the road congestion state. Then, the model implemented an adaptive intersection weight adjustment mechanism based on the evolutionary congestion degree of the nearby links, through which to achieve congestion distribution evaluation and network congestion control at the same time. The simulation results verified the validity of our model for congestion control under predefined networks, and proved an applicability of the intersection weight sequence as a measurement for the congestion degree and distribution of road networks. © 2014 Springer International Publishing Switzerland.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Understanding Credibility of Adversarial Examples against Smart Grid: A Case Study for Voltage Stability Assessment 21

Understanding Credibility of Adversarial Examples against Sm...

引用

12th ACM International Conference on Future Energy Systems, e-Energy 2021

作者： Song, Qun Tan, Rui Ren, Chao Xu, Yan ERI@N Interdisciplinary Graduate School School of Computer Science and Engineering Nanyang Technological University Singapore Singapore School of Computer Science and Engineering Nanyang Technological University Singapore Singapore School of Electrical and Electronic Engineering Nanyang Technological University Singapore Singapore

ISBN: (纸本)9781450383332

Stability assessment is an important task for maintaining reliable operations of power grids. With increased system complexity, deep learning-based stability assessment approaches are promising to address the shortfalls of the traditional time-domain simulation-based approaches. However, in the field of computer vision, the deep learning models are shown vulnerable to adversarial examples. Although this vulnerability has been noticed by the energy informatics research, the domain-specific analysis on the requirements imposed for implementing effective adversarial examples is still lacking. These attack requirements, albeit reasonable in computer vision tasks, can be too stringent in the context of power grids. In this paper, we systematically investigate the requirements and discuss the credibility of six representative adversarial example attacks for a case study of voltage stability assessment for the New England 10-machine 39-bus system. We show that (1) compromising the voltage traces of half of transmission system buses is a rule of thumb requirement;(2) the universal adversarial perturbations that are independent of the original clean voltage trajectory have the same credibility as the widely studied false data injection attacks on power grid state estimation, while other adversarial example attacks are less credible;(3) the universal perturbations can be effectively defended with strong adversarial training. © 2021 ACM.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

Forecasting masked-load with invisible distributed energy resources based on transfer learning and Bayesian tuning

Energy Conversion and Economics

引用

Energy Conversion and Economics 2024年第5期5卷 316-326页

作者： Zhou, Ziyan Ren, Chao Xu, Yan Interdisciplinary Graduate School Nanyang Technological University Singapore Singapore Department of Intelligent Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden School of Electrical and Electronic Engineering Nanyang Technological University Singapore Singapore

Load forecasting with distributed energy resources (DERs) behind-the-meter is more challenging owing to transformed data patterns. Traditional forecasting method which is only based on unmasked-load could not suit the present limited masked-load. To bridge the divergence between unmasked-load and masked-load, this article proposes a masked-load forecasting (MLF) method based on transfer learning technique and Bayesian optimization, which is Maximum Mean Discrepancy-Neural Network with Bayesian optimization (MMD-NNb). At first, common feature vectors between unmasked-load and masked-load are extracted and an outcome predictor could be established based on feature vectors from historical unmasked-load. The feature vectors from masked-load could therefore accommodate to the outcome predictor, and the masked-load could be forecast. Owing to the excessive hyperparameters involved in training, Bayesian optimization is adopted for hyperparameters fine-tuning. MMD-NNb was tested and compared with four related models. The improvements from MMD-NNb were observed in all comparison scenarios. Also, MMD-NNb was proved to have high resilience to the different DERs and not requiring additional DERs-data. © 2024 The Author(s). Energy Conversion and Economics published by John Wiley & Sons Ltd on behalf of The Institution of engineering and Technology and the State Grid Economic & Technological Research Institute Co., Ltd.

关键词： Bayesian optimization distributed energy resources load forecasting masked-load transfer learning

来源：评论

学校读者我要写书评

暂无评论

The use of an oxidized carbon nanotube film to control Zn deposition and eliminate dendrite formation in a Zn ion battery

引用

Carbon 2025年 235卷

作者： Pin-xiang Li Zhe-han Yi Ye-xing Wang Chang He Ji Liang Feng Hou Key Laboratory of Advanced Ceramics and Machining Technology of Ministry of Education School of Materials Science and Engineering Tianjin University Tianjin 300072 China Interdisciplinary Graduate Programme - Collaborative Initiative Graduate College Nanyang Technological University Singapore 637371 Singapore School of Physical and Mathematical Sciences Nanyang Technological University Singapore 637371 Singapore Tianjin Key Laboratory of Low-dimensional Electronic Materials and Advanced Instrumentation Tianjin 300072 China

来源：评论

学校读者我要写书评

暂无评论

Purify Unlearnable Examples via Rate-Constrained Variational Autoencoders 41

Purify Unlearnable Examples via Rate-Constrained Variational...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Yu, Yi Wang, Yufei Xia, Song Yang, Wenhan Lu, Shijian Tan, Yap-Peng Kot, Alex C. Rapid-Rich Object Search Lab Interdisciplinary Graduate Programme Nanyang Technological University Singapore School of Electrical and Electronic Engineering Nanyang Technological University Singapore PengCheng Laboratory Shenzhen China School of Computer Science and Engineering Nanyang Technological University Singapore

Unlearnable examples (UEs) seek to maximize testing error by making subtle modifications to training examples that are correctly labeled. Defenses against these poisoning attacks can be categorized based on whether specific interventions are adopted during training. The first approach is training-time defense, such as adversarial training, which can mitigate poisoning effects but is computationally intensive. The other approach is pre-training purification, e.g., image short squeezing, which consists of several simple compressions but often encounters challenges in dealing with various UEs. Our work provides a novel disentanglement mechanism to build an efficient pre-training purification method. Firstly, we uncover rate-constrained variational autoencoders (VAEs), demonstrating a clear tendency to suppress the perturbations in UEs. We subsequently conduct a theoretical analysis for this phenomenon. Building upon these insights, we introduce a disentangle variational autoencoder (D-VAE), capable of disentangling the perturbations with learnable class-wise embeddings. Based on this network, a two-stage purification approach is naturally developed. The first stage focuses on roughly eliminating perturbations, while the second stage produces refined, poison-free results, ensuring effectiveness and robustness across various scenarios. Extensive experiments demonstrate the remarkable performance of our method across CIFAR-10, CIFAR-100, and a 100-class ImageNet-subset. Code is available at https://***/yuyi-sd/D-VAE. Copyright 2024 by the author(s)

关键词： Variational techniques

来源：评论

学校读者我要写书评

暂无评论

Model Predictive Control of Five-Level Current Source Converter with Optimized Weighting Factors 3

Model Predictive Control of Five-Level Current Source Conver...

引用

3rd IEEE International Conference on Industrial Electronics for Sustainable Energy Systems, IESES 2023

作者： Chen, Muyu Yuan, Zhige Faraji, Faramarz Ghias, Amer M. Y. M. Cha, Honnyong Nicholas, Vun Chan Hua School of Electrical and Electronic Engineering Nanyang Technological University Collab. Initiative Interdisciplinary Graduate Programme Singapore School of Electrical and Electronic Engineering Nanyang Technological University Singapore School of Energy Engineering Kyungpook National University Daegu Korea Republic of School of Computer Science and Engineering Nanyang Technological University Singapore

ISBN: (纸本)9798350324754

This paper presents the finite control set model predictive control (FCS-MPC) with improved control objectives using optimized weighting factors. The Pareto curve obtained from the Particle Swarm optimizes the weighting factors. The optimal weighting factors are then used in the FCS-MPC algorithm to enhance the control objective performance of a three-phase five-level current source converter (5L-CSC). In 5L-CSC, two identical three-level CSC (3L-CSC) modules are connected in parallel with one common current source supply to provide uniform five-level output current waveform. This CSC requires a current balance to operate the converter safely. Therefore, the control objective of the MPC is to control the output voltage and balance the internal currents. The weighting factors are optimized based on the converter's total harmonics distortion (THD) performance and inductor current ripple. The performance enhancement of 5L-CSC, utilizing optimal weighting factors, is confirmed through MATLAB simulations when compared to the model employing arbitrarily assigned weighting factors. The simulation outcomes additionally indicate that the integration of Particle Swarm Optimization (PSO) with FCS-MPC exhibits resilience across various condition settings. © 2023 IEEE.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Extraction of male and female facial features using neural networks

引用

Systems and computers in Japan 2000年第3期31卷 68-76页

作者： Kanno, Tsuneo Nagahashi, Hiroshi Agui, Takeshi Department of Information and Computer Science Polytechnic University Sagamihara 229-1196 Japan Department of Information Processing Interdisciplinary Graduate School of Science and Engineering Tokyo Institute of Technology Yokohama 227-8503 Japan Faculty of Engineering TOIN University of Yokohama Yokohama 225-5802 Japan

Features of male/female facial images are examined by analyzing the distribution of connection weights of the hidden-layer unit and the input-layer unit of a neural network that responds to their distinction. Twenty-five gray-level (black-and-white) facial images were used for each of the male and female samples. Several different numbers of mosaic blocks were used for the whole face region and each facial component region. The training parameters of the neural network and the minimum number of hidden layers that can discriminate male/female were obtained by a genetic algorithm. The neural network consisting of these parameters has a stable convergence in any region so that this can discriminate male/female with 100% accuracy. In the feature extraction experiments, hidden layers were obtained, which significantly respond to male/female facial regions. The facial features of male/female can be extracted by analyzing the connection weights between the hidden-layer unit and the input-layer unit. The facial features extracted by using the proposed method were similar to those obtained by other psychological experiments and facial measurements.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Online Knowledge Distillation via Collaborative Learning with Enhanced Diversity and Gradual Ensemble 12

Online Knowledge Distillation via Collaborative Learning wit...

引用

12th IEEE International Workshop on Computational Intelligence and Applications, IWCIA 2021

作者： Li, Qiuyue Hattori, Motonobu Zhang, Wei Gao, Zhigang Hangzhou Dianzi University School of Computer Science and Technology Hangzhou China University of Yamanashi Interdisciplinary Graduate School of MedicineEngineering and Agriculture Kofu Yamanashi Japan

ISBN: (纸本)9781665444255

In general, knowledge distillation transfers knowledge from a large pre-trained teacher network to a small student network. This is usually referred to as offline distillation and requires two stages of learning: learning of the teacher network and that of the student network. In contrast, in online distillation, the outputs of multiple student networks are integrated and regarded as the output of the teacher network. Compared to offline distillation, this method has the advantage that it does not require a large pre-trained teacher network and can be trained online. However, since online distillation uses ensemble learning, it is extremely important to consider the following two aspects. First, it is important to maintain the diversity of individual student networks during learning. Second, since the performance of each student network is poor at the beginning of the learning and improves as the learning progresses, the distillation needs to account for this change in performance. In this paper, we propose a novel online knowledge distillation method that takes these two points into account: the diversity of individual student networks is enhanced by providing different training data to each student network, and the degree of the ensemble learning is gradually increased by introducing a rump-up function into the loss function. Experiments using CIFAR-100 and Tiny ImageNet show that the proposed method can improve the generalization ability. © 2021 IEEE.

关键词： Distillation

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：