检索结果-内蒙古大学图书馆

International Conference on Computational Intelligence and Applications (ICCIA)

作者： Maythar Poonpanit Narong Punkong Chiabwoot Ratanavilisagul Somkiat Kosolsombat Department of Computer and Information Sciences Faculty of Applied Science King Mongkut's University of Technology North Bangkok (KMUTNB) Bangkok Thailand Digital Technology for Business Faculty of Management Science Kanchanaburi Rajabhat University(KRU) Kanchanaburi Thailand Data Science and Innovation College of Interdisciplinary Studies Thammasat University Pathum Thani Thailand

ISBN: (数字)9798350352214

ISBN: (纸本)9798350352221

Capacitated Vehicle Routing Problem (CVRP) is the vehicle routing problem in which vehicles with limited space have to drop off items at different places. This item consists of certain amounts, weight or volume, and the vehicles can carry a limited load. Many researchers try to solve the CVRP by the meta-heuristic algorithms. The Genetic Algorithm (GA) is a classical method to solve the CVRP. To enhance performance of GA for solving CVRP, the recently proposed GA combines simulated annealing (SA) or a hybrid genetic and simulated annealing algorithm (HGSA). However, both GA and SA enhance population diversity and lead to over distribution of population. If the distribution is too much population, it prevents convergence of population to search for answers. It affects the search that obtains a bad answer. This paper proposed an Improving Genetic Algorithm with Local Search or GALS. The proposed method uses GA for decreasing or solving trapping into local optimum from searching and improving solution by local search techniques. The proposed method does not interrupt the population convergence, so it obtains a good answer. Experiments conducted on twenty-seven maps dataset have shown that the proposed method achieves encouraging performance compared to a hybrid genetic and simulated annealing algorithm.

关键词： Space vehicles Vehicle routing Metaheuristics Simulated annealing Search problems Genetics Genetic algorithms Convergence

来源：评论

学校读者我要写书评

暂无评论

Deep Learning based Multilabel Hateful Speech Text Comments Recognition and Classification Model for Resource Scarce Ethiopian Language: The case of Afaan Oromo

Deep Learning based Multilabel Hateful Speech Text Comments ...

引用

2022 IEEE International Conference on Current Development in Engineering and technology, CCET 2022

作者： Defersha, Naol Bakala Abawajy, Jemal Kekeba, Kula College of Electrical and Mechanical Engineering Centre of Excellence for Hpc & Big Data Analytics Addis Ababa Science and Technology Software Engineering Department 16417 Ethiopia School of Information Technology Deakin University Faculty of Science Engineering and Built Environment GeelongVIC3220 Australia Centre of Excellence College of Electrical and Mechanical Engineering Addis Ababa Science and Technology Department of Software Engineering Technology 16417 Ethiopia

ISBN: (纸本)9781665454155

In response to the phenomenon of hate speech on popular social media such as Facebook, a number of researchers have investigated and developed different automated techniques in order to detect and moderate hate speech. Reliable hate speech detection tools ranging from traditional machine learning models to deep neural network models have been developed and deployed for resource rich languages such as English, French and Arabic. On the Other hand, the topic of building automated techniques for hate speech detection in Afaan Oromo is still the subject of very limited studies. In this study, we have used pretrained word embedding approaches such as word2vec and fast text, and assessed their effectiveness for hateful speech recognition and classification in Afaan Oromo text comments on Facebook. By using the proposed model, the effectiveness of deep learning algorithms like CNN and LSTM was also assessed. Moreover, the significance of one of the recent topic modeling approaches, i.e., BERTopic, has been investigated to in extracting topics that can help the categorization of Afaan Oromo hate speech. Afaan Oromo Multilabel Hateful Speech Detection and dataset (AOMLHSDD), which contains 30728 text comments, was created after we employed the BERTopic to extract relevant topics. Accordingly, Then, we have conducted different experiments to test the effectiveness of CNN and LSTM models by using word2vec and fast text. The result of our experiments has shown showed that LSTM has outperformed the CNN approach by achieving the accuracy of 98.32%. © 2022 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Multi-step and Iterative Backdoor Injection in Federated Machine Unlearning

Multi-step and Iterative Backdoor Injection in Federated Mac...

引用

Cross Strait Quad-Regional Radio science and Wireless technology Conference (CSRWTC)

作者： Zirui Ling Chao Zhang Zijie Pan School of Artificial Intelligence Guangzhou University Guangzhou China National Research Center for Common Information Security Technology Beijing China Faculty of Data Science City University of Macau Macau China

ISBN: (数字)9798331507794

ISBN: (纸本)9798331507800

This paper investigates multistep and iterative back-door injection in federated learning, revealing how gradual and distributed attacks enhance the persistence and stealth of backdoors. These attacks evade detection by standard defenses, complicating the process of machine unlearning. Experimental evaluations show that traditional unlearning methods are only partially effective, while our proposed iterative unlearning strategy significantly reduces backdoor success without degrading model accuracy. The findings emphasize the need for adaptive and robust unlearning techniques designed for the unique challenges of federated learning, offering new directions for defending against sophisticated adversarial attacks.

关键词： Wireless communication Adaptation models Accuracy Federated learning Iterative methods Standards

来源：评论

学校读者我要写书评

暂无评论

Fusenet: Self-Supervised Dual-Path Network For Medical Image Segmentation

Fusenet: Self-Supervised Dual-Path Network For Medical Image...

引用

IEEE International Symposium on Biomedical Imaging

作者： Amirhossein Kazerouni Sanaz Karimijafarbigloo Reza Azad Yury Velichko Ulas Bagci Dorit Merhof School of Electrical Engineering Iran University of Science and Technology Iran Faculty of Informatics and Data Science University of Regensburg Germany Faculty of Electrical Engineering and Information Technology RWTH Aachen University Germany Department of Radiology Northwestern University Chicago IL USA Fraunhofer Institute for Digital Medicine MEVIS Germany

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

Semantic segmentation, a crucial task in computer vision, often relies on labor-intensive and costly annotated datasets for training. In response to this challenge, we introduce FuseNet, a dual-stream framework for self-supervised semantic segmentation that eliminates the need for manual annotation. FuseNet leverages the shared semantic dependencies between the original and augmented images to create a clustering space, effectively assigning pixels to semantically related clusters, and ultimately generating the segmentation map. Additionally, FuseNet incorporates a cross-modal fusion technique that extends the principles of CLIP by replacing textual data with augmented images. This approach enables the model to learn complex visual representations, enhancing robustness against variations similar to CLIP’s text invariance. To further improve edge alignment and spatial consistency between neighboring pixels, we introduce an edge refinement loss. This loss function considers edge information to enhance spatial coherence, facilitating the grouping of nearby pixels with similar visual features. Extensive experiments on skin lesion and lung segmentation datasets demonstrate the effectiveness of our method. GitHub.

关键词： Training Visualization Annotations Image edge detection Semantic segmentation Spatial coherence Manuals

来源：评论

学校读者我要写书评

暂无评论

Improving Zero-shot Adversarial Robustness via Integrating Image Features of Foundation Models

Improving Zero-shot Adversarial Robustness via Integrating I...

引用

IEEE Global Conference on Consumer Electronics (GCCE)

作者： Koshiro Toishi Keisuke Maeda Ren Togo Takahiro Ogawa Miki Haseyama School of Engineering Hokkaido University Hokkaido Japan Data-Driven Interdisciplinary Research Emergence Department Hokkaido University Hokkaido Japan Faculty of Information Science and Technology Hokkaido University Hokkaido Japan

ISBN: (数字)9798350355079

ISBN: (纸本)9798350355086

The Contrastive Language-Image Pre-training (CLIP) model is one of the most successful multi-modal foundation models and is indispensable in the field of computer vision. While the CLIP model performs zero-shot image recognition tasks with high accuracy, it is vulnerable to adversarial examples created by white-box attacks against the CLIP model. To improve the zero-shot adversarial robustness of the CLIP model, almost all methods rely on adversarial training, and other approaches have not been sufficiently explored. In this paper, we propose a novel defense strategy that integrates the CLIP model with another foundation model, ImageBind, which has a different structure and learning mechanism from the CLIP model. Experimental results confirm the effectiveness of the proposed method, showing a significant improvement in the classification accuracy for adversarial examples targeting the CLIP model.

关键词： Training Learning systems Computer vision Accuracy Image recognition Computational modeling Robustness Consumer electronics Glass box

来源：评论

学校读者我要写书评

暂无评论

Maize Plant Disease Prediction of UAV Images for Precision Agriculture Using Fusion of Multimodal

Maize Plant Disease Prediction of UAV Images for Precision A...

引用

Computing and information technology (ICCIT-1441), 2020 International Conference on

作者： Vinay Mishra Nenavath Srinivas Naik Santosh Kumar Saeed Hamood Alsamhi Abdu Saif Edward Curry Department of Computer Science and Engineering International Institute of Information Technology (IIIT)-Naya Raipur Chhattisgarh India Insight Centre for Data Analytics University of Galway Galway Ireland Faculty of Engineering & Information Technology Taiz Yemen

The agriculture sector is vital to a country’s economic and productive development. With technological advancements, we can identify plant diseases in their early stages, similar to how human diseases are diagnosed, and avoid significant financial loss. For example, a new technique has been developed to detect diseases in maize crops, a widely used raw product in the food industry and precision agriculture. Furthermore, farmers ensure the fields do not remain wet for extended periods to prevent fungus infection. Currently, machine learning and deep learning approaches are being utilized, making agriculture one of the most researched topics in AI. This study proposes a novel framework for predicting maize plant disease using a fusion of multi-deep learning models. The proposed framework uses a four-stage pipeline for detecting disease in maize plants by fusion of Xception, DenseNet-121, and ensembling of Xception and DenseNet-121 models to achieve excellent results on the OSF drone image dataset, which consists of 1821 high-resolution images of maize plants taken from unmanned aerial vehicles (UAVs). The accuracy of our proposed approach is 96.95%, which is highly effective, considering the challenges posed by drone images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Deep Probabilistic Spatiotemporal Framework for Dynamic Graph Representation Learning with Application to Brain Disorder Identification

arXiv

引用

arXiv 2023年

作者： Yap, Sin-Yee Loo, Junn Yong Ting, Chee-Ming Noman, Fuad Phan, Raphaël C.-W. Razi, Adeel Dowe, David L. School of Information Technology Monash University Malaysia Department of Data Science and AI Faculty of Information Technology Monash University Australia Turner Institute for Brain and Mental Health School of Psychological Sciences Monash University Australia

Recent applications of pattern recognition techniques on brain connectome classification using functional connectivity (FC) are shifting towards acknowledging the non-Euclidean topology and dynamic aspects of brain connectivity across time. In this paper, a deep spatiotemporal variational Bayes (DSVB) framework is proposed to learn time-varying topological structures in dynamic FC networks for identifying autism spectrum disorder (ASD) in human participants. The framework incorporates a spatial-aware recurrent neural network with an attention-based message passing scheme to capture rich spatiotemporal patterns across dynamic FC networks. To overcome model overfitting on limited training datasets, an adversarial training strategy is introduced to learn graph embedding models that generalize well to unseen brain networks. Evaluation on the ABIDE resting-state functional magnetic resonance imaging dataset shows that our proposed framework substantially outperforms state-of-the-art methods in identifying patients with ASD. Dynamic FC analyses with DSVB-learned embeddings reveal apparent group differences between ASD and healthy controls in brain network connectivity patterns and switching dynamics of brain states. The code is available at https://***/Monash-NeuroAI/ Deep-Spatiotemporal-Variational-Bayes. © 2023, CC BY-NC-ND.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

A Study on the Utilization of Green Hydrogen Energy - An Overview

A Study on the Utilization of Green Hydrogen Energy - An Ove...

引用

2024 International Conference on science, Engineering and Business for Driving Sustainable Development Goals, SEB4SDG 2024

作者： Ikumapayi, Omolayo M. Laseinde, Opeyeolu T. Ting, Tin T. Afolalu, Sunday A. Adetunla, Adedotun O. Ogedengbe, Temitayo S. University of Johannesburg Department of Mechanical and Industrial Engineering Technology South Africa INTI International University Faculty of Data Science and Information Technology Negeri Sembilan Nilai71800 Malaysia Afe Babalola University Department of Mechanical and Mechatronics Engineering Ado-Ekiti Nigeria University of Johannesburg Dept. of Mechanical Engineering Science South Africa Afe Babalola University Department of Mechanical and Mechatronics Engineering Ado-Ekiti Nigeria Nile University of Nigeria FCT Department of Mechanical Engineering Abuja Nigeria

ISBN: (纸本)9798350358155

This review focuses on the use of hydrogen generated from renewable sources for energy generation and storage systems. Different strategies for producing, storing, and transporting environmentally friendly hydrogen will be covered in the first section of the examination. A critical analysis and choice of production method was studied. The study focused on the problems with transporting and storing hydrogen with a view to suggest solutions. The use of hydrogen in reducing carbon emissions was reviewed and an analysis of selected case studies was done with an emphasis on how hydrogen's carbon footprint varies depending on the gas source. © 2024 IEEE.

关键词： Carbon Energy Fuel Hydrogen

来源：评论

学校读者我要写书评

暂无评论

A motion-based compression algorithm for resource-constrained video camera traps

arXiv

引用

arXiv 2024年

作者： Ratnayake, Malika Nisal Gallon, Lex Toosi, Adel N. Dorin, Alan Agents and Decision-Making Group Dept. of Data Science and AI Faculty of Information Technology Monash University ClaytonVIC3800 Australia Monash e-Research Centre Monash University ClaytonVIC3800 Australia School of Computing and Information Systems Faculty of Engineering and Information Technology The University of Melbourne ParkvilleVIC3052 Australia Dept. of Software Systems and Cybersecurity Faculty of Information Technology Monash University ClaytonVIC3800 Australia

Field-captured video facilitates detailed studies of spatio-temporal aspects of animal locomotion, decision-making and environmental interactions including predator-prey relationships and habitat utilisation. But even though data capture is cheap with mass-produced hardware, storage, processing and transmission overheads provide a hurdle to acquisition of high resolution video from field-situated edge computing devices. Efficient compression algorithms are therefore essential if monitoring is to be conducted on single-board computers in situations where such hurdles must be overcome. Animal motion tracking in the field has unique characteristics that necessitate the use of novel video compression techniques, which may be underexplored or unsuitable in other contexts. In this article, we therefore introduce a new motion analysis-based video compression algorithm specifically designed for camera traps. We implemented and tested this algorithm using a case study of insect-pollinator motion tracking on three popular edge computing platforms. The algorithm identifies and stores only image regions depicting motion relevant to pollination monitoring, reducing overall data size by an average of 87% across diverse test datasets. Our experiments demonstrate the algorithm’s capability to preserve critical information for insect behaviour analysis through both manual observation and automatic analysis of the compressed footage. The method presented in this paper enhances the applicability of low-powered computer vision edge devices to remote, in situ animal motion monitoring, and improves the efficiency of playback during behavioural analyses. Our new software, EcoMotionZip, is available Open Access. Copyright © 2024, The Authors. All rights reserved.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Detection of Off-screen Sound Based on Loss Function of Self-supervised Audio-visual Spatialization 10

Detection of Off-screen Sound Based on Loss Function of Self...

引用

10th IEEE Global Conference on Consumer Electronics, GCCE 2021

作者： Yoshida, Masaki Togo, Ren Ogawa, Takahiro Haseyama, Miki Hokkaido University School of Engineering Japan Hokkaido University Education And Research Center For Mathematical And Data Science Japan Hokkaido University Faculty of Information Science And Technology Japan

ISBN: (纸本)9781665436762

This paper presents a method to detect off-screen sounds based on a loss function of self-supervised audio-visual spatialization. Audio source separation is a long-standing problem, and audio-visual source separation has recently attracted attention in the field of acoustic signal processing, image processing and machine learning. Although visual information in a video has important cues for audio source separation, it does not have information about sounds whose sources are not found in the video. The proposed method detects such off-screen sounds by focusing on correspondences between sounds and their sources in the video. For finding the correspondences, we use audio-visual spatialization, which converts mono audio into spatial audio with visual guidance. Experimental results show that the proposed method can achieve high accuracy in the task of off-screen sound detection. © 2021 IEEE.

关键词： Source separation

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：