检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Qian, Yang Wang, Xinbiao Du, Yuxuan Luo, Yong Tao, Dacheng School of Computer Science Faculty of Engineering University of Sydney NSW2008 Australia Institute of Artificial Intelligence School of Computer Science Wuhan University Wuhan China College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore

Quantum Approximate Optimization Algorithm (QAOA) and its variants exhibit immense potential in tackling combinatorial optimization challenges. However, their practical realization confronts a dilemma: the requisite circuit depth for satisfactory performance is problem-specific and often exceeds the maximum capability of current quantum devices. To address this dilemma, here we first analyze the convergence behavior of QAOA, uncovering the origins of this dilemma and elucidating the intricate relationship between the employed mixer Hamiltonian, the specific problem at hand, and the permissible maximum circuit depth. Harnessing this understanding, we introduce the Mixer Generator Network (MG-Net), a unified deep learning framework adept at dynamically formulating optimal mixer Hamiltonians tailored to distinct tasks and circuit depths. Systematic simulations, encompassing Ising models and weighted Max-Cut instances with up to 64 qubits, substantiate our theoretical findings, highlighting MG-Net's superior performance in terms of both approximation ratio and efficiency. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ML-Based Fault Detection Strategies for Power Electronics 9

ML-Based Fault Detection Strategies for Power Electronics

引用

9th IEEE India International Conference on Power Electronics, IICPE 2023

作者： Jain, Aarushi Lathwal, Rani Data Science Jagannath University New Delhi India Amity University Department of Computer Science & Engineering Noida India

ISBN: (纸本)9798350307252

Power electronics plays a pivotal role in modern energy systems, contributing to improved efficiency, reduced emissions, and enhanced control in various applications such as renewable energy integration, electric vehicles, and smart grids. This vital domain within electrical engineering, has undergone a remarkable transformation through the integration of Machine Learning, as the power electronics industry has witnessed significant advancements in optimizing operations, improving reliability, and enabling sustainable energy solutions. This research paper presents various strategies of Machine learning used in power electronics. It focuses on using Machine Learning based models to examine and train various voltage and current record units obtained by simulated malfunctioning transmission line model created with Matlab /Simulink. This yielded a dataset consisting of 12,001 fault data samples. Machine Learning models SVM, KNN and Decision Tree were trained on the same data and were employed to detect the faults. Next, the model was chosen for its strong fault detection capabilities and potential, which were evaluated based on accuracy, precision, and the F1- score. Effective fault detection techniques play a crucial role in optimizing power system control, reducing energy wastage, and ensuring top-notch performance. © 2023 IEEE.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

kProtoClust:Towards Adaptive k-Prototype Clustering without Known k

引用

computers, Materials & Continua 2025年第3期82卷 4949-4976页

作者： Yuan Ping Huina Li Chun Guo Bin Hao School of Information Engineering Xuchang UniversityXuchang461000China Henan Province Engineering Technology Research Center of Big Data Security andApplications Xuchang461000China College of Computer Science and Technology Guizhou UniversityGuiyang550025China Here Data Technology Shenzhen518000China

Towards optimal k-prototype discovery,k-means-like algorithms give us inspirations of central samples collection,yet the unstable seed samples selection,the hypothesis of a circle-like pattern,and the unknown K are still challenges,particularly for non-predetermined data *** propose an adaptive k-prototype clustering method(kProtoClust)which launches cluster exploration with a sketchy division of K clusters and finds evidence for splitting and *** behalf of a group of data samples,support vectors and outliers from the perspective of support vector data description are not the appropriate candidates for prototypes,while inner samples become the first candidates for instability reduction of *** from the representation of samples in traditional,we extend sample selection by encouraging fictitious samples to emphasize the representativeness of *** get out of the circle-like pattern limitation,we introduce a convex decomposition-based strategy of one-cluster-multiple-prototypes in which convex hulls of varying sizes are prototypes,and accurate connection analysis makes the support of arbitrary cluster shapes *** by geometry,the three presented strategies make kProtoClust bypassing the K dependence well with the global and local position relationship analysis for data *** results on twelve datasets of irregular cluster shape or high dimension suggest that kProtoClust handles arbitrary cluster shapes with prominent accuracy even without the prior knowledge K.

关键词： Prototype finding convex hull support vector data description geometrical information

来源：评论

学校读者我要写书评

暂无评论

Multi-task Learning with Pre-trained Language Models for Mental Illness Screening

Multi-task Learning with Pre-trained Language Models for Men...

引用

2024 IEEE International Conference on Big data, Bigdata 2024

作者： Shrestha, Avantika Tlachac, M.L. Flores, Ricardo Hickey, Kevin Rundensteiner, Elke A. Worcester Polytechnic Institute Data Science Department WorcesterMA United States Bryant University Center for Health and Behavioral Sciences Department of Information Systems and Analytics SmithfieldRI United States University of Concepcion Department of Computer Science Biobio Concepcion Chile Worcester Polytechnic Institute Data Science Department Computer Science Department WorcesterMA United States

ISBN: (纸本)9798350362480

Major depressive disorder (MDD) and post-traumatic stress disorder (PTSD) are mental disorders that reduce quality of life. As they are challenging to detect in a timely manner, recent studies explore the mental illness screening potential of language models on modalities such as transcripts. Such datasets suffer from a limited number of participants. To overcome these challenges, we take a two-pronged approach: (1) we leverage multi-task learning to model multiple illnesses concurrently namely MDD and PTSD screening, and (2) we plug in pre-trained language models as a backbone, namely, Bidirectional Encoder Representations from Transformers (BERT) variants - which are capable of learning the linguistic content of clinical interview transcripts. In particular, we experiment with three multi-task weighting strategies and five BERT variants, applying them to 15 transcript sets extracted from the Distress Analysis Interview Corpus. Our results indicate that leveraging multi-task learning, especially with meta-weighting, increases the screening performance compared to single-task learning. Our multi-task learning model strategies improved the F1 scores for all 15 datasets for both MDD and PTSD screening. Notably, multitask learning improved MDD screening ability by 20 percent with transcripts regarding 'regret' and achieved F1 of 0.89 and 0.82 respectively for MDD and PTSD screening with transcripts regarding 'medical history'. Our findings may help researchers develop more effective mental illness screening models. © 2024 IEEE.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Targeted Universal Adversarial Attack Based on Fourier Transform 2nd

Targeted Universal Adversarial Attack Based on Fourier Tran...

引用

2nd International Conference on data Security and Privacy Protection, DSPP 2024

作者： Sun, Yancheng Chen, Yuling Liu, Ziyang Dou, Hui Tan, Chaoyue The State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550025 China

ISBN: (纸本)9789819785391

The existence of adversarial example reveals the fragility in neural networks, and the exploration of their theoretical origins increases the interpretability of deep learning, enhances researchers’ understanding of neural networks, and contributes to the development of next-generation artificial intelligence, which has attracted widespread research in various fields. The targeted adversarial attack problem based on sample features faces two problems: on the one hand, the difference in the model’s attention to different features in the example;On the other hand, the bias that occurs in adversarial attacks can have an impact on targeted attacks. The mechanism of the human eye relies more on the shape information of the image. However, in the past, artificial intelligence models based on convolutional neural networks often relied on the texture features of image examples to make decisions. At present, general optimize adversarial attack algorithms do not distinguish different types of features based on different parts of the image, but only process the entire example in a general manner, making it difficult to effectively utilize the effective features in the example, resulting in poor algorithm performance and interpretability. This article optimizes the adversarial attack algorithm based on optimization iteration, as follows: Firstly, different types of information in adversarial examples are studied, and fourier transform technology is used to process the attacked original image and obtain its low-frequency information. The obtained low-frequency examples are randomly cropped to obtain some feature examples. Then, the clustering effect was studied when the examples were attacked without targets, and an inter-class smoothing loss was designed to improve the success rate of target attacks. This Rebalance Universal Feature Method (RFM) is based on fourier low pass filtering and inter-class smoothing, which effectively improves the ability of optimization iteration bas

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Unleashing the Power of Knowledge Graph for Recommendation via Invariant Learning 24

Unleashing the Power of Knowledge Graph for Recommendation v...

引用

33rd ACM Web Conference, WWW 2024

作者： Wang, Shuyao Sui, Yongduo Wang, Chao Xiong, Hui School of Data Science University of Science and Technology of China China Hong Kong The Department of Computer Science and Engineering The Hong Kong University of Science and Technology Guangzhou Hkust Fok Ying Tung Research Institute Hong Kong

ISBN: (纸本)9798400701719

Knowledge graph (KG) demonstrates substantial potential for enhancing the performance of recommender systems. Due to its rich semantic content and associations among interactive entities, it can effectively alleviate inherent limitations in collaborative filtering (CF), such as data sparsity or cold-start issues. However, most existing knowledge-aware recommendation models indiscriminately aggregate all information in KG, without considering information specifically relevant to the recommendation task. Such indiscriminate aggregation could introduce additional noisy knowledge into representation learning, which can distort the understanding of users' genuine preferences, thereby sacrificing the recommendation quality. In this paper, we introduce the principle of invariance to the knowledge-aware recommendation, culminating in our Knowledge Graph Invariant Learning (KGIL) framework. It aims to discern and harness the task-relevant knowledge connections within KG to enhance the recommendation models. Specifically, we employ multiple environment generators to simulate diverse noisy KG-environments. Then we devise a novel attention learning mechanism for KG and user-item interaction graph, aiming to learn environment-invariant subgraphs. Leveraging an adversarial optimization strategy, we enhance the diversity of the environments, meanwhile, promote invariant representation learning across environments. We conduct extensive experiments on three datasets and compare KGIL with state-of-the-art methods. The experimental results further demonstrate the superiority of our approach. © 2024 ACM.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Koala: An Index for Quantifying Overlaps with Pre-training Corpora

Koala: An Index for Quantifying Overlaps with Pre-training C...

引用

2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023

作者： Vu, Thuy-Trang He, Xuanli Haffari, Gholamreza Shareghi, Ehsan Department of Data Science & AI Monash University Australia Department of Computer Science University College London United Kingdom

In very recent years more attention has been placed on probing the role of pre-training data in Large Language Models (LLMs) downstream behaviour. Despite the importance, there is no public tool that supports such analysis of pre-training corpora at large scale. To help research in this space, we launch Koala, a searchable index over large pretraining corpora using lossless compressed suffix arrays with highly efficient compression rate and search support. In its first release we index the public proportion of OPT 175B, GPT-3, GPT-Neo, GPT-Neo, LLaMA, BERT, ELECTRA, RoBERTA, XLNet pre-training corpora. Koala provides a framework to do forensic analysis on the current and future benchmarks as well as to assess the degree of memorization in the output from the LLMs. Koala is available for public use at https://***/. © 2023 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Underwater target recognition based on adaptive multi-feature fusion network

引用

Multimedia Tools and Applications 2025年第10期84卷 7297-7317页

作者： Pan, Xiaoying Sun, Jia Feng, TianHao Lei, MingZhu Wang, Hao Zhang, WuXia Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi’an710121 China Xi’an Key Laboratory of Big Data and Intelligent Computing Xi’an710121 China School of Computer Science and Technology Xi’an University of Post & Telecommunications Xi’an710121 China

Due to the complexity of the underwater environment, underwater acoustic target recognition is more challenging than ordinary target recognition, and has become a hot topic in the field of underwater acoustics research. In recent years, deep learning has been widely used in underwater recognition due to its powerful feature learning capabilities. However, most deep learning-based underwater target recognition methods use only the time-frequency domain features of signals, ignoring the frequency domain image features of signals. Additionally, they only use simple summation or splicing strategies to fuse and discriminate the extracted features, which leads to limited improvement in the accuracy of underwater target recognition. To address these issues, this paper proposes an underwater target recognition method based on an adaptive multi-feature fusion network. The method consists of a data pre-processing module, a multi-dimensional feature extraction module, and an adaptive multi-feature fusion module. In the multi-dimensional feature extraction module, the long short time memory network (LSTM) and the one-dimensional convolutional neural network (1DCNN) are used to extract the time-frequency features of the underwater signal. Furthermore, the two-dimensional convolutional neural network (2DCNN) is used to extract the image features in the frequency domain. The adaptive multi-feature fusion module uses an attention mechanism for adaptive weighted fusion to make full use of the learned features. The effectiveness of the proposed method is validated on the ShipEar dataset, and the recognition accuracy reaches 94.92%, which is higher than other existing methods. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Comparison of Different Machine Learning Algorithms for Predicting Loan Risk Categories

Comparison of Different Machine Learning Algorithms for Pred...

引用

2023 International Conference on computer science, Information Technology and Engineering, ICCoSITE 2023

作者： Sudjono, Salomo Hendrian Adrian, Favian H.N. Sunarya, Caroline Angelina Ariyanto, Gabrielle Felicia Sagala, Noviyanti T M Bina Nusantara University Data Science Program School of Computer Science Jakarta11480 Indonesia School of Computer Science Bina Nusantara University Statistics Department Jakarta11480 Indonesia

ISBN: (纸本)9798350320954

There are many cases where borrowed money by debtors is not returned. It is because the company misjudged in determining the risk of lending. Thus, debtors cannot repay their debts and end up in losses on the company's side. Thus, this research aims to create an accurate classification model for determining loan risk categories to minimize business losses. We used the public dataset from kaggle website. Then we perform several data transformation and analysis methods are performed to obtain information from the data. We built 2 classification models to predict the original label. Unfortunately, the desired results did not achieve based on the f1-score. Therefore, the clustering method using K-Means is applied to make a new label for the dataset and determine the behavior of each cluster. Each cluster is labeled then build a model to perform cluster classification. We created several classification models and found that gradient tree boosting is the most accurate predictor of the loan risk category based on the accuracy. We used clustering to create a classification model that can have high accuracy. The classification model we built can have high accuracy because it uses clustering. The empirical results of this study and others pave the way for further in-depth future work to guarantee that the algorithm performs acceptably when confronted with more complicated real data. © 2023 IEEE.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Brain Tumor Segmentation and Classification Using ACGAN with U-Net and Independent CNN-Based Validation

Brain Tumor Segmentation and Classification Using ACGAN with...

引用

2024 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2024

作者： Wagle, S. Pandey, S. Poudel, S. Poudel, K. Middle Tennessee State University Computational And Data Science MurfreesboroTN United States Fisk University Mathematics And Computer Science NashvilleTN United States Middle Tennessee State University Computer Science MurfreesboroTN United States

ISBN: (纸本)9798350388572

This study presents an approach that combines Auxiliary Classifier Generative Adversarial Networks (ACGAN) with U-Net architecture to enhance the brain tumor segmentation and classification of brain tumors using synthetic data. Also, the CNN based classifier was used, thus using classification as a means to verify the accuracy and realism of the synthetic image generated by the ACGAN. This strategy aims to improve AI model training by generating diverse synthetic images, addressing issues like data scarcity, necessity for exact tumor segmentation, validation of synthetic image quality, and ethical concerns related to patient data. ACGAN produces artificial images for three types of brain tumors: meningitis, glioma and pituitary as well as healthy brain images. The incorporation of UNet enhances the accuracy of segmentation considerably. An independent CNN-based classifier is used to categorize actual and synthetic images separately in order to verify the accuracy and realism of the synthetic images. The classifier achieved an overall accuracy of 0.84 when trained on combined real and synthetic images, therefore showing the suitability of synthetic images to augment training datasets. The U-Net model performed very well in the generation of accurate segmentation maps, as evidenced by a Dice Coefficient of 76.43% and a MeanIOU of 92.91%, with high sensitivity of 99.49% and specificity of 99.87%. These results demonstrate the great potential of integrating ACGAN with U-Net in the pursuit of developing AI-driven medical imaging solutions. © 2024 IEEE.

关键词： Generative adversarial networks

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：