检索结果-内蒙古大学图书馆

2024 Winter Simulation Conference, WSC 2024

作者： Chan, Chew Wye Gan, Boon Ping Cai, Wentong D-SIMLAB Technologies Pte Ltd Singapore College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (纸本)9798331534202

Adapting dispatch rules via machine learning in a complex manufacturing environment has shown overall factory performance in various studies. However, the performance of the machine learning model depends on the training data. Limited data could reduce the prediction accuracy of the machine learning model, thereby negatively influencing the overall factory performance. Addressing this, we generate synthetic data for the lot attributes, simulate it through a discrete event simulator, and use the resulting data to improve the prediction accuracy for the machine learning model. We evaluate three synthetic data generation approaches: Latin Hypercube, Synthetic Minority Oversampling Technique, and Generative Adversarial Networks (GAN), demonstrating GAN suitability for synthetic data generation. To validate our approach, we apply two evaluation processes: Train on Real, Test on Real, and Train on Synthetic, Test on Real, showing the improved predictive accuracy of the machine learning model when trained with synthetic data. © 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

A Multi-Objective Artificial Physics Optimization Algorithm Based on Two-Phase Search 8

A Multi-Objective Artificial Physics Optimization Algorithm ...

引用

8th International Symposium on Computer science and Intelligent Control, ISCSIC 2024

作者： Zhang, Huihua Xie, Liping Taiyuan University of Science and Technology Shanxi Key Laboratory of Big Data Analysis and Parallel Computing Taiyuan China

ISBN: (纸本)9798350380286

Aiming at the problems of insufficient utilization of information about elite particles in archive and instability of particle motion in the population in the multi-objective artificial physics optimization algorithm (MOAPO) in solving multiobjective optimization problems, A multi-objective artificial physics optimization algorithm based on two-phase search (TPMOAPO) is proposed. To begin with, the algorithm improves the calculation of the mass of particles, so that the strength and weakness of the particles can be accurately transformed into the corresponding masses while improving the efficiency of particle mass calculation. Next, a two-phase search strategy is proposed, which makes the algorithm have strong exploration ability in the first phase, and the second phase gradually enhances the exploitation capability with iterations, which solves the problem of instability motion of particles in the search process. Finally, the simulated binary crossover (SBX) and polynomial-based mutation (PM) operators are adopted in the archive to further enhance the search capability of the algorithm. For verifying the performance of TP-MOAPO, 21 benchmark functions were selected to compare with the classical multi-objective particle swarm optimization algorithms: MOPSO, dMOPSO, SMPSO, MMOPSO, and NMPSO, and the experimental results show the superiority of TP-MOAPO in these functions. © 2024 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

UHH at AVeriTeC: RAG for Fact-Checking with Real-World Claims 7

UHH at AVeriTeC: RAG for Fact-Checking with Real-World Claim...

引用

7th Fact Extraction and VERification Workshop, FEVER 2024

作者： Sevgili, Özge Nikishina, Irina Yimam, Seid Muhie Semmann, Martin Biemann, Chris Language Technology Group Dept. of Informatics & Hub of Computing and Data Science Universität Hamburg Germany

ISBN: (纸本)9798891761728

This paper presents UHH’s approach developed for the AVeriTeC shared task. The goal of the challenge is to verify given real-world claims with evidences from the Web. In this shared task, we investigate a Retrieval-Augmented Generation (RAG) model, which mainly contains retrieval, generation, and augmentation components. We start with the selection of the top 10k evidences via BM25 scores, and continue with two approaches to retrieve the most similar evidences: (1) to retrieve top 10 evidences through vector similarity, generate questions for them, and rerank them or (2) to generate questions for the claim and retrieve the most similar evidence, again, through vector similarity. After retrieving the top evidences, a Large Language Model (LLM) is prompted using the claim along with either all evidences or individual evidence to predict the label. Our system submission, UHH, using the first approach and individual evidence prompts, ranks 6th out of 23 systems. © 2024 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

Machine Learning Approaches for Extremism Detection: Challenges, Pitfall and Opportunities

Machine Learning Approaches for Extremism Detection: Challen...

引用

2024 International Conference on IT and Industrial Technologies, ICIT 2024

作者： Hussain, Muhammad Anwar Shahzad, Khurram Sulaiman, Sarina School of Computing Universiti of Technologi Malaysia Johor Malaysia Department of Data Science University of the Punjab Lahore Pakistan

ISBN: (纸本)9798331504465

Social networks, such as Facebook, Twitter, and YouTube, are free for everyone, including extremist groups. These extremist groups may use social media to spread radical ideas, disseminate propaganda, and recruit young people to promote their cause. Therefore, identifying and eradicating extremist content is among the top challenges for technology companies, counter-terrorism agencies and regulatory authorities. In this study, we have reviewed extremism detection in social media literature. In particular, a systematic literature review is conducted and a synthesis of the literature is performed to examine the strengths and weaknesses of the existing studies on extremism detection. Furthermore, the challenges are identified and opportunities for future research are discussed. We contend that the results of the study can be used by researchers for a better comprehension of the landscape of online extremism extension, as well as to open new horizons for the research community. © 2024 IEEE.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

From Text to Visuals: Advancements in Depression Prediction Using AI and Machine Learning Techniques

From Text to Visuals: Advancements in Depression Prediction ...

引用

2023 IEEE International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication Engineering, RMKMATE 2023

作者： Annapoorani, S. Saravanan, P. Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Kattankulatur India

ISBN: (纸本)9798350305708

Social lifestyle and COVID pandemic situation to produce a direct impact on mental health. Depression remains a primary cause of disability worldwide and contributes significantly to the global health burden. It can typically lead to suicidal ideation and have a negative impact on anyone's professional and personal life. Artificial intelligence, machine learning, and deep learning techniques can forecast depression in a timely manner utilizing a variety of resources. Different kinds of sources, such as surveys, social networking sites, video images, and speech, can be used to accurately identify depression without the assistance of a psychiatrist. People on social networking sites express their feelings through appropriate text, which may be examined using machine learning algorithms. Through visual and speech data, deep learning approaches properly provide remarkable accuracy in predicting depression. This survey study is useful in identifying depression accuracy in advanced ways utilizing diverse resources. © 2023 IEEE.

关键词： Classification Algorithm Deep Learning Depression Ensemble Method Machine Learning

来源：评论

学校读者我要写书评

暂无评论

Enhanced study on Deep learning model for kidney segmentation using DCE-MRI

Enhanced study on Deep learning model for kidney segmentatio...

引用

2023 IEEE International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication Engineering, RMKMATE 2023

作者： Nagarajan, S. Ramprasath, M. Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Chengalpattu India

ISBN: (纸本)9798350305708

Medical imaging is capturing pictures of bodily components for diagnostic or research reasons. Because of advancements in image-handling techniques, which include picture recognition, examination, and upgrading, clinical imaging is expanding swiftly. Picture division is a vital subject in picture handling and PC vision with applications, for example, scene grasping, clinical picture examination, mechanical discernment, video observation, expanded reality, and picture pressure, among numerous others. Numerous picture segmentation methods have been created and are available in the literature. There has been a lot of work done to develop techniques for segmenting pictures using deep-learning models since they have proved effective in various vision applications. Deep learning has turned into a functioning exploration point in the field of clinical picture examination. Compared to the laborious and lengthy conventional technique, deep learning (DL) automatic detection algorithms can speed up diagnostics, increase test accuracy, lower expenses, and lessen the workload on the radiologist. Kidney segmentation is an integral part of any non-intrusive computer-assisted diagnostic (CAD) system for rapidly recognising severe renal repudiation because of the intensity of inhomogeneity brought on by errors in the image capture process, efficient kidney segmentation is challenging in evaluating and therapeutic planning of kidney-related disorders. This article addresses recent developments in DL-based kidney tumor segmentation systems. We highlight their fundamental components and numerous approaches as we discuss the main medical image kinds, segmentation methods, and evaluation standards for segmentation outcomes in kidney tumor++ segmentation. © 2023 IEEE.

关键词： Automatic Detection algorithms Computer-Assisted diagnostic system Deep Learning Kidney tumor segmentation Vision applications

来源：评论

学校读者我要写书评

暂无评论

Intention Analysis Makes LLMs A Good Jailbreak Defender 31

Intention Analysis Makes LLMs A Good Jailbreak Defender

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Zhang, Yuqi Ding, Liang Zhang, Lefei Tao, Dacheng School of Computer Science Wuhan University China The University of Sydney Australia College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore

ISBN: (纸本)9798891761964

Aligning large language models (LLMs) with human values, particularly when facing complex and stealthy jailbreak attacks, presents a formidable challenge. Unfortunately, existing methods often overlook this intrinsic nature of jailbreaks, which limits their effectiveness in such complex scenarios. In this study, we present a simple yet highly effective defense strategy, i.e., Intention Analysis (IA). IA works by triggering LLMs' inherent self-correct and improve ability through a two-stage process: 1) analyzing the essential intention of the user input, and 2) providing final policy-aligned responses based on the first round conversation. Notably, IA is an inference-only method, thus could enhance LLM safety without compromising their helpfulness. Extensive experiments on varying jailbreak benchmarks across a wide range of LLMs show that IA could consistently and significantly reduce the harmfulness in responses (averagely -48.2% attack success rate). Encouragingly, with our IA, Vicuna-7B even outperforms GPT-3.5 regarding attack success rate. We empirically demonstrate that, to some extent, IA is robust to errors in generated intentions. Further analyses reveal the underlying principle of IA: suppressing LLM's tendency to follow jailbreak prompts, thereby enhancing safety. © 2025 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

DEEP ORTHOGONAL HYPERSPHERE COMPRESSION FOR ANOMALY DETECTION 12

DEEP ORTHOGONAL HYPERSPHERE COMPRESSION FOR ANOMALY DETECTIO...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Zhang, Yunhe Sun, Yan Cai, Jinyu Fan, Jicong School of Data Science The Chinese University of Hong Kong Shenzhen China Shenzhen Research Institute of Big Data Shenzhen China School of Computing National University of Singapore Singapore Institute of Data Science National University of Singapore Singapore

Many well-known and effective anomaly detection methods assume that a reasonable decision boundary has a hypersphere shape, which however is difficult to obtain in practice and is not sufficiently compact, especially when the data are in high-dimensional spaces. In this paper, we first propose a novel deep anomaly detection model that improves the original hypersphere learning through an orthogonal projection layer, which ensures that the training data distribution is consistent with the hypersphere hypothesis, thereby increasing the true positive rate and decreasing the false negative rate. Moreover, we propose a bi-hypersphere compression method to obtain a hyperspherical shell that yields a more compact decision region than a hyperball, which is demonstrated theoretically and numerically. The proposed methods are not confined to common datasets such as image and tabular data, but are also extended to a more challenging but promising scenario, graph-level anomaly detection, which learns graph representation with maximum mutual information between the substructure and global structure features while exploring orthogonal single- or bi-hypersphere anomaly decision boundaries. The numerical and visualization results on benchmark datasets demonstrate the superiority of our methods in comparison to many baselines and state-of-the-art methods. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Enhancing intrusion detection in IIoT: optimized CNN model with multi-class SMOTE balancing

引用

Neural computing and Applications 2024年第24期36卷 14643-14659页

作者： Eid, Abdulrahman Mahmoud Soudan, Bassel Nassif, Ali Bou Injadat, MohammadNoor Department of Computer Engineering College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates Department of Data Science and AI Faculty of Information Technology Zarqa University Zarqa Jordan

This work introduces an intrusion detection system (IDS) tailored for industrial internet of things (IIoT) environments based on an optimized convolutional neural network (CNN) model. The model is trained on a dataset that was balanced using a novel multi-class implementation of synthetic minority over-sampling technique (SMOTE) that ensures equal representation of all classes. Additionally, systematic optimization will be used to fine tune the hyperparameters of the CNN model and mitigate the effects of the increased size of the training dataset. Evaluation results will demonstrate substantial improvement in performance when the optimized CNN model is trained on the balanced dataset. The proposed IDS will be evaluated using the IIoT-specific WUSTL-IIOT-2021 dataset, and then its generalization capability will be verified using the non-domain specific UNSW_NB15 dataset. The model’s performance will be evaluated using accuracy, precision, recall, and F1-score metrics. The results will demonstrate that the proposed IDS is highly effective with performance exceeding 99.9% on all performance metrics. The IDS is also highly effective in detecting intrusion for generic IT networks achieving improvements in excess of 30% compared to the default baseline model. The results emphasize the versatility and effectiveness of the proposed IDS model, making it a reliable and adaptable solution for enhancing network security across diverse network environments. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

An in-depth investigation of sparse rate reduction in transformer-like models 24

An in-depth investigation of sparse rate reduction in transf...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Yunzhe Hu Difan Zou Dong Xu School of Computing and Data Science The University of Hong Kong School of Computing and Data Science & Institute of Data Science The University of Hong Kong

ISBN: (纸本)9798331314385

Deep neural networks have long been criticized for being black-box. To unveil the inner workings of modern neural architectures, a recent work [45] proposed an information-theoretic objective function called Sparse Rate Reduction (SRR) and interpreted its unrolled optimization as a Transformer-like model called Coding Rate Reduction Transformer (CRATE). However, the focus of the study was primarily on the basic implementation, and whether this objective is optimized in practice and its causal relationship to generalization remain elusive. Going beyond this study, we derive different implementations by analyzing layer-wise behaviors of CRATE, both theoretically and empirically. To reveal the predictive power of SRR on generalization, we collect a set of model variants induced by varied implementations and hyperparameters and evaluate SRR as a complexity measure based on its correlation with generalization. Surprisingly, we find out that SRR has a positive correlation coefficient and outperforms other baseline measures, such as path-norm and sharpness-based ones. Furthermore, we show that generalization can be improved using SRR as regularization on benchmark image classification datasets. We hope this paper can shed light on leveraging SRR to design principled models and study their generalization ability.

关键词：

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：