检索结果-内蒙古大学图书馆

4th International Conference of science and Information technology in Smart Administration, ICSINTESA 2024

作者： Prasetyo, Simeon Yuda Rachmawati, Ika Dyah Agustia Wulandari, Ajeng Bina Nusantara University School of Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350376111

Breast cancer represents a significant global health burden, with millions of new cases diagnosed each year, making it the most common cancer in women worldwide and a leading cause of cancer-related mortality. Early detection is crucial for improving patient outcomes and reducing mortality rates associated with breast cancer. Machine learning techniques offer promising avenues for enhancing early detection and diagnosis. In this study, we investigate the performance of Multi Layer Perceptron (MLP) models with varying numbers of neuron units in two hidden layers for breast cancer diagnosis. Through systematic experimentation, we identify the optimal configuration, achieving the highest accuracy of 84.91% with the first hidden layer containing 5 neuron units and the second hidden layer containing 10 neuron units. Interestingly, competitive performance is observed in models with 5 neuron units in both hidden layers, showcasing accuracy levels ranging from 84.8% to 84.9%. Variations in other performance metrics across different configurations are minor. Overall, MLP models with 10 neuron units in both hidden layers demonstrate superior performance, with models featuring 5 units in both layers as viable alternatives. These findings underscore the versatility of MLP models in healthcare applications and contribute valuable insights to breast cancer diagnostics. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Align is not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Models

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年第6期35卷 5475-5488页

作者： Wang, Youze Hu, Wenbo Dong, Yinpeng Liu, Jing Zhang, Hanwang Hong, Richang Hefei University of Technology School of Computer Science and Information Engineering Hefei230009 China Tsinghua University Beijing100084 China Chinese academy of science Institute of automation Beijing100190 China Nanyang Technological University School of Computer Science and Engineering 639798 Singapore

Large Language Models (LLMs) have evolved into Multimodal Large Language Models (MLLMs), significantly enhancing their capabilities by integrating visual information and other types, thus aligning more closely with the nature of human intelligence, which processes a variety of data forms beyond just text. Despite advancements, the undesirable generation of these models remains a critical concern, particularly due to vulnerabilities exposed by text-based jailbreak attacks, which have represented a significant threat by challenging existing safety protocols. Motivated by the unique security risks posed by the integration of new and old modalities for MLLMs, we propose a unified multimodal universal jailbreak attack framework that leverages iterative image-text interactions and transfer-based strategy to generate a universal adversarial suffix and image. Our work not only highlights the interaction of image-text modalities can be used as a critical vulnerability but also validates that multimodal universal jailbreak attacks can bring higher-quality undesirable generations across different MLLMs. We evaluate the undesirable context generation of MLLMs like LLaVA, Yi-VL, MiniGPT4, MiniGPT-v2, and InstructBLIP, and reveal significant multimodal safety alignment issues, highlighting the inadequacy of current safety mechanisms against sophisticated multimodal attacks. This study underscores the urgent need for robust safety measures in MLLMs, advocating for a comprehensive review and enhancement of security protocols to mitigate potential risks associated with multimodal capabilities. © 1991-2012 IEEE.

关键词： Human form models

来源：评论

学校读者我要写书评

暂无评论

PLUS-CODE+: Zero-installment Rover Indoor Localization

引用

IEEE Sensors Journal 2025年第12期25卷 23088-23104页

作者： Khudoyberdiev, Azimbek Kim, Ho Young Ryoo, Jihoon Incheon21985 Korea Republic of Stony Brook University Department of Computer Science United States

This paper presents PLUS-CODE+, an innovative zero-installation indoor localization system designed for autonomous robots, addressing the challenges posed by conventional Indoor Positioning Systems (IPS) such as extensive pre-installation and multi-floor navigation difficulties. PLUS-CODE+ introduces five major innovations: (i) it eliminates the need for sensor or antenna installation, drastically simplifying deployment;(ii) it utilizes OCR-based Visual RTK to enhance GNSS-DR data in real-time, ensuring high localization accuracy even in environments where GNSS signals are compromised;(iii) it introduces a DNN-based adaptive fusion model that seamlessly integrates GNSS-DR with vRTK measurements, further enhancing positioning accuracy by compensating for predictable sensor errors;(iv) it incorporates a global indoor location code encoder-decoder, facilitating universal access and shareability of multi-floor locations;and (v) it achieves centimeter-level accuracy in localization. Our proof-of-concept tests conducted in large multi-floor environments demonstrate that PLUS-CODE+ not only meets but exceeds the precision requirements for indoor localization, attaining accuracy on par with satellite-based GNSS RTK systems. This capability significantly enhances autonomous navigation in complex indoor settings, enabling seamless transitions between indoor and outdoor environments. © 2001-2012 IEEE.

关键词： Global positioning system

来源：评论

学校读者我要写书评

暂无评论

Automated Depression Detection from Tweets: A Comparison of NLP Techniques 8

Automated Depression Detection from Tweets: A Comparison of ...

引用

8th International Artificial Intelligence and Data Processing Symposium, IDAP 2024

作者： Balci, Emirhan Sarac, Esra Adana Science and Technology University Department of Computer Engineering Adana Turkey

ISBN: (纸本)9798331531492

This paper aims to classify suicidal ideation as a symptom of depression from social media posts by applying the state-of-the-art classification model BERT (Bidirectional Encoder Representations from Transformers) and three traditional machine learning algorithms for binary classification. Since depression is one of the most prevalent mental health disorders amongst psychiatric disorders, the authors intended to present an experimental analysis of the machine learning classifier results as a comparison of novel depression detection techniques. We utilized undiagnosed user posts from Twitter as our dataset and tested the fine-tuned BERT model by applying hold-out and 10-fold cross-validation techniques. Since the dataset is highly unbalanced, Support Vector Machine (SVM), Naive Bayes, and Random Forest algorithms were employed on the same dataset with and without the oversampling method SMOTE (Synthetic Minority Oversampling Technique). The results demonstrate that traditional machine learning classifiers cannot infer sentiment from data containing various linguistic cues, such as depression symptoms. On the other hand, the state-of-the-art model BERT achieves 99.29% and 99.56% macro and micro-F-measure values, respectively, surpassing traditional machine learning algorithms in terms of these metrics. As a robust solution to depression detection from textual data, the BERT model is more trustworthy than the traditional machine learning classifiers to detect specific cues related to depression and similar mental disorders. This study contributes to the relevant research areas of natural language processing by indicating the performance difference between the BERT model and several traditional machine learning algorithms as a generalized approach for classification tasks. © 2024 IEEE.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Adaptable Machine Learning Methods for a Twitter Followee Recommendation System 2

Adaptable Machine Learning Methods for a Twitter Followee Re...

引用

2nd IEEE International Conference on IoT, Communication and Automation technology, ICICAT 2024

作者： Yadav, Sandeep Srivastav, Shashank Buddha Institute of Technology Computer Science and Engineering Department Gorakhpur India

ISBN: (纸本)9798350368109

Recommender systems for social networking have recently used machine learning (ML) methods. This paper describes a multi-agent system that simulates a Twitter recommender system to give users a list of helpful suggestions, i.e., a list of users who are followed, or they want to follow. When processing data in parallel on multi-node distributed systems, a machine learning technique (such as a neural network or multilayer perceptron) is evaluated for scalability using a simulator. A multi-agent modelling simulates the dispersed environment. The quantity of nodes, the method used within the model recommender framework, and the real followers and followees data are the first parameters that need to be configured on the simulator. The experimental findings were acquired on three different datasets to evaluate the speed and precision of a simulated recommender system when evaluating the machine learning method under various conditions. © 2024 IEEE.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Hybrid brave-hunting optimisation for heart disease detection model with SVM coupled deep CNN

引用

International Journal of Intelligent Information and Database Systems 2025年第1期17卷 92-123页

作者： Tambe, Pravin M. Shrivastava, Manish Department of Computer Science and Engineering Vivekananda Global University Jagatpura Rajasthan Jaipur303012 India

This research proposes a novel hybrid optimisation method called brave-hunting optimisation (BHO) inspired by lion optimisation (LO) and coyote optimisation (CO). The BHO algorithm is employed to fine-tune the SVM parameters, enhancing its classification performance. Simultaneously, a deep CNN model extracts complex and informative features from medical data. The combined approach capitalises on the strengths of both optimisation techniques to create a robust and accurate model for heart disease diagnosis. The performance evaluation of our model is conducted using comprehensive metrics, which achieve an accuracy of 94.89%, an F1-score of 94.48%, a precision of 94.48%, and a recall of 94.58% for a 90 TP. In the context of a ten k-fold evaluation, achieved 94.78% accuracy, 94.36% F1-score, 94.55% precision, and 94.13% recall. Copyright © 2025 Inderscience Enterprises Ltd.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Formal Foundations for Translational Separation Logic Verifiers

引用

Proceedings of the ACM on Programming Languages 2025年第POPL期9卷 569-599页

作者： Dardinier, Thibault Sammler, Michael Parthasarathy, Gaurav Summers, Alexander J. Müller, Peter ETH Zurich Department of Computer Science Zurich Switzerland University of British Columbia Vancouver Canada

Program verification tools are often implemented as front-end translations of an input program into an intermediate verification language (IVL) such as Boogie, GIL, Viper, or Why3. The resulting IVL program is then verified using an existing back-end verifier. A soundness proof for such a translational verifier needs to relate the input program and verification logic to the semantics of the IVL, which in turn needs to be connected with the verification logic implemented in the back-end verifiers. Performing such proofs is challenging due to the large semantic gap between the input and output programs and logics, especially for complex verification logics such as separation logic. This paper presents a formal framework for reasoning about translational separation logic verifiers. At its center is a generic core IVL that captures the essence of different separation logics. We define its operational semantics and formally connect it to two different back-end verifiers, which use symbolic execution and verification condition generation, resp. Crucially, this semantics uses angelic non-determinism to enable the application of different proof search algorithms and heuristics in the back-end verifiers. An axiomatic semantics for the core IVL simplifies reasoning about the front-end translation by performing essential proof steps once and for all in the equivalence proof with the operational semantics rather than for each concrete front-end translation. We illustrate the usefulness of our formal framework by instantiating our core IVL with elements of Viper and connecting it to two Viper back-ends as well as a front-end for concurrent separation logic. All our technical results have been formalized in Isabelle/HOL, including the core IVL and its semantics, the semantics of two back-ends for a subset of Viper, and all proofs. © 2025 Copyright held by the owner/author(s).

关键词： Program translators

来源：评论

学校读者我要写书评

暂无评论

Movie Recommendation System: A Comparison of Content-Based and Collaborative Filtering 9th

Movie Recommendation System: A Comparison of Content-Based a...

引用

9th International Conference on computer science and Computational Intelligence, ICCSCI 2024

作者： Kurniawan, Hans Hendersen Lukman, William Susanto Fredyan, Renaldy Ibrahim, Muhammad Amien Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia

Watching movies has been our source of entertainment for decades. In this modern world, watching movies has never been more convenient with the existence of video streaming services. This convenience also comes with new problems because there are a lot of movies and series on the platform that exploring it on our own will take time and effort. To solve that problem, companies use recommendation systems to improve user experience. In the field of recommendation systems, there are two famous approaches, content-based filtering, and collaborative filtering. This research aims to compare both methods and find the best possible method to use in a video streaming service platform. We found that the difference between the two is located on the data that they need for the model to work properly. Content-based recommendation systems have higher accuracy when using a limited amount of data while collaborative filtering needs more data about user's behavior. Other than that, both methods give different recommendations because content-based only gives recommendations that are like the content that the user likes while collaborative filtering recommends contents that other users like. © 2024 The Authors.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Automated Pulmonary Tuberculosis Detection in Chest Radiographs using Pretrained DCNN Models 9

Automated Pulmonary Tuberculosis Detection in Chest Radiogra...

引用

9th International Conference on Information Management and technology, ICIMTech 2024

作者： Prasetyo, Simeon Yuda School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350390025

The problem of pulmonary tuberculosis (PTB) worldwide is still considered to be a significant one, and it is therefore necessary to develop precise and effective diagnostic tools that will make it possible to carry out early interventions and treatment. In this research, the deep convolutional neural network (DCNN) architectures named VGG-16, VGG-19, ResNet-50, ResNet-101, and MobileNet were utilized for the detection of PTB from chest radiographs. By means of transfer learning and fine-tuning approaches it was possible to increase the diagnostic performance. Notably, VGG-16 consistently demonstrated exceptional performance, achieving a remarkable accuracy of 99.524% in both transfer learning and fine-tuning phases. Similarly, MobileNet exhibited strong performance, with an accuracy of 99.524% in transfer learning and 98.095% in fine-tuning. The results obtained show that VGG-16 and MobileNet are very good for the detection of PTB from chest X-ray images. Moreover, the fine-tuning showed the best performance of ResNet models, therefore, it confirmed the effectiveness of the iterative refinement process. In general, the results mainly highlight the significance of transfer learning and fine-tuning in the best model parameter adjustment, with VGG-16 being the most effective model. Possible future directions will be investigated through ensemble methods, domain-specific knowledge integration, advanced augmentation techniques, and multimodal data sources that will aim to improve PTB detection accuracy and deal with the changing healthcare challenges. © 2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Successful Integration of IoT and Blockchain Technologies Using Several Machine Learning Algorithms 5

Successful Integration of IoT and Blockchain Technologies Us...

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Calarany, C. Indumathy, M. Senthilraja, P. Suganya, D. Gopi Vardhan, V. Rahul, Yelisetty Shanmukh Tagore Government Arts and Science College Department of Computer Science Puducherry India Rajiv Gandhi College of Engineering & Technology Department of Information Technology Kirumampakkam India K.S.Rangasamy College of Technology Department of Computer Science Tamil Nadu India Rajiv Gandhi College of Engineering & Technology Department of Computer Science Kirumampakkam India Data Science and Business Systems Srm Institute of Science and Technology Kattankulathur India

ISBN: (纸本)9798350383522

Internet of Things (IoT) produces massive amounts of data that need to be processed and saved securely. The strong features of Blockchain makes it as a best candidate for storing the data received from IoT sensors. However, there is a need of concern to take care of the challenges associated with both IoT and blockchain paradigms. Firstly, the enormous amount of data should be effortlessly handled by Blockchain network, without adding much complexity. Secondly, the heterogeneous nature of data that are received from various IoT Sensors should be stored within the blockchain. In this paper, a conceptual framework based on Multimodal Machine Learning (MML) algorithm is proposed as an interface between the IoT sensors and Blockchain networks. The MML algorithm is used to understand the different modalities of the data and provides a way to manage the heterogeneity in that data. The MML algorithms provides an intelligent data processing that allows for real-time data storage in the blockchain networks. The conceptual frame assumes that audio, video, and text are the three types of data as received from IoT. These inputs are processed in simplistic Recurrent neural network RNN that acts as MML and then passed to Blockchain networks for secure storage. Simulation of the above said conceptual framework is performed assuming all other relevant requirements of IoT, MML and Blockchain are taken into account with default parameters and values. The results obtained provide a promising note for future scope in this direction. © 2024 IEEE.

关键词： IoT MML RNN

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：