检索结果-内蒙古大学图书馆

9th IEEE International Conference on Computational Intelligence and Applications, ICCIA 2024

作者： Tantikulvichit, Naragorn Kosolsombat, Somkiat Ratanavilisagul, Chiabwoot College of Interdisciplinary Studies Thammasat University Data Science and Innovation Pathum Thani Thailand King Mongkut's University of Technology Faculty of Applied Science Department of Computer and Information Science North Bangkok Thailand

ISBN: (纸本)9798350352214

In today's world, cyber-attacks are on the rise, and PDF files are commonly used as a means of attack. One common type of attack through PDF files is the covert embedding of dangerous malware and tricking users into clicking on malicious links. The victims may have their important data stolen and suffer various forms of damage. Detecting malware embedded in PDF files can help mitigate the harm to users. This project aims to study methods for detecting malware embedded in PDF files using machine learning techniques, with the best-performing model being Gradient Boosting, achieving an accuracy of 99% in 5-fold cross-validation and 97% using 10 features. Using Feature Selection Technique Voting from 3 Models consist of Logistic Regression, Random Forest, Lasso Regression, Each model will choose matching features to use for machine learning analysis. This project approach reduce feature for machine learning to detect PDFMalware. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Advances, challenges and opportunities in creating data for trustworthy AI (vol 4, pg 669, 2022)

引用

NATURE MACHINE INTELLIGENCE 2022年第10期4卷 904-904页

作者： Liang, Weixin Tadesse, Girmaw Abebe Ho, Daniel Fei-Fei, L. Zaharia, Matei Zhang, Ce Zou, James Department of Computer Science Stanford University Stanford CA USA Department of Biomedical Data Science Stanford University Stanford CA USA IBM Research – Africa Nairobi Kenya Stanford Law School Stanford University Stanford CA USA Department of Computer Science ETH Zurich Zurich Switzerland

As artificial intelligence (AI) transitions from research to deployment, creating the appropriate datasets and data pipelines to develop and evaluate AI models is increasingly the biggest challenge. Automated AI model builders that are publicly available can now achieve top performance in many applications. In contrast, the design and sculpting of the data used to develop AI often rely on bespoke manual work, and they critically affect the trustworthiness of the model. This Perspective discusses key considerations for each stage of the data-for-AI pipeline—starting from data design to data sculpting (for example, cleaning, valuation and annotation) and data evaluation—to make AI more reliable. We highlight technical advances that help to make the data-for-AI pipeline more scalable and rigorous. Furthermore, we discuss how recent data regulations and policies can impact AI.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Multivariate Time-Series Deep Learning for Joint Prediction of Temperature and Relative Humidity in a Closed Space 8

Multivariate Time-Series Deep Learning for Joint Prediction ...

引用

8th International Conference on computer science and Computational Intelligence, ICCSCI 2023

作者： Gunawan, Fergianto E. Budiman, Arief S. Pardamean, Bens Juana, Endang Romeli, Sugiarto Cenggoro, Tjeng W. Purwandari, Kartika Hidayat, Alam A. Redi, Anak A.N.P. Asrol, Muhammad Industrial Engineering Department BINUS Graduate Program - Master of Industrial Engineering Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Program Bina Nusantara University Jakarta11480 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Electrical Engineering Department Faculty of Industrial Technology Universitas Trisakti Jakarta11440 Indonesia PT Impack Pratama Industri Jakarta14350 Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Mathematics Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia

An accurate predictive model of temperature and humidity plays a vital role in many industrial processes that utilize a closed space such as in agriculture and building management. With the exceptional performance of deep learning on time-series data, developing a predictive temperature and humidity model with deep learning is propitious. In this study, we demonstrated that deep learning models with multivariate time-series data produce remarkable performance for temperature and relative humidity prediction in a closed space. In detail, all deep learning models that we developed in this study achieve almost perfect performance with an R value over 0.99. © 2023 The Authors. Published by Elsevier B.V.

关键词： closed space deep learning humity prediction indoor temperature prediction

来源：评论

学校读者我要写书评

暂无评论

Survey of Online Exam Proctoring Model to Detect Cheating Behavior based on Face Recognition 8

Survey of Online Exam Proctoring Model to Detect Cheating Be...

引用

8th International Conference on Systems and Informatics, ICSAI 2022

作者： Rabiha, Sucianna Ghadati Kartowisastro, Iman Herwidiana Setiawan, Reina Budiharto, Widodo Bina Nusantara University Binus Graduate Program - Computer Science. Computer Science Department Jakarta11480 Indonesia Bina Nusantara University Faculty of Engineering Computer Science Department Binus Graduate Program - Computer Science Computer Engineering Department Jakarta11480 Indonesia Bina Nusantara University School of Computer Science Computer Science Department Binus Graduate Program - Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9781665474481

Exams are an important component of any educational program, including online education. In any test, there is a possibility of cheating, so its detection and prevention is important. This study aims to conduct an in-depth study of the online exam monitoring model approach based on facial recognition used to detect cheating. Based on the inclusion and exclusion criteria designed, 13 selected studies were obtained. From these studies, we conducted further analysis regarding the Face Detection Method, Face Recognition Method, Initial Feature, Behavior Analysis and Evaluation Metrics used in each study so as to provide answers to research questions. the most frequently used Face detection method was Viola-Jones with a presentation of 20%, then CNN and MTCNN with a total presentation of 21%. The most widely used face recognition method in selected studies is CNN and metrics Accuracy is one of the most frequently used evaluations with a percentage of 33%. While the features that are usually used to detect cheating during online exams include facial motion and head pose which occupies the first position. The second is eye movement, then multiple faces gaze estimation and facial expression is in third place. Other features that also play a role in analyzing cheating behavior are mouth detection, facial vector, landmark location, gesture and posture. © 2022 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Prospector Heads: Generalized Feature Attribution for Large Models & data 41

Prospector Heads: Generalized Feature Attribution for Large ...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Machiraju, Gautam Derry, Alexander Desai, Arjun Guha, Neel Karimi, Amir-Hossein Zou, James Altman, Russ B. Ré, Christopher Mallick, Parag Department of Biomedical Data Science Stanford University United States Cartesia AI United States Department of Computer Science Stanford University United States Department of Electrical & Computer Engineering University of Waterloo Canada Department of Radiology Stanford University United States

Feature attribution, the ability to localize regions of the input data that are relevant for classification, is an important capability for ML models in scientific and biomedical domains. Current methods for feature attribution, which rely on "explaining" the predictions of end-to-end classifiers, suffer from imprecise feature localization and are inadequate for use with small sample sizes and high-dimensional datasets due to computational challenges. We introduce prospector heads, an efficient and interpretable alternative to explanation-based attribution methods that can be applied to any encoder and any data modality. Prospector heads generalize across modalities through experiments on sequences (text), images (pathology), and graphs (protein structures), outperforming baseline attribution methods by up to 26.3 points in mean localization AUPRC. We also demonstrate how prospector heads enable improved interpretation and discovery of class-specific patterns in input data. Through their high performance, flexibility, and generalizability, prospectors provide a framework for improving trust and transparency for ML models in complex domains. Copyright 2024 by the author(s)

关键词： data assimilation

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning-Based Semi-Supervised Generative Adversarial Network for Malaria Classification

引用

computers, Materials & Continua 2023年第3期74卷 6335-6349页

作者： Ibrar Amin Saima Hassan Samir Brahim Belhaouari Muhammad Hamza Azam Institute of Computing Kohat University of Science and TechnologyKohat26000K.P.KPakistan College of Science and Engineering Hamad bin Khalifa UniversityDohaQatar Centre of Research in Data Science Computer and Information Sciences DepartmentUniversiti Teknologi PETRONASSeri Iskandar32610PerakMalaysia

Malaria is a lethal disease responsible for thousands of deaths worldwide every *** methods of malaria diagnosis are timeconsuming that require a great deal of human expertise and *** automated diagnosis of diseases is progressively becoming *** deep learning models show high performance in the medical field,it demands a large volume of data for training which is hard to acquire for medical ***,labeling of medical images can be done with the help of medical experts *** recent studies have utilized deep learning models to develop efficient malaria diagnostic system,which showed promising ***,the most common problem with these models is that they need a large amount of data for *** paper presents a computer-aided malaria diagnosis system that combines a semi-supervised generative adversarial network and transfer *** proposed model is trained in a semi-supervised manner and requires less training data than conventional deep learning *** of the proposed model is evaluated on a publicly available dataset of blood smear images(with malariainfected and normal class)and achieved a classification accuracy of 96.6%.

关键词： Generative adversarial network transfer learning semi-supervised malaria VGG16

来源：评论

学校读者我要写书评

暂无评论

Classification Attack on IoT Devices with Machine Learning 9

Classification Attack on IoT Devices with Machine Learning

引用

9th IEEE International Conference on Computational Intelligence and Applications, ICCIA 2024

作者： Charoenwong, Nutcha Kosolsombat, Somkiat Ratanavilisagul, Chiabwoot College of Interdisciplinary Studies Thammasat University Data Science and Innovation Pathum Thani Thailand King Mongkut's University of Technology Faculty of Applied Science Department of Computer and Information Science North Bangkok Thailand

ISBN: (纸本)9798350352214

Internet of Things (IoT) devices are small, low-power devices used for detecting and processing data remotely through the internet. These devices have increasingly been integrated into our daily lives, both in the digital and physical world. However, this interconnectedness poses risks of being targeted by malware due to limited resources and connectivity. Machine learning (ML) techniques can be used to identify and prevent malware attacks on IoT devices. In this research report, we investigate the use of ML techniques for classifying malware in IoT devices. Our research includes the implementation and evaluation of decision tree, k-nearest neighbors (KNN), and XGBoost algorithms. Our evaluation metrics include accuracy, precision, recall, and the average of precision and recall. Our method is tested using a dataset of real-world malware attacks on IoT devices, and the XGBoost algorithm achieves the highest accuracy of 98.44%, demonstrating its effectiveness in detecting and classifying malware in IoT devices. © 2024 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Editorial Deep Learning-Empowered Big data Analytics in Biomedical Applications and Digital Healthcare

引用

IEEE/ACM Transactions on Computational Biology and Bioinformatics 2024年第4期21卷 516-520页

作者： Zhou, Xiaokang Leung, Carson K. Wang, Kevin I-Kai Fortino, Giancarlo Shiga University Faculty of Data Science Shiga Hikone522-0069 Japan University of Manitoba Department of Computer Science WinnipegR3T 2N2 Canada University of Auckland Department of Electrical Computer and Software Engineering Auckland1010 New Zealand University of Calabria DIMES Department Rende CS87036 Italy

Deep learning and big data analysis are among the most important research topics in the fields of biomedical applications and digital healthcare. With the fast development of artificial intelligence (AI) and Internets of Things (IoT) technologies, deep learning (DL) for big data analytics - including affective learning, reinforcement learning, and transfer learning - are widely applied to sense, learn, and interact with human health. Examples of biomedical applications include smart biomaterials, biomedical imaging, heartbeat/blood pressure measurement, and eye tracking. These biomedical applications collect healthcare data through remote sensors and transfer the data to a centralized system for analysis. With an enormous amount of historical data, DL and big data analysis technologies are able to identify potential linkage between features and possible risks, raise important decision for medical diagnosis, and provide precious advice for better healthcare treatment and lifestyle. Although significant progress has been made with AI, DL, and big data analytic technologies for medical and healthcare research, there remain gaps between the computer-aided treatment design and real-world healthcare demands. In addition, there are unexplored areas in the fields of healthcare and biomedical applications with cutting-edge AI and DL technologies. Hence, exploring the possibility of DL and big data analytics in the fields of biomedical applications and digital healthcare is in high demand. © 2004-2012 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Expand-and-Cluster: Parameter Recovery of Neural Networks 41

Expand-and-Cluster: Parameter Recovery of Neural Networks

引用

41st International Conference on Machine Learning, ICML 2024

作者： Martinelli, Flavio Şimşek, Berfin Gerstner, Wulfram Brea, Johanni Department of Life Sciences and Computer Sciences EPFL Lausanne Switzerland Center for Data Science NYU New York United States

Can we identify the weights of a neural network by probing its input-output mapping? At first glance, this problem seems to have many solutions because of permutation, overparameterisation and activation function symmetries. Yet, we show that the incoming weight vector of each neuron is identifiable up to sign or scaling, depending on the activation function. Our novel method 'Expand-and-Cluster' can identify layer sizes and weights of a target network for all commonly used activation functions. Expand- and-Cluster consists of two phases: (i) to relax the non-convex optimisation problem, we train multiple overparameterised student networks to best imitate the target function;(ii) to reverse engineer the target network's weights, we employ an ad-hoc clustering procedure that reveals the learnt weight vectors shared between students - these correspond to the target weight vectors. We demonstrate successful weights and size recovery of trained shallow and deep networks with less than 10% overhead in the layer size and describe an 'ease-of-identifiability' axis by analysing 150 synthetic problems of variable difficulty. Copyright 2024 by the author(s)

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Joint Communication and Synchronization Performance Optimization in Digital Twin Enabled Networks

Joint Communication and Synchronization Performance Optimiza...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Yu, Hanzhi Liu, Yuchen Chen, Mingzhe University of Miami Department of Electrical and Computer Engineering Frost Institute for Data Science and Computing Coral GablesFL33146 United States North Carolina State University Department of Computer Science RaleighNC27695 United States

ISBN: (纸本)9798350351255

In this paper, we investigate an accurate synchronization between a physical network and its digital network twin (DNT) that is a virtual representation of the physical network. The considered network includes a physical network where a base station (BS) serves a set of users, and a DNT that evolves with the status of both DNT and the physical network. The BS must use its limited spectrum resources to serve the users, as well as transmit the physical network information to the cloud server for DNT synchronization. Since the DNT can predict the physical network status, the BS may not need to transmit physical network information to the server at each time slot thus saving spectrum resources to serve users. However, if the BS does not transmit physical information to the DNT over a long period of time, the DNT may not be able to represent the physical network accurately. To this end, the BS must determine whether to send physical network information to the server to update DNT and the spectrum resources used for physical network information transmission and serving users. We formulate this resources allocation problem as an optimization problem aiming to maximize the sum of data rates of all users, while minimizing the gap between the states of the physical network and the DNT. The formulated problem is challenging to solve by conventional optimization methods, since the BS may not be able to know the future status of the DNT. To solve this problem, we design a gate recurrent unit (GRU) and soft action-critic (SAC) based algorithm. The GRU enables the DNT to predict its future states by using historical state data, and updating the DNT when the BS does not transmit physical network information. The SAC based algorithm enables the BS to learn the relationship between the physical network information transmission and the future status estimation accuracy of the DNT thus determining whether to transmit physical network information to the cloud server, ensuring an accurac

关键词： Resource allocation

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：