检索结果-内蒙古大学图书馆

3rd Conference on Lifelong Learning Agents, CoLLAs 2024

作者： Guo, Li Xia, Yuxuan Wang, Shengjie Department of Computer Science and Data Science New York University Shanghai China

Source-free domain adaptation (SFDA) has gained significant attention as a method to transfer knowledge from a pre-trained model on source domains toward target domains without accessing the source data. Recent research in SFDA has predominately adopted a self-training paradigm, focusing on utilizing local consistency constraints to refine pseudo-labels during self-training. These methods aim to encourage similar predictions among samples residing in local neighborhoods. However, despite their effectiveness, the significance of global consistency is often overlooked in such approaches. Moreover, such self-training based adaptation processes suffer from the "confirmation bias": models use self-generated sub-optimal pseudo-labels to guide their subsequent training, resulting in a loop of self-reinforcing errors. In this study, we address the aforementioned limitations through two key contributions. Firstly, we introduce a label propagation method that seamlessly enforces both local and global consistency, leading to more coherent label predictions within the target domain. Secondly, to mitigate the "confirmation bias", we aggregate the affinity matrix derived from current and historical models during the label propagation process. This approach takes advantage of different snapshots of the model to obtain a more accurate representation of the underlying graph structure, significantly enhancing the efficacy of label propagation and resulting in more refined pseudo-labels. Extensive experimental evaluations demonstrate the superiority of our approach over existing methods by a large margin. Our findings not only highlight the significance of incorporating global consistency within the SFDA framework but also offer a novel approach to mitigate the confirmation bias that arises from the use of noisy pseudo-labels in the self-training paradigm. © 2024 CoLLAs. All Rights Reserved.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

Automated Adversarial-Attack Removal with SafetyNet Using ADGIT 10

Automated Adversarial-Attack Removal with SafetyNet Using AD...

引用

10th International Conference on Smart Computing and Communication, ICSCC 2024

作者： Halim, Steven Anandi, Arvio Devin, Vyos Agung Santoso Gunawan, Alexander Eka Setiawan, Karli School of Computer Science Bina Nusantara University Data Science Program Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350363104

In the realm of artificial intelligence (AI), a notable challenge has surfaced: adversarial attacks, these attacks involve altering input data to mislead AI models. Developing defensive measures against adversarial attacks is necessary for a more reliable AI system to protect its users from potential harm. In response to the risk of adversarial attacks, this study aims to mitigate the risk of such attacks, especially in image classification tasks, by proposing Adversarial Detection Guided Input Transformation (ADGIT) as an architecture designed to handle such attacks. In this study, the author will experiment with creating such architecture and measure the quality of the proposed technique. ADGIT works by utilizing SafetyNet as an adversarial detector to detect and cleanse adversarial attacks. The author concludes that the proposed technique could improve robustness against adversarial attacks increasing consistent prediction accuracy from 43% to 60% and reconstructing adversarial input images to be more similar to their unperturbed version, with reconstructed images' PSNR score on 0.007 perturbation increased from 43.1182 to 89.0999. The technique proposed could be used as a new defensive measure and improving robustness against adversarial attacks. Although ADGIT is capable of handling adversarial samples, ADGIT has a drawback in performance speed due to the extra preprocessing step. © 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

Cosmetics Recommendation System Based on Ingredients Using Cosine Similarity 7

Cosmetics Recommendation System Based on Ingredients Using C...

引用

7th International Conference on data science and Its Applications, ICoDSA 2024

作者： Alisha Firdaus, Sekar Dwi Nurmuthia, Laksmi Imtiyaz, Raina Agung Santoso Gunawan, Alexander Eka Setiawan, Karli School of Computer Science Bina Nusantara University Data Science Program Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350365351

In the rapidly evolving beauty industry, consumers are often bombarded with an overwhelming array of skincare brands and products, making the quest for the perfect skincare regimen a daunting task. This saturation of the market not only confuses consumers but also poses the risk of resource wastage and potential skin damage due to incompatible ingredient combinations. To mitigate these challenges, our research presents an innovative recommendation system designed to streamline the product selection process. Utilizing the principle of cosine similarity, our methodology involves a detailed analysis of the ingredients contained in various skincare products. A quantitative foundation for evaluating ingredient lists of various skincare products is provided by cosine similarity, a mathematical metric that evaluates the similarity between two non-zero vectors by computing the cosine of the angle between them. Our algorithm generates customized product recommendations by thoroughly comprehending the intricate interactions among different constituents. This bespoke approach simplifies the decision-making process for consumers, enabling them to make well-informed choices that cater to their unique skin health needs. The effectiveness of our recommendation system is validated through comprehensive user feedback, demonstrating its potential to redefine the paradigm of personalized skincare recommendations within the beauty industry. Through providing customers with critical information and encouraging a culture of knowledgeable choice, we see a time when customized skincare products will not only increase customer satisfaction but also brand loyalty, which will be a big step toward the democratization of customized skincare. © 2024 IEEE.

关键词： Skin care products

来源：评论

学校读者我要写书评

暂无评论

A Novel Eccentric Intrusion Detection Model Based on Recurrent Neural Networks with Leveraging LSTM

引用

computers, Materials & Continua 2024年第3期78卷 3089-3127页

作者： Navaneetha Krishnan Muthunambu Senthil Prabakaran Balasubramanian Prabhu Kavin Kishore Senthil Siruvangur Kavitha Chinnadurai Jehad Ali Department of Computer Applications Karpagam College of EngineeringCoimbatore641032India Department of Computer Science and Engineering Karpagam College of EngineeringCoimbatore641032India Department of Data Science and Business Systems College of Engineering and TechnologySRM Institute of Science and TechnologyKattankulathur603203India Department of Computer Science and Engineering Sathyabama Institute of Science and TechnologyJeppiaar NagarRajiv Gandhi SalaiChennai600119India Department of AI Convergence Network Ajou UniversitySuwon16499Korea

The extensive utilization of the Internet in everyday life can be attributed to the substantial accessibility of online services and the growing significance of the data transmitted via the ***,this development has expanded the potential targets that hackers might *** adequate safeguards,data transmitted on the internet is significantly more susceptible to unauthorized access,theft,or *** identification of unauthorised access attempts is a critical component of cybersecurity as it aids in the detection and prevention of malicious *** research paper introduces a novel intrusion detection framework that utilizes Recurrent Neural Networks(RNN)integrated with Long Short-Term Memory(LSTM)*** proposed model can identify various types of cyberattacks,including conventional and distinctive *** networks,a specific kind of feedforward neural networks,possess an intrinsic memory *** Neural Networks(RNNs)incorporating Long Short-Term Memory(LSTM)mechanisms have demonstrated greater capabilities in retaining and utilizing data dependencies over extended *** such as data types,training duration,accuracy,number of false positives,and number of false negatives are among the parameters employed to assess the effectiveness of these models in identifying both common and unusual *** are utilised in conjunction with LSTM to support human analysts in identifying possible intrusion events,hence enhancing their decision-making capabilities.A potential solution to address the limitations of Shallow learning is the introduction of the Eccentric Intrusion Detection *** model utilises Recurrent Neural Networks,specifically exploiting LSTM *** proposed model achieves detection accuracy(99.5%),generalisation(99%),and false-positive rate(0.72%),the parameters findings reveal that it is superior to state-of-the-art techniques.

关键词： Cybersecurity intrusion detection machine learning leveraging long short-term memory(LLSTM) CICIDS2019 dataset innovative cyberattacks

来源：评论

学校读者我要写书评

暂无评论

A hybrid memory architecture supporting fine-grained data migration

引用

Frontiers of computer science 2024年第2期18卷 31-41页

作者： Ye CHI Jianhui YUE Xiaofei LIAO Haikun LIU Hai JIN National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabCluster and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China Department of Computer Science Michigan Technological UniversityMichigan 49931USA

Hybrid memory systems composed of dynamic random access memory(DRAM)and Non-volatile memory(NVM)often exploit page migration technologies to fully take the advantages of different memory *** previous proposals usually migrate data at a granularity of 4 KB pages,and thus waste memory bandwidth and DRAM *** this paper,we propose Mocha,a non-hierarchical architecture that organizes DRAM and NVM in a flat address space physically,but manages them in a cache/memory *** the commercial NVM device-Intel Optane DC Persistent Memory Modules(DCPMM)actually access the physical media at a granularity of 256 bytes(an Optane block),we manage the DRAM cache at the 256-byte size to adapt to this feature of *** design not only enables fine-grained data migration and management for the DRAM cache,but also avoids write amplification for Intel Optane *** also create an Indirect Address Cache(IAC)in Hybrid Memory Controller(HMC)and propose a reverse address mapping table in the DRAM to speed up address translation and cache ***,we exploit a utility-based caching mechanism to filter cold blocks in the NVM,and further improve the efficiency of the DRAM *** implement Mocha in an architectural *** results show that Mocha can improve application performance by 8.2%on average(up to 24.6%),reduce 6.9%energy consumption and 25.9%data migration traffic on average,compared with a typical hybrid memory architecture-HSCC.

关键词： non-volatile memory hybrid memory system data migration fine-grained caching

来源：评论

学校读者我要写书评

暂无评论

Blockchain with drug traceability in medical supply chain with Henry gas solubility optimisation algorithm

引用

International Journal of Wireless and Mobile Computing 2025年第2期28卷 135-148页

作者： Devi, P. Yamini Sriramya, P. Department of Computer Science and Engineering Saveetha School of Engineering Thandalam Tamil Nadu Chennai India Department of Data Science Saveetha School of Engineering SIMATS Tamil Nadu Chennai India

The drug traceability model is used for ensuring drug quality and its safety for customers in the medical supply chain. The healthcare supply chain is a complex network, which is susceptible to failures and leakage of information because of cyber security attacks. Hence, this research aims to design a blockchain to perform traceability of drugs using Henry Gas Solubility Optimisation (HGSO). The entities include distributors, wholesalers, retailers, blockchain and patients. This model comprises initialisation, registration, key generation, authentication, drug distribution with traceability and key generation phases. Any exchange of medicines needs the approval of both sender and receiver. The drugs are registered in the blockchain, which then generates a secret key that is obtained using HGSO. The verification and authentication of drugs are performed after the authentication process. The implemented model outperformed with the response time, memory, normalised variance, and privacy of 32.678 sec, 84 MB, 0.958 and 0.958. Copyright © 2025 Inderscience Enterprises Ltd.

关键词： authentication blockchain drug traceability key generation medical supply chain

来源：评论

学校读者我要写书评

暂无评论

Blockchain based Security Management of Internet of Medical Things (IoMT) using Homomorphic Encryption using Metaheuristics with a Deep Learning Model 2

Blockchain based Security Management of Internet of Medical ...

引用

2nd IEEE International Conference on Trends in Quantum Computing and Emerging Business Technologies, TQCEBT 2024

作者： Santiago, S. Prasanna, B.T. Qureshi, Kashif Subash, K. Trichy India Jss Science and Technology University Department of Computer Science and Engineering Mysuru India Department of Data Science Ai India Department of Data Science Trichy India

ISBN: (纸本)9798350384277

The introduction of the Internet of Medical Things (IoMT), has drastically transformed the worldwide landscape of healthcare delivery. The proliferation of IoMT devices in healthcare systems brings new issues in guaranteeing the security and privacy of sensitive patient data. We must secure a substantial amount of sensitive data from modification since IoMT is a high-volume, continually developing data domain. Since then, blockchain (BC) technology has been recognised as a distributed ledger that can manage a huge number of intelligent transactions and increase data security at the same time. A comprehensive resource management system may be offered by Blockchain-based security mechanisms with specific customisation and additional levels of authentication and verification. It has functioned brilliantly as a crucial component of the Bitcoin cryptocurrency. This work creates a blockchain-based Internet of Medical Things security management system using homomorphic encryption (HE). Key generation shows how the DOA may enhance cryptographic system security and efficacy. The IoMT-based HE-DOA system provided in this study employs blockchain to secure data exchange and diagnostic models. HE-DOA allows safe data transmission and diagnostic models with BC aid in IoMT. The recommended technique includes data collecting, encryption, and categorization. Blockchains (BCs) securely store data, and IoMT devices are crucial to early data collection. For data encryption, the dingo optimisation algorithm (DOA) may generate the key. Performance experiments and comparison with similar protocols show that the recommended procedure may enhance PSNR, accuracy, and computational time by 19.34%, 95.78%, and 1.887ms, respectively. Comparing HE-DOA to prior studies shows its scalability and durability. © 2024 IEEE.

关键词： Distributed ledger

来源：评论

学校读者我要写书评

暂无评论

A Linked List Encryption Scheme for Image Steganography without Embedding

引用

computer Modeling in Engineering & sciences 2024年第10期141卷 331-352页

作者： Pengbiao Zhao Qi Zhong Jingxue Chen Xiaopei Wang Zhen Qin Erqiang Zhou Network and Data Security Key Laboratory of Sichuan Province University of Electronic Science and Technology of ChinaChengdu610054China Faculty of Data Science City University of MacaoMacao999078China Department of Computer Science and Engineering University of CaliforniaRiversideCA 92521USA

Information steganography has received more and more attention from scholars nowadays,especially in the area of image steganography,which uses image content to transmit information and makes the existence of secret information *** enhance concealment and security,the Steganography without Embedding(SWE)method has proven effective in avoiding image distortion resulting from cover *** this paper,a novel encrypted communication scheme for image SWE is *** reconstructs the image into a multi-linked list structure consisting of numerous nodes,where each pixel is transformed into a single node with data and pointer *** employing a special addressing algorithm,the optimal linked list corresponding to the secret information can be *** receiver can restore the secretmessage fromthe received image using only the list header position *** scheme is based on the concept of coverless steganography,eliminating the need for any modifications to the cover *** boasts high concealment and security,along with a complete message restoration rate,making it resistant to ***,this paper proposes linked-list construction schemeswithin theproposedframework,which caneffectively resist a variety of attacks,includingnoise attacks and image compression,demonstrating a certain degree of *** validate the proposed framework,practical tests and comparisons are conducted using multiple *** results affirm the framework’s commendable performance in terms of message reduction rate,hidden writing capacity,and robustness against diverse attacks.

关键词： Steganography encryption steganography without embedding coverless steganography

来源：评论

学校读者我要写书评

暂无评论

Lung Cancer Detection: A Comparative Approach Using Regressor Methods 4

Lung Cancer Detection: A Comparative Approach Using Regresso...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Puri, Chetan Sharma, Mansi Reddy, K.T.V. Department of Computer Science and Design Wardha India Department of Artificial Intelligence and Data Science Wardha India

ISBN: (纸本)9798331523923

Lung cancer detection is the detection of tumors or cancerous cells in lung tissue. It is done using several medical imaging modalities, such as nuclear and genetic tests, magnetic resonance imaging (MRI), computed tomography (CT) scans, and X-rays. Detection of lung cancer at an early stage is very important as it increases the likelihood of successful treatment. For better diagnostic accuracy and patient outcomes, sophisticated detection methods now utilize regression models and machine learning algorithms. As one of the most common reasons for cancer fatalities globally, lung cancer highlights the urgent need for early and accurate diagnostic techniques. This research considers the use of regression-based strategies in lung cancer detection, suggesting their ability to improve diagnostic sensitivity and patient results. We created a strong predictive model that could effectively differentiate malignant nodules through sophisticated machine learning methods, such as support vector machines (SVM), decision trees, and linear regression. Regression analysis was used to assess how well benign and malignant lung lesions could be differentiated using a large clinical and medical imaging dastaset. Findings from research show that regression methods provide a sound method of enhancing early lung cancer detection, allowing for timely intervention and increased survival rates. The significance of machine learning in medical diagnosis is also illustrated through discussions on clinical implications and future research directions. The models that were tested, Random Forest had the best accuracy (94.6%), according to Stratified K-Fold cross-validation. The other models, including Gradient Boosting, Support Vector Classifier (SVC), and XGBoost, also showed high levels of accuracy, while the Multinomial Naïve Bayes model had the worst accuracy (75.7%). By reviewing clinical and imaging information and subjecting it to machine learning algorithms to identify patterns and associat

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Drug sales forecasting in the pharmaceutical market using deep neural network algorithms

International Journal of Systematic Innovation

引用

International Journal of Systematic Innovation 2024年第3期8卷 63-83页

作者： Qassrawi, Noura Azzeh, Mohammad Hijjawi, Mohammad Department of Computer Science Applied Science Private University Amman Jordan Department of Data Science Princess Sumaya University for Technology Amman Jordan

Drug sales and price forecasting have become an attractive investigation topic due to their important role in the pharmaceutical industry, A sales forecast helps every business to make better business decisions in overall business planning, budgeting, marketing, and risk management. The traditional forecasting method focuses on a conventional statistical model, which highly depends on the availability of historical sales data. However, for new drug entities, where not enough historical data is available, new methods of Machine Learning are applied. The aim of this paper is to identify an efficient Deep Neural Network algorithm suitable to forecast drug sales and pricing by applying Deep Neural Network Algorithms such as Multilayer Perceptron, Convolutional Neural Network, and Long Short-Term Memory, which are expected to perform well on this issue. The results are carried out to determine the efficiency of these algorithms by evaluating the performances of the models using MAE and RMSE performance metrics to identify the best algorithm for Drug Sales and Price Forecasting. The accepted accuracy should be more than 80\% of the actual value for quantity which is less than three thousand by unit and less than two dollars (USD) for price, Based on the results of the experiments Long Short Term Memory performed better than MLP and CNN for generating predictions with average Root Mean Square Error of for sales is 1.28(k) and Mean Absolute Error of about 0.85(k), and with average Root Mean Square Error for USD Prices is about 0.75, and Mean Absolute Error is about 0.44. The forecasts are then used to adjust stock levels according to the predictions. © (2024), (Society of Sytematic Innovation). All rights reserved.

关键词： Convolutional Neural Network Drug sales Forecasting Long Short-Term Memory Multilayer Perceptron

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：