检索结果-内蒙古大学图书馆

32nd ACM World Wide Web Conference, WWW 2023

作者： Wang, Ruijie Li, Zheng Yang, Jingfeng Cao, Tianyu Zhang, Chao Yin, Bing Abdelzaher, Tarek Department of Computer Science University of Illinois Champaign Urbana United States *** Inc United States School of Computational Science and Engineering Georgia Institute of Technology United States

ISBN: (纸本)9781450394161

This paper investigates cross-lingual temporal knowledge graph reasoning problem, which aims to facilitate reasoning on Temporal Knowledge Graphs (TKGs) in low-resource languages by transfering knowledge from TKGs in high-resource ones. The cross-lingual distillation ability across TKGs becomes increasingly crucial, in light of the unsatisfying performance of existing reasoning methods on those severely incomplete TKGs, especially in low-resource languages. However, it poses tremendous challenges in two aspects. First, the cross-lingual alignments, which serve as bridges for knowledge transfer, are usually too scarce to transfer sufficient knowledge between two TKGs. Second, temporal knowledge discrepancy of the aligned entities, especially when alignments are unreliable, can mislead the knowledge distillation process. We correspondingly propose a mutually-paced knowledge distillation model MP-KD, where a teacher network trained on a source TKG can guide the training of a student network on target TKGs with an alignment module. Concretely, to deal with the scarcity issue, MP-KD generates pseudo alignments between TKGs based on the temporal information extracted by our representation module. To maximize the efficacy of knowledge transfer and control the noise caused by the temporal knowledge discrepancy, we enhance MP-KD with a temporal cross-lingual attention mechanism to dynamically estimate the alignment strength. The two procedures are mutually paced along with model training. Extensive experiments on twelve cross-lingual TKG transfer tasks in the EventKG benchmark demonstrate the effectiveness of the proposed MP-KD method. © 2023 ACM.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Automated Early Diagnosis of Lung Tumor Based on Deep Learning Algorithms 1

Automated Early Diagnosis of Lung Tumor Based on Deep Learni...

引用

1st IEEE International Conference on Applied Intelligence and Sustainable Computing, ICAISC 2023

作者： Maheswari, M. Jothi, B. Devi, P. Gayathri Chitradevi, B. Pradeep, Kumar S SRM Institute of Science and Technology Department of Computational Intelligence Chennai India Panimalar Engineering College Department of ECE Chennai India Department of Computer Science Engineering Perambalur India Nitte Meenakshi Institute of Technology Department of Electronics and Communication Engineering Bengaluru India

ISBN: (纸本)9798350323795

The main goals of this study are to identify the early stages of lung cancer and investigate the degree of accuracy of various machine learning algorithms. A thorough review of the literature revealed that certain classifiers have low accuracy while others have higher accuracy but are challenging to approach nearer to 100%. Low accuracy and high implementation costs as a result of inappropriate DICOM image handling Many various types of images are utilised in medical image processing, however CT scans are typically chosen since they have less noise. Deep learning has been shown to be the most effective technique for processing medical images, identifying and classifying lung nodules, extracting features, and predicting the stage of lung cancer. This system's initial stage employed image processing methods to separate lung sections. Using K Means, the segmentation is carried out. Segmented images are used to extract the features, which are then classified using a variety of machine learning algorithms. The accuracy, sensitivity, and specificity of the proposed techniques, as well as their classification time, are used to assess their performance. © 2023 IEEE.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Efficient Net-based Expert System for Personalized Facial Skincare Recommendations 7

Efficient Net-based Expert System for Personalized Facial Sk...

引用

7th International Conference on Intelligent Computing and Control Systems, ICICCS 2023

作者： Akshya, J. Mehra, Vinit Sundarrajan, M. Sri, Pattapu Teja Choudhry, Mani Deepak SRM Institute of Science and Technology Department of Computational Intelligence Chennai India SRM Institute of Science and Technology Department of Computer Science and Engineering Chennai India KGiSL Institute of Technology Department of Information Technology Coimbatore India

ISBN: (纸本)9798350397253

In recent years, recommender systems have gained a lot of traction in both the commercial world and the academic research community. The term 'recommendation system for facial skin care' refers to an automated system that gives consumers advice on which facial skin care products to use based on their specific skin type, skin issues, and preferences. Product recommendation systems analyze user data using a variety of methods, including collaborative filtering, content-based filtering, and machine learning algorithms. Better skincare results may be achieved through the usage of a suggestion system in which consumers receive advice related to their own skin issues. The problem with current models is that they don't adequately address users' issues and concerns while being based on collaborative or content-based filtering. In order to create an effective face skincare model, the authors of this study suggest a hybrid approach that integrates several existing methods (including KNN, CNN, Transfer Learning of Efficient Net BO, and a content-based filtering recommendation engine). The user's skin tone, skin type, and acne severity are all inputs into the algorithm, which then outputs a recommendation for the most suitable product. The results of a comparison between the suggested model and other models prove its superiority. Using a hybrid model that takes into account a number of different methodologies and user inputs, the article aspires to deliver a more all-encompassing and individualized solution for facial skincare recommendations. The proposed model has the potential to enhance the precision and efficiency of current skincare recommendation systems. The implementation of EfficientNet B0 improves the model's accuracy, which now has a validation accuracy of 80% and a training accuracy of 87.10%. © 2023 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Advancing Cloud Security Frameworks Implementing Distributed Ledger Technology for Robust Data Protection and Decentralized Security Management in Cloud Computing Environments 2

Advancing Cloud Security Frameworks Implementing Distributed...

引用

2nd IEEE International Conference on Advances in Information Technology, ICAIT 2024

作者： Rajasekar, P. Kalaiselvi, K. Shanmugam, Raju Tamilselvan, S. Pandian, A. Pasumpon Department of ECE Sri Krishna College of Technology Kovaipudur Tamil Nadu Coimbatore India Department of Electronics and Communication Engineering Hindusthan College of Engineering and Technology Tamil Nadu Coimbatore India Unitedworld School of Computational Intelligence Karnavati University Gujarat India Department of Computer Science and Engineering Saveetha School of Engineering SIMATS Saveetha University Tamil Nadu Chennai India Department of Computer Science and Engineering CARE College of Engineering Tamilnadu Trichy India

ISBN: (纸本)9798350383867

Cloud computing caused the paradigm shift in business performance, from scalability to flexibility as well as affordability in the management of computing resources. Nevertheless, ensuring security of the data remains a key issue in the cloud due to the centralized interactions between service provider and a single vulnerability in the network can put rest of the data at risk. Consequently, the application of DLT, in addition to other solutions such as DLT, demonstrates a big step towards the improvement of cloud security frameworks. This article focuses on the implementation of DLT for data protection applications that are based on a solid dataset and decentralized security procedures in cloud environments. DLT utilization, like blockchain, provides an organization with integrity data, transparency, and fitness to counter cyber threats. Architecture stacks up sponsors such as cloud providers, users, and applications and DLT is responsible for the security of the transaction and the security policy enforcement. Customers use those services via desktop based application with transparent security policy arisen from DLT. Moreover, DLT also does identity management in the way that is decentralized, data sharing in the manner that it is secure, and the compliance to regulatory frameworks, which in addition reduces the trust and privacy risks in the cloud ecosystems. The proposed architecture is genuinely a big jump toward protecting cloud security from centralized control interruptions and thus, enhancing resilience and stability in cloud computing. © 2024 IEEE.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

Modified U-Net and CRF for Image Segmentation of Crop Images 1

引用

4th International Conference on Image Processing and Capsule Networks, ICIPCN 2023

作者： Chakraborty, Shantanu Sanap, Rushikesh Swami, Muddayya Attar, V.Z. Department of Computer Engineering and IT COEP Technological University Pune411005 India School of Computational Science COEP Technological University Pune411005 India

ISBN: (数字)9789819970933

ISBN: (纸本)9789819970926

Smart agriculture is the need of the hour, especially in a country like India whose economic and cultural backbone is agriculture. Detection of anomalies in crop images, like the presence of diseased spots and the presence of weeds is one of the most important strides in this direction. An important pre-requisite to this is the segmentation of crop images. A lot of related work has been done on the segmentation of crop images, using state-of-the-art neural network-based architecture and image processing-based techniques. This paper explores neural networks-based encoder–decoder architectures, particularly U-Net and introduces additions/modifications to it. On evaluating, the results of this modified U-Net are assessed qualitatively and quantitatively, it was found that the modified U-Net led to better results in terms of segmentation accuracy. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A Two Stream Fusion Assisted Deep Learning Framework for Stomach Diseases Classification

引用

computers, Materials & Continua 2022年第11期73卷 4423-4439页

作者： Muhammad Shahid Amin Jamal Hussain Shah Mussarat Yasmin Ghulam Jillani Ansari Muhamamd Attique Khan Usman Tariq Ye Jin Kim Byoungchol Chang Department of Computer Science COMSATS University IslamabadWah CampusPakistan Department of Information Sciences University of Education Lahore(Multan Campus)Pakistan Department of Computer Science HITEC University TaxilaPakistan College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz UniversityAl-KharjSaudi Arabia Department of Computer Science Hanyang UniversitySeoul04763Korea Center for Computational Social Science Hanyang UniversitySeoul04763Korea

Due to rapid development in Artificial Intelligence(AI)and Deep Learning(DL),it is difficult to maintain the security and robustness of these techniques and algorithms due to emergence of novel term adversary *** technique is sensitive to these ***,fake samples cause AI and DL model to produce diverse *** attacks that successfully implemented in real world scenarios highlight their applicability even *** this regard,minor modifications of input images cause“Adversarial Attacks”that altered the performance of competing attacks ***,such attacks and defensive strategies are gaining lot of attention by the machine learning and security *** use different kinds of technologies to examine the patient abnormalities including Wireless Capsule Endoscopy(WCE).However,using WCE it is very difficult for doctors to detect an abnormality within images since it takes enough time while inspection and deciding *** a result,it took weeks to generate patients test report,which is tiring and strenuous for ***,researchers come out with the solution to adopt computerized technologies,which are more suitable for the classification and detection of such *** far as the classification is concern,the adversarial attacks generate problems in classified *** days,to handle this issue machine learning is mainstream defensive approach against adversarial ***,this research exposes the attacks by altering the datasets with noise including salt and pepper and Fast Gradient Sign Method(FGSM)and then reflects that how machine learning algorithms work fine to handle these noises in order to avoid *** obtained on the WCE images which are vulnerable to adversarial attack are 96.30%accurate and prove that the proposed defensive model is robust when compared to competitive existing methods.

关键词： WCE images adversarial attacks FGSM noise salt and pepper noise feature fusion deep learning

来源：评论

学校读者我要写书评

暂无评论

Feature Analysis and Classification of Collusive Android App-Pairs Using DBSCAN Clustering Algorithm 1st

Feature Analysis and Classification of Collusive Android A...

引用

1st EAI International Conference on Safe, Secure, Ethical, Responsible Technologies and Emerging Applications, SAFER-TEA 2023

作者： Mawoh, Roger Yiran Tchakounte, Franklin Ali, Joan Beri Fachkha, Claude Department of Computer Science Faculty of Science University of Buea Buea Cameroon Department of Mathematics and Computer Science Faculty of Science University of Ngaoundéré Ngaoundéré Cameroon Cybersecurity with Computational and Artificial Intelligence Research Group Faculty of Science University of Ngaoundéré Ngaoundéré Cameroon College of Engineering and IT University of Dubai Dubai United Arab Emirates

ISBN: (纸本)9783031563959

In this study, we tackle the issue of application collusion, which involves multiple apps working together to achieve malicious goals that they couldn’t achieve individually. The current security model of Android, which focuses on permissions, doesn’t effectively address this threat because it only mitigates risks associated with individual apps. To address this limitation, we carried out an extensive analysis of features to identify the key Android permissions utilized by colluding app-pairs. We propose an approach to classify collusive app-pairs using the DBSCAN clustering algorithm. Our results provide valuable insights into the relationship between specific Android permission sets and the malicious activities performed by colluding app-pairs. We identified 12 permissions as the most important features contributing to the classification of collusive app-pairs. We also identified 4 distinct clusters of colluding Android app-pairs. © ICST Institute for computer sciences, Social Informatics and Telecommunications engineering 2024.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Neural Cryptography with Fog Computing Network for Health Monitoring Using IoMT

引用

computer Systems science & engineering 2023年第1期44卷 945-959页

作者： G.Ravikumar K.Venkatachalam Mohammed A.AlZain Mehedi Masud Mohamed Abouhawwash Department of Computer Science and Engineering Coimbatore Institute of Engineering and TechnologyCoimbatore641109India Department of Applied Cybernetics Faculty of ScienceUniversity of Hradec Králové50003Hradec KrálovéCzech Republic Department of Information Technology College of Computers and Information TechnologyTaif UniversityP.O.Box 11099Taif21944Saudi Arabia Department of Computer Science College of Computers and Information TechnologyTaif UniversityP.O.Box 11099Taif21944Saudi Arabia Department of Mathematics Faculty of ScienceMansoura UniversityMansoura35516Egypt Department of Computational Mathematics Scienceand Engineering(CMSE)Michigan State UniversityEast LansingMI48824USA

Sleep apnea syndrome(SAS)is a breathing disorder while a person is *** traditional method for examining SAS is Polysomnography(PSG).The standard procedure of PSG requires complete overnight observation in a *** typically provides accurate results,but it is expensive and time ***,for people with Sleep apnea(SA),available beds and laboratories are ***,it may produce inaccurate ***,this paper proposes the Internet of Medical Things(IoMT)framework with a machine learning concept of fully connected neural network(FCNN)with k-near-est neighbor(k-NN)*** paper describes smart monitoring of a patient’s sleeping habit and diagnosis of SA using FCNN-KNN+average square error(ASE).For diagnosing SA,the Oxygen saturation(SpO2)sensor device is popularly used for monitoring the heart rate and blood oxygen *** diagnosis information is securely stored in the IoMT fog computing *** can care-fully monitor the SA patient remotely on the basis of sensor values,which are efficiently stored in the fog computing *** proposed technique takes less than 0.2 s with an accuracy of 95%,which is higher than existing models.

关键词： Sleep apnea polysomnography IOMT fog node security neural network KNN signature encryption sensor

来源：评论

学校读者我要写书评

暂无评论

An Effective Hand Gesture Recognition using Convolutional Neural Network with Long Short-Term Memory

An Effective Hand Gesture Recognition using Convolutional Ne...

引用

2023 International Conference on Evolutionary Algorithms and Soft Computing Techniques, EASCT 2023

作者： Sunil, G. Saranya, A. Duraimurugan, N. Dineshkumar, R. Ramachandra, A.C. Sr University School of Computer Science & Artificial Intelligence Warangal India Srm Institute of Science and Technology Department of Computational Intelligence Chennai India Rajalakshmi Engineering College Department of Computer Science and Engineering Chennai India Saveetha School of Engineering Department of Ece Thandalam India Engineering Nitte Meenakshi Institute of Technology Department of Electronics and Communication Bengaluru India

ISBN: (纸本)9798350313413

A Hand Gesture (HG) constitutes a mode of nonverbal communication or non-vocal interaction, where discernible bodily movements convey specific messages, either independently or in combination with spoken language. Gesture recognition techniques are employed to create systems capable of transmitting information among individuals with disabilities for operating devices. In this paper, we propose the use of Electromyography (EMG) signals for classifying hand gestures through Employing both a Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) in combination is being used. The main problem lies in the noise signals produced by the EMG sensor. In this work, we employ a Low Pass Filter for preprocessing the signal images, followed by feature extraction using the CNN model. To reduce the high-dimensional signal and normalize the features for the classification process, we utilize LSTM. This experiment was conducted using the Ninapro DB1 dataset. This model successfully addresses the previous issues and attains an overall accuracy of 95.56%, Precision 91.90%, Recall 89.50%, and F1 score 85.50% 91.90%, then the accurate classification compares to other existing models like Bidirectional Convolutional Gated Recurrent Unit, and Deformable convolutional network models. © 2023 IEEE.

关键词： Convolutional Neural Network Electromyography Hand Gesture Long Short-Term Memory Low Pass Filter

来源：评论

学校读者我要写书评

暂无评论

GPU-Based Efficient Parallel Heuristic Algorithm for High-Utility Itemset Mining in Large Transaction Datasets (Extended Abstract) 40

GPU-Based Efficient Parallel Heuristic Algorithm for High-Ut...

引用

40th IEEE International Conference on Data engineering, ICDE 2024

作者： Fang, Wei Jiang, Haipeng Lu, Hengyang Sun, Jun Wu, Xiaojun Lin, Jerry Chun-Wei Jiangnan University Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Department of Computer Science and Technology Wuxi214122 China Silesian University of Technology Department of Distributed Systems and IT Devices Poland

ISBN: (纸本)9798350317152

Heuristic algorithms have been developed to find approximate solutions for high-utility itemset mining (HUIM) problems that compensate for the performance bottlenecks of exact algorithms. However, heuristic algorithms still face the problem of long runtime and insufficient mining quality, especially for large transaction datasets with thousands to tens of thousands of items and up to millions of transactions. To solve these problems, a novel GPU-based efficient parallel heuristic algorithm for HUIM (PHA-HUIM) is proposed in this paper. The iterative process of PHA-HUIM consists of three main steps: the search strategy, fitness evaluation, and ring topology communication. The search strategy and ring topology communication are designed to run in constant time on GPU. The parallelism of fitness evolution helps to substantially accelerate the algorithm. To improve the mining quality, a multi-start strategy with an unbalanced allocation strategy is employed in the search process. Ring topology communication is adopted to maintain population diversity. A load balancing strategy is introduced to reduce the thread divergence to improve the parallel efficiency. The experimental results on nine large datasets show that PHA-HUIM outperforms state-of-the-art HUIM algorithms in terms of speedup performance, runtime, and mining quality. © 2024 IEEE.

关键词： Graphics processing unit

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：