检索结果-内蒙古大学图书馆

Optimizing Healthcare Delivery through CloudBased Clinical Decision Support Systems

学校读者我要写书评

暂无评论

Optimizing Healthcare Delivery through CloudBased Clinical D...

Emerging Trends in Industry 4.0 (ETI 4.0)

作者： U. Samson Ebenezar Jenila G. Vennila T. Suresh Balakrishnan Prabhakar Krishnan Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India Department of Computer Science and Engineering CARE College of Engineering Trichy Tamil Nadu Department of AI & ML School of Computing Mohan Babu University Tirupati Andhra Pradesh Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai India Center for Cyber security Systems and Networks Amrita Vishwa Vidyapeetham Amritapuri-campus India

ISBN: (数字)9798350373783

ISBN: (纸本)9798350373790

The experiment aims at evaluating how four machine learning algorithms work: Decision Tree, Random Forest, SVM, and Neural Network, in a task, of binary classification. Models were evaluated using comprehensive metrics such as accuracy, precision, recall, F-score and AUC that revealed a good diagnostic performance. Models selected for the experiment and parameters tested on real datasets show steady changes in performance. The Neural Network model remained on top, achieving accuracy, precision, recall, F-score and AUC-ROC of 91.8%, 92.1%, 91.3%, 91.7% and 0.93 respectively. Random Forest displayed a competitive accordance along with the accuracy of 88.6%, precision of 89.2%, recall of 88.7%, and the F-score of 89.0%, and the AUC of 0.91. From the results, Support Vector Machine and Decision Tree models posted lower accuracy, recall, and fscores compared to the Neural Network and Random Forest models in most cases. These reveal the need for the improvement of the suitable machine learning model that comes from specific task needs as well as the consideration of each one of factors including accuracy, interpretability, and computational efficiency. Extensive and development of the model may result in more comprehensive understanding of how the model leads classifying of real-world applications such as medical diagnoses, fraud detection and target marketing.

关键词： Support vector machines Measurement Accuracy Machine learning algorithms Computational modeling Neural networks Medical services

Downstream-agnostic Adversarial Examples

学校读者我要写书评

暂无评论

Downstream-agnostic Adversarial Examples

International Conference on computer Vision (ICCV)

作者： Ziqi Zhou Shengshan Hu Ruizhi Zhao Qian Wang Leo Yu Zhang Junhui Hou Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Wuhan University School of Information and Communication Technology Griffith University Department of Computer Science City University of Hong Kong School of Computer Science and Technology Huazhong University of Science and Technology Cluster and Grid Computing Lab

Self-supervised learning usually uses a large amount of unlabeled data to pre-train an encoder which can be used as a general-purpose feature extractor, such that downstream users only need to perform fine-tuning operations to enjoy the benefit of "large model". Despite this promising prospect, the security of pre-trained encoder has not been thoroughly investigated yet, especially when the pre-trained encoder is publicly available for commercial *** this paper, we propose AdvEncoder, the first framework for generating downstream-agnostic universal adversarial examples based on the pre-trained encoder. AdvEncoder aims to construct a universal adversarial perturbation or patch for a set of natural images that can fool all the downstream tasks inheriting the victim pre-trained encoder. Unlike traditional adversarial example works, the pre-trained encoder only outputs feature vectors rather than classification labels. Therefore, we first exploit the high frequency component information of the image to guide the generation of adversarial examples. Then we design a generative attack framework to construct adversarial perturbations/patches by learning the distribution of the attack surrogate dataset to improve their attack success rates and transferability. Our results show that an attacker can successfully attack downstream tasks without knowing either the pre-training dataset or the downstream dataset. We also tailor four defenses for pre-trained encoders, the results of which further prove the attack ability of AdvEncoder. Our codes are available at: https://***/CGCL-codes/AdvEncoder.

关键词：

A Facial Recognition and Detection System using openVC

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2022年

作者： Goel, Yaman Gupta, Ishu Rani, Pooja Singh, Ashutosh Kumar Department of Computer Applications National Institute of Technology Kurukshetra136119 India Cloud Computing Research Center Department of Computer Science and Engineering National Sun Yat-sen University Kaohsiung Taiwan

Detection of the human face and matching it against user data, saved in our databases, with the intent of authenticating a person’s identity through the computer is an engaging and challenging task. With the development in the field of robotics and computer vision technologies, real-time human face recognition has also emerged as a key ongoing area. So, we proposed a novel scheme to process the real-time images according to requirements, captured in a computer web camera. By making use of open source computer vision library (OpenCV) and applying its in-built functions, we can easily detect human faces and then match them against the training sets (face images stored in the database) to recognize a human’s identity. Image handling and processing are done using basic library methods. These library functions are able to capture images from a webcam, create windows to hold the images at run time, save them in the database and process them to check exact likeness. CascadeClassifier is used for face detection, and HaarCascade is used for this purpose. FaceRecognizer class is used for face recognition. EigenFaces, FisherFaces and Local Binary Patterns are the basic methods that can be used for this. Images are stored in form of a CSV database. © 2022, CC BY.

关键词： Face recognition

A HOLISTIC VIEW ON DATA PROTECTION FOR SHARING, COMMUNICATING, AND computing ENVIRONMENTS: TAXONOMY AND FUTURE DIRECTIONS

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Gupta, Ishu Singh, Ashutosh Kumar Cloud Computing Research Center Department of Computer Science and Engineering National Sun Yat-sen University Kaohsiung Taiwan Department of Computer Applications National Institute of Technology Kurukshetra136119 India

The data is an important asset of an organization and it is essential to keep this asset secure. It requires security in whatever state is it i.e. data at rest, data in use, and data in transit. There is a need to pay more attention to it when the third party is included i.e. when the data is stored in the cloud then it requires more security. Since confidential data can reside on a variety of computing devices (physical servers, virtual servers, databases, file servers, PCs, point-of-sale devices, flash drives, and mobile devices) and move through a variety of network access points (wireline, wireless, VPNs, etc.), there is a need of solutions or mechanism that can tackle the problem of data loss, data recovery and data leaks. In this context, the paper presents a holistic view of data protection for sharing and communicating environments for any type of organization. A taxonomy of data leakage protection systems and major challenges faced while protecting confidential data are discussed. Data protection solutions, Data Leakage Protection System’s analysis techniques, and, a thorough analysis of existing state-of-the-art contributions empowering machine learning-based approaches are entailed. Finally, the paper explores and concludes various critical emerging challenges and future research directions concerning data protection. © 2022, CC BY.

关键词： Digital storage

TIDF-DLPM: TERM AND INVERSE DOCUMENT FREQUENCY BASED DATA LEAKAGE PREVENTION MODEL A PREPRINT

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Gupta, Ishu Mittal, Sloni Tiwari, Ankit Agarwal, Priya Singh, Ashutosh Kumar Cloud Computing Research Center Department of Computer Science Engineering National Sun Yat-sen University Kaohsiung Taiwan Department of Computer Applications National Institute of Technology Kurukshetra136119 India

Confidentiality of the data is being endangered as it has been categorized into false categories which might get leaked to an unauthorized party. For this reason, various organizations are mainly implementing data leakage prevention systems (DLPs). Firewalls and intrusion detection systems are being outdated versions of security mechanisms. The data which are being used, in sending state or are rest are being monitored by DLPs. The confidential data is prevented with the help of neighboring contexts and contents of DLPs. In this paper, a semantic-based approach is used to classify data based on the statistical data leakage prevention model. To detect involved private data, statistical analysis is being used to contribute secure mechanisms in the environment of data leakage. The favored Frequency-Inverse Document Frequency (TF-IDF) is the facts and details recapture function to arrange documents under particular topics. The results showcase that a similar statistical DLP approach could appropriately classify documents in case of extent alteration as well as interchanged documents. © 2022, CC BY.

关键词： Semantics

PCA-RF: AN EFFICIENT PARKINSON'S DISEASE PREDICTION MODEL BASED ON RANDOM FOREST CLASSIFICATION

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Gupta, Ishu Kaur, Sizman Sharma, Vartika Singh, Ashutosh Kumar Cloud Computing Research Center Department of Computer Science and Engineering National Sun Yat-Sen University Kaohsiung Taiwan Department of Computer Applications National Institute of Technology Kurukshetra136119 India

In this modern era of overpopulation disease prediction is a crucial step in diagnosing various diseases at an early stage. With the advancement of various machine learning algorithms, the prediction has become quite easy. However, the complex and the selection of an optimal machine learning technique for the given dataset greatly affects the accuracy of the model. A large amount of datasets exists globally but there is no effective use of it due to its unstructured format. Hence, a lot of different techniques are available to extract something useful for the real world to implement. Therefore, accuracy becomes a major metric in evaluating the model. In this paper, a disease prediction approach is proposed that implements a random forest classifier on Parkinson's disease. We compared the accuracy of this model with the Principal Component Analysis (PCA) applied Artificial Neural Network (ANN) model and captured a visible difference. The model secured a significant accuracy of up to 90%. © 2022, CC BY.

关键词： Neural networks

HISA-SMFM: HISTORICAL AND SENTIMENT ANALYSIS BASED STOCK MARKET FORECASTING MODEL

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Gupta, Ishu Madan, Tarun Kumar Singh, Sukhman Singh, Ashutosh Kumar Cloud Computing Research Center Department of Computer Science and Engineering National Sun Yat-Sen University Kaohsiung Taiwan Department of Computer Applications National Institute of Technology Kurukshetra136119 India

One of the pillars to build a country's economy is the stock market. Over the years, people are investing in stock markets to earn as much profit as possible from the amount of money that they possess. Hence, it is vital to have a prediction model which can accurately predict future stock prices. With the help of machine learning, it is not an impossible task as the various machine learning techniques if modeled properly may be able to provide the best prediction values. This would enable the investors to decide whether to buy, sell or hold the share. The aim of this paper is to predict the future of the financial stocks of a company with improved accuracy. In this paper, we have proposed the use of historical as well as sentiment data to efficiently predict stock prices by applying LSTM. It has been found by analyzing the existing research in the area of sentiment analysis that there is a strong correlation between the movement of stock prices and the publication of news articles. Therefore, in this paper, we have integrated these factors to predict the stock prices more accurately. © 2022, CC BY.

关键词： Sentiment analysis

Optimizing Multi-Hop Quantum Communication using Bidirectional Quantum Teleportation Protocol

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Ikken, N. Kumar, P. Slaoui, A. Kar, B. Laamara, R. Ahl Almousa, M. El-Latif, A.A. Abd LPHE-Modeling and Simulation Faculty of Sciences Mohammed V University Rabat Morocco Department of Computer Science and Information Engineering National Taiwan University of Science and Technology Taipei Taiwan Centre of Physics and Mathematics CPM Faculty of Sciences Mohammed V University in Rabat Rabat Morocco EIAS Data Science Lab College of Computer and Information Sciences Center of Excellence in Quantum and Intelligent Computing Prince Sultan University Riyadh11586 Saudi Arabia Department of Information Technology College of Computer and Information Sciences Princess Nourah bint Abdulrahman University Riyadh11671 Saudi Arabia Department of Mathematics and Computer Science Faculty of Science Menoufia University Shebin El-Koom32511 Egypt

In this paper, we introduce a new method for Bidirectional Quantum Teleportation called Bidirectional Quantum Teleportation using the Modified Dijkstra Algorithm and Quantum Walk (BQT-MDQW). This method uses different types of entangled states, such as the GHZ-Bell state, W-Bell state, and Cluster-Bell state, to improve quantum communication in multi-hop quantum wireless networks. We focus on the W-Bell state and compare the quantum Dijkstra algorithm with the classical Dijkstra method to see which one works better. We apply both versions to quantum and classical simulators, measuring their performance through fidelity, memory utilization, and throughput calculations. Our results show that the shortest path problem may be solved with significantly reduced computer complexity using the quantum Dijkstra algorithm based on quantum walks. The introduction of a quantum walk, which permits dynamic transitions between quantum channels and the effective exploration of quantum network states, is an important part of the protocol. Using the capacity of the quantum walk to adjust to changing quantum states, we also introduce a method for successfully identifying unitary matrices under varying quantum channels. The bidirectional teleportation structure of the protocol is designed to solve the multi-hop teleportation problem in quantum wireless networks. In addition, we present quantum Dijkstra’s algorithm, which uses quantum gates to significantly decrease computational complexity and solve the networking problem by building on the quantum walk framework. This method shows how quantum computing may be used to solve arbitrary optimization issues such as the shortest path problem. Finally, we present a novel multi-hop quantum teleportation system encompassing both unidirectional and bidirectional communication, as introduced in the quantum Dijkstra algorithm system. This system significantly enhances communication in quantum networks by enabling efficient and reliable information

关键词： Quantum channel

Physics-inspired Machine Learning for Quantum Error Mitigation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Xu, Xiao-Yue Xue, Xin Chen, Tianyu Ding, Chen Li, Tian Zhou, Haoyi Huang, He-Liang Bao, Wan-Su Henan Key Laboratory of Quantum Information and Cryptography Zhengzhou Henan450000 China Department of Computer Science Beihang University Beijing100191 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing100191 China Department of Software Beihang University Beijing100191 China

Noise is a major obstacle in current quantum computing, and Machine Learning for Quantum Error Mitigation (ML-QEM) promises to address this challenge, enhancing computational accuracy while reducing the sampling overheads of standard QEM methods. Yet, existing models lack physical interpretability and rely heavily on extensive datasets, hindering their scalability in large-scale quantum circuits. To tackle these issues, we introduce the Neural Noise Accumulation Surrogate (NNAS), a physics-inspired neural network for ML-QEM that incorporates the structural characteristics of quantum noise accumulation within multi-layer circuits, endowing the model with physical interpretability. Experimental results demonstrate that NNAS outperforms current methods across a spectrum of metrics, including error mitigation capability, quantum resource consumption, and training dataset size. Notably, for deeper circuits where QEM methods typically struggle, NNAS achieves a remarkable reduction of over half in errors. NNAS also demands substantially fewer training data, reducing dataset reliance by at least an order of magnitude, due to its ability to rapidly capture noise accumulation patterns across circuit layers. This work pioneers the integration of quantum process-derived structural characteristics into neural network architectures, broadly enhancing QEM's performance and applicability, and establishes an integrative paradigm that extends to various quantum-inspired neural network architectures. © 2025, CC BY.

关键词： Quantum computers