检索结果-内蒙古大学图书馆

International Conference on Control Communication & computing India (ICCC)

作者： Varsha Varghese Mahalakshmi S Senthilkumar Kb Cyber Forensics and Information Security Department of Computer Science & Engineering ER&DCI Institute of Technology Thiruvananthapuram Cyber Security Group Centre for Development of Advanced Computing Thiruvananthapuram Scientict_E Cyber Security Group Centre for Development of Advanced Computing Thiruvananthapuram

Darknet has emerged as an excellent platform for cybercriminals to conduct various illicit activities such as operating a fully functional crypto-currency-based marketplace or maintaining a highly anonymous communication channel. However, it also acts as a source of Cyber Threat Intelligence which is the information about the techniques, tactics, or motives of an emerging threat. The life cycle of a Darknet-based Cyber Threat Intelligence solution mainly consists of the Collection, Processing, Analysis, and Production of Data from the Darknet. The Collection and Processing stages deal with accumulating information from various dark web pages and transforming the data into some format using a big data system. The Analysis part is integral to the Threat Intelligence schema since it constitutes the extraction of named entities like Organization, Offensive Activity, Tools, etc., and the determination of relationships between these entities. The production stage is like data mining where some knowledge is extracted that can be relevant to an organization under consideration. Such knowledge can mitigate risks and disrupt any targeted cyber-attack campaigns, making Cyber Threat Intelligence actionable. In this research, an open-source-intelligence toolset is used to scan and collect data from the dark web forums through crawling and scrapping. The collected data is then ingested into a state-of-the-art NLP model that extracts actionable threat intelligence using Named Entity Recognition. The experimental results indicate that the model could identify HackerIds, tools, software, organizations, and other entities in the discussions of dark web forums with better efficiency and accuracy. This could be used to identify the source of a data leak, the release of new malware, evidence of a new exploit, and other offensive activities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Study of Cryptographic Primitives in the context of Blockchain's Data Integrity and Privacy 11

A Study of Cryptographic Primitives in the context of Blockc...

引用

11th International Conference on System Modeling and Advancement in Research Trends, SMART 2022

作者： Singh, Ramveer Pooja Agarwal, Ambuj Kumar Naaz, Rohaila Kumar, Raj Vijay, Richa Greater Noida Institute of Professional Studies Greater Noida India School of Engineering and Technology Ct University Ludhiana India School of Engineering and Technology Sharda University Department of Computer Science and Engineering Greater Noida India Teerthanker Mahaveer University Faculty of Engineering and Computing Sciences Moradabad India Department of Computer Applications Faridabad India

ISBN: (纸本)9781665487320

In Today's World, Blockchain is a promising Technology in all areas;things have also been drastically changed after COVID-19;challenges surfaced for implementing blockchain technology in the context of its computational complexity and security. After invention of it in 2008, cryptocurrency applications, i.e., Bitcoin it also getting introduced in Different applications. One of the Major Building blocks of Blockchain is Cryptography techniques. This paper discusses Cryptographic primitives used in different phases of Blockchain implementation and the challenges of implementing these cryptographic primitives. Bitcoin uses Cryptographic primitives to generate public-private key pairs and mining, while Ethereum uses Elliptic curve cryptography to create public-private keys and digital signatures. This paper divided uses of cryptographic primitives into three categories used in Blockchains, i.e., key generation Hashes, signature generation hashes, and proof hashes. © 2022 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

TACNET: TEMPORAL AUDIO SOURCE COUNTING NETWORK

arXiv

引用

arXiv 2023年

作者： Ahmadnejad, Amirreza Darviishani, Ahmad Mahmmodian Asadi, Mohmmad Mehrdad Saffariyeh, Sajjad Yousefi, Pedram Fatemizadeh, Emad Department of Electrical Engineering Sharif University of Technology Tehran11155-4365 Iran Department of Computer Science Institute for Advanced Studies in Basic Sciences Zanjan45137-66731 Iran

In this paper, we introduce the Temporal Audio Source Counting Network (TaCNet), an innovative architecture that addresses limitations in audio source counting tasks. TaCNet operates directly on raw audio inputs, eliminating complex preprocessing steps and simplifying the workflow. Notably, it excels in real-time speaker counting, even with truncated input windows. Our extensive evaluation, conducted using the LibriCount dataset, underscores TaCNet's exceptional performance, positioning it as a state-of-the-art solution for audio source counting tasks. With an average accuracy of 74.18 % over 11 classes, TaCNet demonstrates its effectiveness across diverse scenarios, including applications involving Chinese and Persian languages. This cross-lingual adaptability highlights its versatility and potential impact. © 2023, CC0.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Developing Real-World Applications with Algorithmic Intelligence in Reinforcement Learning for Robotics

Developing Real-World Applications with Algorithmic Intellig...

引用

Trends in Quantum computing and Emerging Business Technologies (TQCEBT), International Conference on

作者： M. Bhanumathi M. Sangeetha F. Mary Harin Fernandez A. Ganesh Ramachandran S.K. Saravanan Department of Computer Science and Engineering Vels Institute of Science Technology and Advanced Studies (VISTAS) Chennai India Department of Computer Engineering University of Technology and Applied Sciences Nizwa Sultanate of Oman Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai India Department of Computer Science Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai India Department of Computers Science and Engineering BigData and Network Security Saveetha School of Engineering SIMATS Chennai Tamil Nadu

ISBN: (数字)9798350384277

ISBN: (纸本)9798350384284

In the study, three leading reinforcement learning algorithms Deep Q-Network (DQN), Proximal Policy Optimization (PPO) and Asynchronous Advantage Actor – Critic (A3Cc are applied in a number of real-world robotics tasks. The focus of our analysis is on performance indicators, computational efficiencies across multiple environments as well with respect to customer satisfaction rating. The DQN demonstrated good performance, with the success rate of up to 85% in object manipulation tasks and confirmed its reliability under controlled lab conditions where it made only a 5 percent error. PPO excelled in autonomous navigation (82%) and was the most energy-efficient option, requiring just 10 hours for training and using only twelve KWH of power. Compared with A3C, the method performed to a higher level of adaptability and robustness, especially in object manipulation (90% success rate) and dynamic environments (10% error rates applicable for outdoor variable weather conditions). But A3C was also the most automatable, which required 15 hours to train and consumed an astonishing amount of electricity – 18 kWh. Regarding customer satisfaction, PPO performs the best in end-user rating on user interface; A3C shows a preference with engineers due to its advanced features and flexibility. The focus of this study is significant trade-offs between performance, efficiency and user preference in real robotics applications that advocate for individual tailoring selections as well as deployments based on task specifics nature.

关键词： Training Error analysis Heuristic algorithms Customer satisfaction Reinforcement learning Robustness Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Detecting Information on the Spread of Dengue on Twitter Using Articial Neural Networks

引用

computers, Materials & Continua 2021年第4期67卷 1317-1332页

作者： Samina Amin M.Irfan Uddin M.Ali Zeb Ala Abdulsalam Alarood Marwan Mahmoud Monagi H.Alkinani Institute of Computing Kohat University of Science and TechnologyKohat26000Pakistan College of Computer Science and Engineering University of JeddahJeddah21959Saudi Arabia Faculty of Applied Studies King Abdulaziz UniversityJeddahSaudi Arabia Department of Computer Science and Articial Intelligence College of Computer Sciences and EngineeringUniversity of JeddahJeddahSaudi Arabi

Social media platforms have lately emerged as a promising tool for predicting the outbreak of epidemics by analyzing information on them with the help of machine learning *** analytical and statistical models are available to infer a variety of user sentiments in posts on social *** amount of data generated by social media platforms,such as Twitter,that can be used to track diseases is increasing *** paper proposes a method for the classication of tweets related to the outbreak of dengue using machine learning *** articial neural network(ANN)-based method is developed using Global Vector(GloVe)embedding to use the data in tweets for the automatic and efcient identication and classication of *** proposed method classies tweets related to the outbreak of dengue into positives and *** were conducted to assess the proposed ANN model based on performance evaluation matrices(confusion matrices).The results show that the GloVe vectors can efciently capture a sufcient amount of information for the classier to accurately identify and classify tweets as relevant or irrelevant to dengue *** proposed method can help healthcare professionals and researchers track and analyze epidemic outbreaks through social media in real time.

关键词： Articial neural network classication social media GloVe social networking sites

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Assessment and Evaluation: Enhancing Sustainability in Educational Practices

AI-Driven Assessment and Evaluation: Enhancing Sustainabilit...

引用

Automation, computing and Renewable Systems (ICACRS), International Conference on

作者： P. Chinnasamy M. Pushpalatha V. Nirmala Vidhya V Ramesh Kumar Ayyasamy Divya Priya Department of Computer Science and Engineering School of Computing Kalasalingam Academy of Research and Education Tamilnadu India Department of Computer Science and Technology Karpagam College of Engineering Coimbatore India Department of MCA Annamacharya PG College of Computer Studies Kadapa Artificial Intelligence and Data Science Kongunadu College of Engineering and Technology (Autonomous) Faculty of Information and Communication Technology Universiti Tunku Abdul Rahman (UTAR) Kampar Perak Malaysia Department of Computer Science and Engineering MLR Institute of Technology Hyderabad India

ISBN: (数字)9798331532420

ISBN: (纸本)9798331532437

AI-powered educational technologies are emerging as transformative forces in the quickly changing field of education, where innovation is essential to keeping ahead of the competition. Assessments are one area that is undergoing revolutionary transformation. Artificial Intelligence (AI) is redefining the way we evaluate learning outcomes as traditional evaluation approaches struggle to keep up with the demands of the digital age. The field of artificial intelligence-powered learning assessments has a lot of promising future developments ahead of it. This research proposes novel technique in assessment and evaluation based on online education system using Artificial intelligence in machine learning techniques. Here, the input has been analysed as student performance data based on online education and processed for removing of missing values with noise removal. Then this data has been analysed using spatio LSTM convolutional fuzzy neural network for classification of evaluation and assessment model. the experimental analysis has been carried out for various student performance analysis dataset in terms of training accuracy, average precision, specificity, F-measure and recall. Proposed method training accuracy 97%, Average precision 94%, F-measure 90%, RECALL 93%, SPECIFICITY 96%.

关键词： Training Technological innovation Renewable energy sources Accuracy Education Learning (artificial intelligence) Machine learning Fuzzy neural networks Sustainable development Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Automated Heart Disease Diagnosis and Monitoring System Using Similarity-Navigated Graph Neural Networks with Leopard Seal Optimization in IoT Healthcare Applications

Automated Heart Disease Diagnosis and Monitoring System Usin...

引用

Sustainable Expert Systems (ICSES), International Conference on

作者： V. Sripathi Raja Ruchira Rawat Karuna Pandit Raghu Dhumpati Vipul Vekariya S Vijitha Department of Biomedical Engineering B V Raju Institute of Technology Narsapur Telangana India Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun Uttarakhand India Department of Information Science and Engineering NMAM Institute of Technology (NITTE Deemed to be University) Nitte Karkala Udupi District Karnataka India Department of Computer Science and Engineering Bahrain Polytechnic Isa Town Isa Town Bahrain Department of Computer Science and Engineering Parul Institute of Engineering and Technology Parul University Waghodia Gujarat India Department of computer science and Engineering Vels Institute of Science Technology and Advanced Studies Pallavaram Chennai Tamil Nadu India

ISBN: (数字)9798331540364

ISBN: (纸本)9798331540371

One of the leading causes of death worldwide continues to be heart disease; therefore, early detection and precise diagnosis are essential to better patient outcomes. The conventional methods of diagnosing chemotherapy-induced nail changes involve a great deal of laboratory testing, which is more than exhaustive. In order to tackle these obstacles, this research introduces a novel methodology for the automated diagnosis and continuous tracking of heart diseases in the IoT -based health care system, integrated with deep learning algorithms. The proposed system includes several state-of-the art techniques to improve diagnostic reliability and speed. First of all, min-max normalization is used as a pre-processing technique that aims at pre-scaling the data of patients to a consistent level and, as a result, enhancing the performance of the model. The Mud Ring Algorithm is then used for feature selection, whereby the best features are chosen together with the reduction in dimensionality to decrease computational intensity, thus improving diagnostic accuracy. The core diagnostic engine is based on Similarity Navigated Graph Neural Networks (SNGNN) and has been enhanced with Leopard Seal Optimization (LSO), a new meta-method motivated by the hunting patterns of leopard seals. This combination enables the system to relate various features and give the correct prognosis for heart diseases. These techniques, applied within the IoT framework, enable real-time monitoring and diagnosis and therefore have the benefit of being a scalable solution for modern health care systems. The results show that the proposed method for providing diagnosis of heart disease is accurate, timely, and reliable and thus has the potential to revolutionize patient management in healthcare based on the IoT.

关键词： Heart Navigation Medical services Seals Feature extraction Graph neural networks Reliability Optimization Monitoring Diseases

来源：评论

学校读者我要写书评

暂无评论

Efficient Quantum Simulation Algorithms in the Path Integral Formulation

arXiv

引用

arXiv 2024年

作者： Shum, Serene Wiebe, Nathan University of Toronto Department of Physics Toronto Canada University of Toronto Department of Computer Science Toronto Canada Pacific Northwest National Laboratory High Performance Computing Division Richland United States Canadian Institute for Advanced Study Toronto Canada

We provide a new paradigm for quantum simulation that is based on path integration that allows quantum speedups to be observed for problems that are more naturally expressed using the path integral formalism rather than the conventional sparse Hamiltonian formalism. We provide a quantum algorithm for Lagrangians of the form ∑γ mγ/2 x 2γ − V (x), as well as two novel quantum algorithms based on Hamiltonian versions of the path integral formulation. The Lagrangian path integral algorithm is based on a new rigorous derivation of a discrete version of the Lagrangian path integral. We show that for the time evolution of a system with η particles in D + 1 dimensions for time T, our Lagrangian simulation algorithm requires a number of queries to an oracle that computes the discrete Lagrangian that scales in the continuum limit as Oe(ηDT2/ϵ), if V (x) is bounded and finite and the wave function obeys appropriate position and momentum cutoffs. This shows that Lagrangian dynamics can be efficiently simulated on quantum computers and opens up the possibility for quantum field theories for which the Hamiltonian is unknown to be efficiently simulated on quantum computers. Our first Hamiltonian path integral method breaks up the paths into short time steps. It is efficient under appropriate sparsity assumptions and requires a number of queries to oracles that give the eigenvalues and overlaps between the eigenvectors of the Hamiltonian terms that scales as to(1)/ϵo(1) for simulation time t and error ϵ. The second approach uses long-time path integrals for near-adiabatic systems and has query complexity that scales as O(1/√ϵ) if the energy eigenvalue gaps and simulation time is sufficiently long. © 2024, CC BY.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI 41

Position: Bayesian Deep Learning is Needed in the Age of Lar...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Papamarkou, Theodore Skoularidou, Maria Palla, Konstantina Aitchison, Laurence Arbel, Julyan Dunson, David Filippone, Maurizio Fortuin, Vincent Hennig, Philipp Hernández-Lobato, José Miguel Hubin, Aliaksandr Immer, Alexander Karaletsos, Theofanis Khan, Mohammad Emtiyaz Kristiadi, Agustinus Li, Yingzhen Mandt, Stephan Nemeth, Christopher Osborne, Michael A. Rudner, Tim G.J. Rügamer, David Teh, Yee Whye Welling, Max Wilson, Andrew Gordon Zhang, Ruqi Department of Mathematics The University of Manchester Manchester United Kingdom Eric and Wendy Schmidt Center Broad Institute of MIT and Harvard Cambridge United States Spotify London United Kingdom Computational Neuroscience Unit University of Bristol Bristol United Kingdom Centre Inria de l'Université Grenoble Alpes Grenoble France Department of Statistical Science Duke University United States Statistics Program KAUST Saudi Arabia Helmholtz AI Munich Germany Department of Computer Science Technical University of Munich Munich Germany Munich Center for Machine Learning Munich Germany Tübingen AI Center University of Tübingen Tübingen Germany Department of Engineering University of Cambridge Cambridge United Kingdom Department of Mathematics University of Oslo Oslo Norway Bioinformatics and Applied Statistics Norwegian University of Life Sciences Ås Norway Department of Computer Science ETH Zurich Switzerland Chan Zuckerberg Initiative CA United States Center for Advanced Intelligence Project RIKEN Tokyo Japan Vector Institute Toronto Canada Department of Computing Imperial College London London United Kingdom Department of Computer Science UC Irvine Irvine United States Department of Mathematics and Statistics Lancaster University Lancaster United Kingdom Department of Engineering Science University of Oxford Oxford United Kingdom Center for Data Science New York University New York United States Department of Statistics LMU Munich Munich Germany DeepMind London United Kingdom Department of Statistics University of Oxford Oxford United Kingdom Informatics Institute University of Amsterdam Amsterdam Netherlands Courant Institute of Mathematical Sciences Center for Data Science Computer Science Department New York University New York United States Department of Computer Science Purdue University West Lafayette United States

In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language datasets. However, a broader perspective reveals a multitude of overlooked metrics, tasks, and data types, such as uncertainty, active and continual learning, and scientific data, that demand attention. Bayesian deep learning (BDL) constitutes a promising avenue, offering advantages across these diverse settings. This paper posits that BDL can elevate the capabilities of deep learning. It revisits the strengths of BDL, acknowledges existing challenges, and highlights some exciting research avenues aimed at addressing these obstacles. Looking ahead, the discussion focuses on possible ways to combine large-scale foundation models with BDL to unlock their full potential. Copyright 2024 by the author(s)

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Algorithmic Innovations in Machine Learning for Drug Discovery and Pharmaceutical Innovations

Algorithmic Innovations in Machine Learning for Drug Discove...

引用

Trends in Quantum computing and Emerging Business Technologies (TQCEBT), International Conference on

作者： M. Sangeetha F. Mary Harin Fernandez A. Ganesh Ramachandran S. K. Saravanan M. Bhanumathi Department of Computer Engineering University of Technology and Applied Sciences Nizwa Sultanate of Oman Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai India Department of Computer Science Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai India Department of Computers Science and Engineering BigData and Network Security Saveetha School of Engineering SIMATS Chennai Tamil Nadu Department of Computer Science and Engineering Vels Institute of Science Technology and Advanced Studies (VISTAS) Chennai India

ISBN: (数字)9798350384277

ISBN: (纸本)9798350384284

Algorithmic advancements in machine learning have transformed drug discovery and pharmaceutical innovation. This study examines how machine learning might speed medication development and pharmaceutical innovation. Data from genomes, chemistry, and clinical trials is collected to start the research. Careful data cleansing, normalization, and feature engineering prepare the data for model building. Random Forest, SVM, NN, Decision Tree, and Logistic Regression are tested for prediction. ROC AUC results show that Random Forest is the most accurate model at 86%. Ensemble approaches have drug discovery potential. Beyond accuracy, models are assessed for precision, false positive, and false negative rates. Drug discovery relies on precision to measure positive predictions. The Random Forest model makes the most accurate positive predictions at 0.87. However, false positives and negatives also matter in drug discovery. The Decision Tree model contains the falsest positives (35), underlining the need to reduce them to save resources. The Neural Network approach reduces false negatives to 12, ensuring good medication candidates are not overlooked. The results show that different machine learning models have trade-offs, underscoring the necessity for a personalized strategy depending on objectives and restrictions. Algorithmic breakthroughs in pharmaceutical innovation reduce medication development time by 40% and cost by 25%, according to the study.

关键词： Support vector machines Drugs Technological innovation Logistic regression Machine learning algorithms Genomics Prediction algorithms

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：