检索结果-内蒙古大学图书馆

Marching Forward: Redefining Human-machine Interactions in Conversational AI Through Hybrid intelligence, Blockchain Security, and Autonomous Agents 9

Marching Forward: Redefining Human-Machine Interactions in C...

引用

9th International Conference on Communication and Electronics Systems, ICCES 2024

作者： Charanya, P. Santhos Raj, B.S. Naveen Kumar, T. Pradheeban, A. Sri Eshwar College of Engineering Department of Artificial Intelligence and Machine Learning Coimbatore India Sri Eshwar College of Engineering Coimbatore India

ISBN: (纸本)9798350377972

Conversational AI has emerged as an essential instrument in enhancing human-computer interaction, with applications spanning customer service to personal assistants. This paper offers a comprehensive examination of recent developments in conversational AI, including novel techniques in natural language generation (NLG), dialogue systems, and dynamic response optimization. We analyze advancements including transformer-based architectures, reinforcement learning for dialogue generation, and retrieval-augmented models, emphasizing their roles in enhancing the quality and contextual accuracy of conversations. Additionally, we examine the feasibility of blockchain technology as the foundation for decentralized AI, promoting secure, transparent, and distributed frameworks for AI applications, hence improving privacy and control in data exchanges. Hybrid methodologies that combine symbolic reasoning with deep learning are analyzed, highlighting their effectiveness in addressing complex dialogues. These advancements, supported by empirical research and benchmark performance, signify the evolution towards more personalized, intelligent, and decentralized conversational systems. © 2024 IEEE.

关键词： Chatbots

来源：评论

学校读者我要写书评

暂无评论

Identification of Infectious Disease Like COVID-19 Gene Biomarkers Using a Clear artificial intelligence Approach

引用

SN Computer Science 2025年第4期6卷 1-13页

作者： Dubey, Shivendra Verma, Dinesh Kumar Kumar, Mahesh Department of Artificial Intelligence and Machine Learning Manipal University Jaipur Rajasthan Jaipur India Department of Computer Science and Engineering Jaypee University of Engineering and Technology MP Guna India

This study offers an approach that uses SARS-COV-2 mNGS (meta-genomic next-generation sequencing) samples to apply XAI (explainable artificial intelligence) methodologies derived from the use of machine learning methods. The research's data set contains 15,979 expressions of genes from 234 infected persons, of whom 39.68% (93) had SARS-COV-2 that was positive and 60.29% (141) had SARS-COV-2 that was negatives. The SARS-COV-2 related gene was chosen using the LASSO (least absolute shrinkage and selection operator) technique. The class imbalanced issue has been resolved using the SVM-SMOTE (Support Vector machine - Synthetic Minority Oversampling Technique) approach. To identify SARS-COV-2 related biomarkers possibilities and increase the comprehensibility of the final approach, an explainable strategy that utilized SHAP (SHAPley Additive exPlanations) as well as LIME (local interpretable model-agnostic explanations) approaches were used. The XGBoost (92.98% accuracy) approach performs better for the identification of infectious diseases like COVID-19 than the LR (91.17% accuracy), SVM (87.68% accuracy), and RF (91.18% accuracy) models. The three most significant genes connected to COVID-19 by the SHAP method were FAM83A, LGR6, and IFI27. The LIME findings demonstrated that the likelihood of a positive class was particularly influenced by the elevated degree of IFI27 expression of genes. Infectious diseases like COVID-19 could be accurately predicted using the suggested framework (XGBoost). The findings demonstrate that SHAP and LIME, along with the exploit of ML methods, it could be clarify the biological marker prognosis for infectious disease and give health center a clear knowledge about how potential risk factors affect the forecasts made by the model. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Biomarker Gene LIME SARS SHAP

来源：评论

学校读者我要写书评

暂无评论

The Impact of machine learning (ML) Driven Algorithm Ranking and Visualization on Task Scheduling in Cloud Computing 3

The Impact of Machine Learning (ML) Driven Algorithm Ranking...

引用

3rd International Conference on Advancement in Electronics and Communication engineering, AECE 2023

作者： Chhabra, Manish Arora, Gagandeep Vardhaman College of Engineering Department of Artificial Intelligence and Machine Learning Telangana Hyderabad501286 India

ISBN: (纸本)9798350330724

Efficient task organization is essential to maximizing cloud computing's performance. We provide a new machine learning (ML) approach to evaluate and rank task scheduling algorithms based on their features. By employing GDrive and the Spacy English model for feature extraction, we identify and quantify important phrases related to algorithm characteristics. We establish the relative importance of each attribute by giving these terms precedence based on our methodology, particularly based on their frequency. We then combine these priorities to get priority scores for each algorithm, which reveal the algorithms' performance potential. An analysis of the priority ratings can be used to determine the best work scheduling algorithm. The X- Y plot that displays these ratings makes it easier for people to comprehend and contrast the various algorithms. With the help of our innovative method, users-whether personal or business-can make well-informed decisions that maximize cloud resource use and boost overall productivity. In order to optimize cloud computing efficiency, this research paper suggests a machine learning-driven idea backed by feature to follow navigate several work algorithms for scheduling. In cloud environments, artificial intelligence's power greatly aids in achieving greater resource efficiency and enhanced performance. © 2023 IEEE.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

Secure Healthcare Monitoring: Algorithms and Techniques for Heart Disease Detection and Data Privacy 1

Secure Healthcare Monitoring: Algorithms and Techniques for ...

引用

1st International Conference on Intelligent Systems and Computational Networks, ICISCN 2025

作者： Poonam Mallapur, Sujata V. Sharnbasva University Department of Computer Science and Engineering Kalaburagi India Sharnbasva University Department of Artificial Intelligence & Machine Learning Kalaburagi India

ISBN: (纸本)9798331529246

This survey offers the review of Healthcare Monitoring Systems (HMS) and Privacy Preservation (PP) approaches. The main objective is based on the detection of heart disease and maintain the security for patient data. The machine learning models such as SVM, decision trees, and neural networks for heart disease detection and encryption approaches such as AES, ECC, and homomorphic encryption for securing the data are the major topics that reviewed in this survey. Moreover, the survey highlights the performance evaluation for heart disease prediction and the datasets used for heart disease. It also ensures the privacy to tackle the challenges in real time monitoring. A higher accuracy of 99.8 was reached by FHE-based encryption method. Moreover, it discusses the research gaps like scalability, efficiency, and regulatory compliance which motivates the need of novel privacy-preserving techniques for healthcare systems, which is highlighted in the future scope. © 2025 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Solar Power Plant Capacity Monitoring Using Random Forest machine learning Algorithm

Solar Power Plant Capacity Monitoring Using Random Forest Ma...

引用

2024 IEEE IAS Industrial and Commercial Power System Asia, I and CPS Asia 2024

作者： Ogar, Emmanuel Ede Chaitusaney, Surachai Benjapolakul, Watit Center of Excellence in Artificial Intelligence Machine Learning and Smart Grid Technology Chulalongkorn University Faculty of Engineering Department of Electrical Engineering Bangkok Thailand

ISBN: (纸本)9798350352290

The natural abundance of solar energy and its favorable environmental impacts have led to growing acceptance and utilization as the world transitions from a fossil fuel-based economy to a cleaner, more sustainable, and ecologically friendly alternative. An increasing number of solar photovoltaic projects have emerged to capitalize on these benefits. However, factors such as weather conditions, exposure to natural elements, device deterioration, improper installations, and maintenance concerns can eventually compromise these systems' power-generating performance and dependability over time. This study demonstrates how the random forest machine learning classifier can be used to monitor and categorize the performance of solar PV plants to ensure their reliability and efficiency. The study collected and preprocessed a field dataset containing various environmental and electrical parameters. These parameters include plant capacity, active power, generating capacity, ambient temperature, global radiation, and module temperature. This data was used to train a random forest machine learning algorithm to categorize the operational condition of the solar power plant. The results demonstrate that the model efficiently classified the operational condition of the solar power plant by effectively identifying conditions such as optimal mode, moderate sub-optimal mode, severe sub-optimal mode, critical mode, emergency mode, and offline mode, achieving 99.92% accuracy on the test set. The proposed method provides an effective technique for estimating and monitoring the generating capacity and operational condition of solar power plants in near real time, thereby serving as a distinctive instrument for boosting the efficiency and reliability of solar power generation. © 2024 IEEE.

关键词： artificial intelligence Capacity monitoring machine learning Random Forest algorithm Solar cell

来源：评论

学校读者我要写书评

暂无评论

Advanced Energy Consumption Forecasting in Smart Grids Using Quantum Boltzmann machines 2

Advanced Energy Consumption Forecasting in Smart Grids Using...

引用

2nd IEEE Global Conference on Communications and Information Technologies, GCCIT 2024

作者： Velayutham, P. Balaji, V.S. Krissh Shankaran, N. Aarupadai Veedu Institute of Technology Department of Computer Science and Engineering India Rajalakshmi Engineering College Department of Artificial Intelligence and Machine Learning India

ISBN: (数字)9798350388916

ISBN: (纸本)9798350388916

Smart grid systems are seen as the next big thing to energy distribution and management with more efficiency, stability, and sustainability in power distribution and energy management systems. It is challenging to predict the amount of energy consumption in smart grid system because of its randomness resulting from various factors such as consumer's behavior, weather conditions. This is mainly because traditional forecasting techniques are usually inadequate in capturing these complexities and as a result resources are poorly allocated and organizational processes become inefficient. The work provides the energy consumption forecasting in smart grids through the application of Quantum Boltzmann machine(QBM) in the smart grid utilizing historical data. Some of the variables incorporated in the data are reaction time, power balance, and price elasticity coefficients customized through smart meters. Once raw data is preprocessed, QBMs are developed to establish an empirical probability model that will predict actual future energy utilization characteristics. The QBM is tested against the actual consumption data and focuses on the visualization of energy profile and identification of points like local extremes. © 2024 IEEE.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

Improved fuzzy C means with deep learning-based MANET routing model for multimedia communication

引用

International Journal of Networking and Virtual Organisations 2024年第4期31卷 306-338页

作者： Biradar, Manjula A. Mallapur, Sujata Department of Computer Science and Engineering Sharnbasava University Sharan Nagar Karnataka Kalaburagi585105 India Department of Artificial Intelligence and Machine Learning Sharnbasava University Sharan Nagar Karnataka Kalaburagi585105 India

The rapid growth of wireless communication amazed the researchers to done multimedia communication via wireless networks. The significant rise of mobile ad-hoc networks (MANET) in wireless communication is widely researched by researchers for an efficient transmission of multimedia data. MANET works on non-infrastructure topology with high quality of service (QoS) for better user experience. Though, it suffers from limitations such as routing, limited bandwidth, dynamic mobile node nature, etc. That’s why, this research paper is dedicated to introduce a MANET routing model for multimedia communication by providing reliable retransmission for better communication. An optimal cluster-based routing via improved fuzzy C-means (FCM) clustering takes place before it gets started nodal energy prediction is done by modified deep CNN model. And optimal cluster head selection is done via self-improved coati optimisation (SICO) under certain constraints. Finally, it is finished off with reliable retransmission to enhance the reliability of communication. Further, the efficiency of the proposed model is proved by various analysis. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Mobile ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Intelligent Accessory for Self Defense 1

Intelligent Accessory for Self Defense

引用

1st International Conference on Electronics, Communication and Signal Processing, ICECSP 2024

作者： Harshith, Venuthurupalli Swarna, Kanagandla Kumar, Badugula Bharath Abhinay, Pilli Sneha, Baddam Unnisa, Fatima Vardhaman College of Engineering Department of Artificial Intelligence and Machine Learning Hyderabad India Vardhaman College of Engineering Department of Electrical and Electronics Engineering Hyderabad India

ISBN: (纸本)9798350364590

In an instance when fears about personal safety are growing, especially for the weaker members of society like the physically impaired, inventive technological solutions are essential. This study describes a multifunctional self-defense gear that combines cloud computing, Internet of Things (IoT) devices, and machine learning (ML) algorithms to lessen potential threats. The add-on uses a pulse sensor to recognize high heart rates that could be a sign of danger. This allows a camera to be activated in order to analyze the threat. The ML algorithms use facial gesture analysis and prerecorded photographs of known criminals to evaluate the scenario and, if needed, trigger a small pepper spray module for immediate defense. The gadget also has a GPS tracker built in to notify local authorities of the user's location in the happening of an emergency. The captured video is securely kept on a cloud-based stand that is only accessible to the owner, escalating the usefulness of the add-on as a prophylactic and possible proof lest of an urgent situation. This essay describes the self-defense accessory's development, application, and assessment, emphasizing how it might deeply improve private security for people of all ability levels. © 2024 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Streamlining Personal Finances: An ExpenseTracker Website Study

Streamlining Personal Finances: An ExpenseTracker Website St...

引用

2024 IEEE International Conference on Signal Processing and Advance Research in Computing, SPARC 2024

作者： Sahel, Mohammed Ismail, Shaik Sohail, Shaik Srilekha, Sirasawada Unnisa, Fatima Vardhaman College of Engineering Department of Artificial Intelligence & Machine Learning Hyderabad India Vardhaman College of Engineering Department of Electrical and Electronics Engineering Hyderabad India

ISBN: (纸本)9798350385199

Expense tracker is a machine based function. The 'Expense Chaser' function can simplify and improve personal money management, resulting in improved financial health and reduced stress and also it is designed to computerize the process of managing and following up on pending or overdue expenses. This function leverages a systematic algorithm that identifies expenses requiring attention based on their due dates and statuses. It uses supervised learning methods, like as neural networks or decision trees, to learn and forecast categories based on past data. Which is work by querying the database to find expenses marked as pending or overdue, and then sends timely reminders to users via email as their due dates approach or pass. Additionally, it updates the status of expenses in real-time, ensuring accurate recordkeeping. By automating these tasks, it can enhances financial management, improves user experience and maintains up-to date records, thereby promoting financial discipline and ensuring that all obligations are met efficiently. Further, it can be extended by scanning the barcode on the price tag, enhanced to reduce the effort required to enter data into the input fields. In addition to recording individual logs, it proposed to add a shared consuming group to this system in future. © 2024 IEEE.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Predictive Modeling Techniques for Anticipating Vaccine Demand 1

Predictive Modeling Techniques for Anticipating Vaccine Dema...

引用

1st IEEE International Conference on Computing and Data Science, ICCDS 2024

作者： Vinitha, S. Prasanthi, T. Nithya, D. Jerusalem College of Engineering Department of Artificial Intelligence and Machine Learning Chennai India Jerusalem College of Engineering Department of Cyber Security Chennai India

ISBN: (纸本)9798350365337

Infant vaccine stock prediction is a critical aspect of health care logistics management aimed at ensuring the availability of essential vaccines to safeguard children against preventable diseases. With an emphasis on newborn requirements, this study suggests employing cutting-edge machine learning algorithms to forecast vaccine supply requirements. Traditional forecasting methods often struggle to adapt to the dynamic and complex nature of vaccine demand, leading to inefficient stock management and potential shortages. To address these challenges, this research explores the efficacy of advanced machine learning algorithms such as Gradient Boosting machines (GBM), Long Short-Term Memory (LSTM) networks, and Support Vector regression (SVR) in predicting infant vaccination stock needs. These algorithms provide the capacity to examine past immunization data, spot trends, and more reliably and accurately proj ect future demand. Through extensive experimentation and evaluation using real-world vaccination data sets, the proposed algorithms demonstrate promising results in accurately predicting stock requirements for infant vaccines. The results of this study help to improve the efficacy and efficiency of vaccination supply chains, guaranteeing infants across the world will have timely access to vaccinations that can save their lives. The present investigation employed machine learning models, namely the linear regression model, Random Forest model, GBM and SVR model, and deep learning models, such as ANN and LSTM, to forecast future trends in essential infant vaccines. The models' performances were compared using the evaluation metrics RMSE and R-Square, as well as by comparing their predictions. © 2024 IEEE.

关键词： Long short-term memory

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：