检索结果-内蒙古大学图书馆

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Gupta, Keshav Kumar, Vikas Jain, Abhishek Singh, Pranita Jain, Amit Kumar Prasad, M.S.R. Grd Institute of Management and Technology Department of Computer Science and Engineering Dehradun India School of Computer Science & Engineering Dev Bhoomi Uttrakhand University Dehradun India Uttaranchal University Department of Computer Science and Engineering Dehradun India Roorkee Institute of Technology Department of Computer Science and Engineering Roorkee India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Vaddeswaram India

ISBN: (纸本)9798350371055

Provide an attraction recommendation system that uses deep learning and is powered by the Internet of Things (IoT) to develop the smart city visitor experience. Users of a smart city app or website will be able to record information about their trips, including whether they are going independently or with an accompanying companion, the sort of companion (e.g., a family with children or a lover), the purpose of their trip (business or pleasure), and personal characteristics (e.g., age, interests, etc.). Using this unique combination of input data, the suggested deep learning-based recommendations system would suggest tourist activities and sights that match the user's profile nicely. In addition, the suggested tourist attraction recommendations system uses actual data obtained from Internet of Things (IoT) devices to offer content-based information (such as previously looked-at sights) and context related data (such as weather conditions, location, time of day, etc.) to potential visitors in the smart city. Regarding the initial case [(a) planning and searching for activities earlier travelling], the suggested multi-label deep learning classifiers achieve a recall, accuracy, precision, and loss of 1.6%, 98.6%, 98.8%, and 98.7%, respectively, compared to other models such as extra tree, decision tree, k-nearest neighbour, and randomized forest. As for the second scenario, it can effectively suggest tourist spots while searching for smart city activities (b) with a recall, accuracy, precision, and loss of 2.6%, 98.4%, 98.6%, and 98.7%, respectively. © 2024 IEEE.

关键词： Deep Learning Internet of Things Personal Characteristics Recommendation System Smart City Activities

来源：评论

学校读者我要写书评

暂无评论

TamilCogniBERT: Enhancing Tamil Language Comprehension using Self Learning

TamilCogniBERT: Enhancing Tamil Language Comprehension using...

引用

2024 International Conference on Advances in Data engineering and Intelligent Computing Systems, ADICS 2024

作者： Ashwinraj, G. Sarfraz Hussain, M. Madhu Perkin, T. Hindustan Institute Of Technology And Science Department Of Computer Science & Engineering Chennai India

ISBN: (纸本)9798350364828

TamilCogniBERT is a ground-breaking initiative that uses cutting-edge natural language processing methods to improve comprehension of the Tamil language. The research uses a leading deep learning model called BERT (Bidirectional Encoder Representations from Transformers) to create a powerful language comprehension system designed for Tamil. TamilCogniBERT aims to close the gap in language processing technology for Tamil, facilitating more efficient communication and understanding in this complex and multifaceted language. The project comprises several essential elements, such as gathering data, preprocessing, modifying the model, incorporating user input, and implementing self-learning processes. First, a large-scale corpus of Tamil text data is carefully selected from a variety of internet, offline, and social media sources. Tokenization, noise reduction, and normalization are just a few of the rigorous preparation procedures this corpus goes through to guarantee quality and consistency. Subsequently, the Tamil corpus is utilized to modify and enhance a pre-trained BERT model. This technique entails using tasks like text categorization, sentiment analysis, and question answering to train the model on information pertinent to Tamil language understanding. The model is now capable of correctly comprehending and interpreting Tamil text thanks to this update. TamilCogniBERT's use of user feedback techniques is one of its unique advantages. The model learns to be more sensitive to the subtleties and complexities of the Tamil language as it is used in everyday situations by asking users for feedback and incorporating their responses into the learning process. TamilCogniBERT enhances the training process by using self-learning strategies. © 2024 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Supporting 6G Mission-Critical Services on O-RAN

引用

IEEE Internet of Things Magazine 2023年第3期6卷 32-37页

作者： Kaliski, Rafael Cheng, Shin-Ming Hung, Cheng-Feng Taiwan Taiwan National Taiwan University of Science and Technology Department of Computer Science and Information Engineering Taipei Taiwan

In the era of 6G, cellular networks will no longer be locked into a small set of equipment manufacturers;instead, cellular networks will be disaggregated and support open interfaces. Thus, there is an inherent need for networking functions to be softwarized and virtualized so that customers can apply different vendors' solutions. 6G mission-critical networks must be dependable and secure, ultra-reliable and low latency, and support high connectivity, all while being flexible enough to support custom user deployments. 6G will integrate Artificial Intelligence (AI) into the network architecture to meet the diverse user requirements of 3rd party solutions. A possible 6G candidate capable of supporting the requirements above is Open Radio Access Networks (O-RAN). O-RAN enables multiple levels of AI-based control for RAN Intelligent Controllers (RICs). RICs facilitate real-time sensing, reaction, policy determination, and management of radio resources. When coupled with Multi-access Edge Computing (MEC), O-RAN enables customized per-device AI service chains that can address the needs of dynamic, diverse 6G networks in real-time. This article presents an O-RAN architecture that supports split-plane multi-component cooperative AI models that utilize multiple RIC-centric and MEC-centric control loops. Through multiple example applications and O-RAN testbeds, we demonstrate the efficacy of our proposed architecture and how it can address the multitude of 6G requirements as necessitated for mission-critical Internet of Things applications. © 2018 IEEE.

关键词： Radio access networks

来源：评论

学校读者我要写书评

暂无评论

Echo Guidance: Voice-Activated Application for Blind with Smart Assistive Stick Using Machine Learning and IoT

Echo Guidance: Voice-Activated Application for Blind with Sm...

引用

2024 International Conference on Advances in Data engineering and Intelligent Computing Systems, ADICS 2024

作者： Abishek Kumar, G. Surya, G. Sathyadurga, V. Hindustan Institute Of Technology And Science Department Of Computer Science & Engineering Chennai India

ISBN: (纸本)9798350364828

Navigating the world without sight presents profound challenges for millions of visually impaired individuals. Echo Guidance includes a pioneering application, addresses these obstacles by facilitating independence and mobility through voice-driven interaction and an IoT smart assistive device for obstacle detection by utilizing Ultrasonic, GPS and GSM modules powered by Arduino. This study explores the design and evaluation of Echo Guidance, highlighting its utilization of advanced algorithms like RGB888 conversion, matrix transformation, and Optical Character Recognition (OCR) for real-time object recognition. The application boasts a voice-centric interface tailored to the needs of the visually impaired, seamlessly integrating day-to-day functionalities such as weather forecasting, reminders, and a calculator accessible through voice commands. Central to Echo Guidance is its innovative object detection and recognition approach, employing the MobileNetObjDetector class powered by TensorFlow Lite for swift and accurate object detection. The OverlayView class visually represents detected objects, enhancing spatial awareness. Additionally, the integration of IoT devices, such as the smart stick with ultrasonic sensors for obstacle detection and head-level obstacle detection, coupled with SOS functionality in case of any emergency using GPS and GSM modules, further enhances Echo Guidance's capabilities. This research underscores Echo Guidance's transformative potential in improving the quality of life for visually impaired individuals, representing a significant advancement in assistive technology. Prioritizing accessibility and user experience, this paper empowers individuals worldwide with newfound independence and confidence in navigating their surroundings. © 2024 IEEE.

关键词： Linear transformations

来源：评论

学校读者我要写书评

暂无评论

Network Summarization Through the Lens of Latent Semantic Analysis and Fuzzy Techniques

Network Summarization Through the Lens of Latent Semantic An...

引用

International Conference on Internet of Everything and Quantum Information Processing, IEQIP 2023

作者： Vanathi, M. Lakshmanan, L. Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India

ISBN: (纸本)9783031619281

Extracting text summarization involves the retention of only the most important sentences in a document. Finding the appropriate ranking order of the phrases in the document according to their relevance is a vital step in extractive text summarization. Singular value decomposition or SVD algorithm based on latent semantic analysis focuses on recognizing the sections in the document which are related in terms of their semantic nature. Fuzzy algorithms involve reasoning of the priority order of the sentences using fuzzy logic unlike the use of discrete values. While significant work has been done for extractive text summarization in English and other foreign languages, there is ample scope for improving the performance of systems when dealing with Marathi text. An analysis of the characteristics of both these techniques is conducted to compare their benefits and shortcomings. The performance of both the algorithms is evaluated on a document dataset using standard performance metrics including the ROUGE metric. Both of these approaches are objectively compared in order to determine their applicability, particularly when dealing with non-English text in general or Marathi in particular. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

An Assistive Vision for a Visually Challenged Person using Alexa 4

An Assistive Vision for a Visually Challenged Person using A...

引用

4th IEEE International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2024

作者： Dheeraj, Chilakapati Reddy, Kothapalli Sujith Rajalakshmi, R. Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350360165

It has been associated with converters and inverters. The system has been found to be feasible in efficiently utilizing Photovoltaic energy and integrating it with the electrical grid without any disturbances. The successful integration of this two-stage system assures not only that the power generated comes from the photovoltaic panels but also that grid stability and power quality are assured. This project brings in a new control methodology for active power regulation and is the main constituent for this system. Based on real-time monitoring and advanced control algorithms, it assures very accurate matching of power generation with grid demand in dynamic power adjustment capabilities. This feature maximizes the consumed power but also improves the grid stability through voltage and frequency control, thus minimizing the impact of variable Photovoltaic irradiance. Alongside, the converters and inverters applied in the system provide an essential interface between the D.C. output from the Photovoltaic panels and the A.C. grid;thus, it is possible to provide bidirectional power flow seamlessly into the grid. The active power regulation control approach to be adopted in this double-stage single-phase gridconnected P.V. system, with the converter and inverter facilities, is a sustainable and reliable solution for Photovoltaic power generation and grid integration. Such development and deployment will not only become a part and parcel of the global shift to renewable energy but also provide the current grid integration, power quality, and efficiency challenges with a feasible and promising solution. Considering the huge role that Photovoltaic energy can play in our profile, this project actually becomes a contribution to furthering renewable energy systems. © 2024 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

An Integrated Development Of IoT Based Machine Learning For Data-Driven Travel Recommendations

An Integrated Development Of IoT Based Machine Learning For ...

引用

2024 International Conference on Advances in Data engineering and Intelligent Computing Systems, ADICS 2024

作者： Rifath, Shakeel Sridhar Xavier, Constance Brindasri, S. Hindustan Institute Of Technology And Science Computer Science And Engineering Department Chennai India

ISBN: (纸本)9798350364828

An innovative methodology is introduced in this Research to enhance data-driven travel decision-making by integrating IoT technology and data science techniques. With a specific focus on air and sound pollution, the research utilizes real-time sensor data from various urban sources to develop predictive models for forecasting future pollution levels. These models serve as the backbone for decision support tools seamlessly integrated into open-source platforms like ThingSpeak and IFTTT, facilitating proactive travel planning for both the general public and patients. The core of this methodology lies in the real-time aggregation of IoT sensor data, offering users comprehensive insights into prevailing air pollution levels at their intended destinations. Augmented by predictive machine learning algorithms such as logistic regression and decision trees, the system's real-time monitoring capabilities are significantly enhanced, with the decision tree algorithm particularly noted for its accuracy in assessing destination safety for patients. The forecasting accuracy and reliability of the model are upheld through rigorous training on historical data. Notably, the synergy between ThingSpeak and IFTTT enables the delivery of personalized travel recommendations grounded in predictive analytics and real-time environmental monitoring. This research underscores the pivotal role of data-driven decision-making in travel planning, empowering patients with tailored guidance derived from robust data analysis. © 2024 IEEE.

关键词： Predictive analytics

来源：评论

学校读者我要写书评

暂无评论

Spectrogram Features and Xception Classifier Based Audio Spoof Detection System

Spectrogram Features and Xception Classifier Based Audio Spo...

引用

2024 International Conference on computer, Electronics, Electrical engineering and their Applications, IC2E3 2024

作者： Chakravarty, Nidhi Dua, Mohit Thapar Institute of Engineering and Technology Computer Science and Engineering Department Patiala India National Institute of Technology Department of Computer Engineering Haryana Kurukshetra India

ISBN: (纸本)9798350388534

Voice biometric authentication has gained significant attention in recent years due to its non-intrusive and user-friendly nature. In this research paper, we present a comprehensive study on the effectiveness of three different spectrograms - Constant Q Transform (CQT), Mel and Gammatone at the front end of an Audio Spoof Detection (ASD) system. The back end of the system employs the Xception pretrained model. Our experimental results reveal that Gammatone Spectrograms outperform both CQT Spectrograms and Mel Spectrograms in terms of performance. Specifically, combination of Gammatone Spectrogram with Xception pretrained has achieved a remarkable 3.5% and 2% Equal Error Rate (EER) for ASVspoof 2021 DF and DECRO dataset, respectively © 2024 IEEE.

关键词： Spectrographs

来源：评论

学校读者我要写书评

暂无评论

Bald Eagle Search Algorithm with Hierarchical Deep Learning for Internet of Things Assisted Sleep Quality Recognition

引用

SN computer science 2024年第5期5卷 1-10页

作者： Duhayyim, Mesfer Al Sharif, Mahir Mohammed Munjal, Muskaan Hilal, Anwer A. Department of Computer Science College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz University Al-Kharj 16273 Saudi Arabia Department of Computer Science Faculty of Computer Science and Information Technology Omdurman Islamic University Omdurman Sudan Computer Engineering Thapar Institute of Engineering and Technology Punjab Patiala India Department of Information System Faculty of Computer Science and Information Technology Omdurman Islamic University Omdurman Sudan

Sleep quality prediction in Internet of Things (IoT) involves leveraging a system of interrelated devices to gather as well as analyse related data. Smart devices like wearable devices or smart mattresses endlessly monitor many parameters such as body movement, heart rate, and environmental situations in bedroom. Real-time recommendations and feedback transported to consumers, allowing them to create informed lifestyle changes for superior sleep hygiene. As IoT ecosystem continues to develop, a combination of various data streams as well as classy analytics holds assurance for further refining sleep quality forecasts and improving overall well-being. The article designs a Bald Eagle Search Algorithm with Hierarchical Deep Learning for Internet of Things Assisted Sleep Quality Recognition (BESHDL-SQP) technique. The purpose of the BESHDL-SQP technique is to recognize and classify the quality of the sleep level in the IoT environment. In the presented BESHDL-SQP technique, the preliminary stage of data pre-processing using min–max normalization involved to normalize the input data. For predicting sleep quality, hierarchical long short-term memory (LSTM) technique exploited. Lastly, BES model utilized for optimal hyperparameter selection of LSTM method which helps in attaining enhanced results. To validate better performance of BESHDL-SQP technique, a huge range of simulation analysis is carried out. The extensive results stated that the BESHDL-SQP technique exhibits supreme performance over other models. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Bald eagle search Internet of things LSTM Sleep quality recognition Smart devices

来源：评论

学校读者我要写书评

暂无评论

Alzheimer's Disease Prediction using an Artificial Butterfly Optimizer with a Two-Layer CNN Approach 4

Alzheimer's Disease Prediction using an Artificial Butterfly...

引用

4th IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2024

作者： Jevin, J.A. Umamageswari, A. Srm Institute of Science & Technology Department of Computer Science & Engineering Chennai India

ISBN: (纸本)9798350352931

Alzheimer's disease, the most common dementia, involves brain damage. Alzheimer's starts with mild symptoms and worsens over time, making it difficult to treat. Early detection can prevent disease progression or reduce symptoms before major impairment. This study uses multiple stages to detect Alzheimer's early. Model training, feature selection, and thorough data preprocessing are system essentials. Data scaling, missing value imputation, and outlier treatment prepared the clinical dataset. Information gain, correlation coefficient, and chi-square were used to choose Alzheimer's disease predictors. The model was trained on hundreds of clinical samples. The ABO-2layer CNN architecture achieved a maximum prediction accuracy of 94.56%, indicating that preprocessing and feature selection improve model performance. The high anticipated accuracy showed the significance of Alzheimer's disease early detection methods. This study improves feature selection and uses advanced CNN architectures to create tools that may help diagnose Alzheimer's early, one way to battle neurodegenerative diseases. © 2024 IEEE.

关键词： Convolutional neural networks

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：