检索结果-内蒙古大学图书馆

communication, Control and Intelligent systems (CCIS)

作者： V. Anandi Ramesh Muthuswamy A Pranav Dept. Of Electronics and Communication Ramaiah Institute of Technology Bengaluru India School of Management Presidency University Bengaluru India Dept. Of Computer Science Engineering VIT Chennai Campus Chennai India

ISBN: (数字)9798331528201

ISBN: (纸本)9798331528218

The paper deals with switched capacitor-based designs for power-efficient rechargeable hearing aids. Switched-capacitor DC-DC power converters are a subset of DC-DC power converters that use only switches and capacitors to convert one voltage to another efficiently. By using switched-capacitor circuits, the aim is to increase the efficiency of hearing aids. To achieve long battery life, a high conversion efficiency is required. At the same time, the physical size should be low as it is desirable for the end-user to have small hearing aids. The voltage levels thus have to be stepped down from the voltage provided by a Li-ion (rechargeable) to levels closer to that of Zn-Air (non-rechargeable).

关键词： Capacitors Switches DC-DC power converters Hearing aids Control systems Switched capacitor circuits Topology Batteries Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Interactive RF Game Design for Deciphering Real-World Human Motion: Activities, Gestures, and Sign Language

Interactive RF Game Design for Deciphering Real-World Human ...

引用

IEEE National Conference on Radar

作者： Sevgi Z. Gurbuz Chris Crawford Darrin J. Griffin Emre Kurtoglu Oladipupo Adeoluwa Josh Haeker Dept. of Electrical and Computer Engineering The University of Alabama Tuscaloosa AL USA Dept. of Computer Science The University of Alabama Tuscaloosa AL USA Dept. of Communication Studies The University of Alabama Tuscaloosa AL USA

Current methods for acquiring datasets for human motion classification are limited to controlled settings where participants are directed by a human experiment organizer. Datasets acquired in controlled settings often cannot capture natural human behaviors and are inadequate for obtaining large amounts of real-world data in a sustainable fashion. This paper proposes a new paradigm for automated acquisition of natural human movements based on Interactive RF Gaming. The training of AI/ML models is considered over an evolution of time: pre-deployment via physics-aware batch training and post-deployment via continual learning from interactions. Algorithms needed to address real-world considerations such as the parsing of continuous streams of data, computational constraints, real-time processing, and game design considerations based on cyber-physical human system requirements are also discussed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning and Sentiment Analysis Improve E-commerce Sales Prediction

Deep Learning and Sentiment Analysis Improve E-commerce Sale...

引用

2023 International Conference on Data Science and Network Security, ICDSNS 2023

作者： Geetha, K. Swarnalatha, K. Ananda Babu, J. Sudha, Poranki V. L. R. N. Sai Ramachandra, A.C. Gst Gitam University Bengaluru Campus Dept. of Cse Bengaluru India Thandavapura Mysore Dept of Ai and Ds Mit India Malnad College of Engineering Hassan Department of Information Science and Engineering India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Andhra Pradesh India Nitte Meenakshi Institute of Technology Bengaluru Department of Electronics and Communication Engineering India

ISBN: (纸本)9798350301595

The dataset labelled 'Amazon and Yelp Reviews' is a useful resource for sentiment analysis and opinion mining. It has roughly 1.5 million reviews from Amazon and Yelp for a wide range of products and services, as well as the relevant information for each review, which includes product ratings, review dates, and review titles. The dataset's size and diversity make it a good choice for training large-scale deep learning models to handle sentiment analysis tasks. The recommended approach for undertaking sentiment analysis using the 'Amazon and Yelp Reviews' dataset includes three steps: collecting data on a daily basis, preparing user comments, and applying a BiLSTM model for sentiment analysis. Assessing consumer sentiment entails evaluating comments, goods, and businesses to develop predictions about how people feel about various products and services. Some of the measures used in the model evaluation process include accuracy, precision, recall, and F1-score. The proposed method achieves an average accuracy of 87.3%, which is comparable to existing deep learning methods such as character-level convolutional neural networks (CNNs)- LSTM and deep transfer learning. The model's errors may be evaluated to discover where it can be improved, and additional assessment metrics such as AUC- ROC, AUC-PR, G-mean, and MCC can be used to determine how well the model is doing. The dataset and methods presented have the potential to be useful for a wide range of applications, including customer feedback analysis, product and service development, and online reputation management. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Detection of Brain Tumor using Convolution Neural Network through Detection of Metastasis

Detection of Brain Tumor using Convolution Neural Network th...

引用

Devices for Integrated Circuit (DevIC)

作者： Soumen Santra Suman Sardar Swarnadeep Sil Rudra Sarkar Arpan Deyasi Dept. of Computer Application Techno International New Town Kolkata India Dept. of Electronic Science Acharya Prafulla Chandra College New Barrackpore India Dept. of Electronics and Communication Engineering RCC Institute of Information Technology Kolkata India

ISBN: (数字)9798350391107

ISBN: (纸本)9798350391114

A novel model using convolution neural network has been developed for near accurate detection of brain tumor by carefully preprocessing the data and addressing class imbalance. Dataset was gathered between December 2017 and March 2018, consists of 7,001 JPG MRI pictures, 3,800 of which show a healthy brain, and 3,201 of which show a brain with tumors; results 94.14% accuracy in training, 94.33% accuracy in testing and 95.12% accuracy in validation. Insignificant losses are reported in all the cases, speaks in favor of quality of segregation between pathological and normal tissues. Present study provides 92.39% sensitivity, 96.63% specificity and 97.03% precision which clearly outperforms peer-reviewed works carried out using CNN; and therefore, justifies novelty of the work.

关键词： Training Pathology Accuracy Sensitivity Convolution Neural networks Brain tumors Brain modeling Integrated circuit modeling Testing

来源：评论

学校读者我要写书评

暂无评论

Health Care Data Mining using Intelligent Classification Techniques

Health Care Data Mining using Intelligent Classification Tec...

引用

Advances in Computing, communication Control and Networking (ICAC3N), International Conference on

作者： Jyoti Antil Rahul Rishi Sonia Sharma Rajkumar Yadav Dept. of Computer Science Engineering University Institute of Engineering and Technology MDU Rohtak Hrayana India Dept. of Electronic and Communication Engineering University Institute of Engineering and Technology MDU Rohtak Hrayana India

ISBN: (数字)9798350330861

ISBN: (纸本)9798350330878

Classification models can be learned from complicated multivariate temporal data and this is a topic we investigate in electronic health record systems. The difficulty is to come up with a collection of attributes that accurately reflect the data’s temporal nature. Using temporal abstractions and pattern mining, we extract the classification features from the data. There are frequently a lot of temporal patterns that aren’t related to the classification job that are returned by temporal pattern mining.

关键词： Decision making Feature extraction Data models Complexity theory Data mining Medical diagnosis Electronic medical records

来源：评论

学校读者我要写书评

暂无评论

Automation of black tea oxidation process leveraging Internet of Things in Rwanda: Case of Rwanda Mountain Tea Factory Limited

Automation of black tea oxidation process leveraging Interne...

引用

Artificial Intelligence and Internet of Things (GCAIoT), IEEE Global Conference

作者： Abraham Natukunda Kwasi K. Adomako Dept. of Information and Communication Technology Carnegie Mellon University Pittsburgh USA Dept. of Electrical and Computer Engineering Carnegie Mellon University Pittsburgh USA

Black tea production at Rwanda Mountain Tea Factory relies on human sensory analysis to determine optimum oxidation levels to produce customer-desired tea-grade quality. This process is subject to errors of omission resulting from unpredictable human insensitivity and variability due to individualistic differentiations leading to inconsistency in produced tea quality. As a result, market prices fluctuate and thus unpredictable returns. This research has developed an Internet of Things (IoT) approach to supplement this process. This is accomplished by using low-power end-node sensor devices assembled to form an electronic nose (e-nose) comprising different gas, temperature and humidity sensors to detect variations in reactive components until pre-set optimum oxidation mean levels are realized. Data from the sensors is sent through a wireless gateway and transmitted to a database. A web-based visualization platform has been built to relay sensor data with the ability to provide real-time monitoring of considered reactive elements and compounds during the tea oxidation period. This ensures that there is monitoring, traceability, prediction, and actuation upon attainment of desired set values. This control results in improved consistency of black tea quality production which allows tea processors to earn predictable and consistent revenues from each bushel of tea harvested.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring Deep Learning Architectures for RF Signal Classification

Exploring Deep Learning Architectures for RF Signal Classifi...

引用

International Conference on Radioelektronika

作者： Ladislav Polak Samuel Turak Roman Sotner Jan Kufa Roman Marsalek Arvind Dhaka Department of Radio Electronics Brno University of Technology FEEC Brno Czech Republic Dept. of Computer and Communication Engineering Manipal University Jaipur Rajasthan India

ISBN: (数字)9798331544478

ISBN: (纸本)9798331544485

Future 6G radio networks will heavily rely on deep learning (DL) models for both signal and data processing. DL-based solutions can be highly effective in classifying various radio frequency (RF) signals influenced by noise or intentional jamming as they are capable of recognizing patterns even under challenging conditions. This paper focuses on the classification of different RF signals using three DL-based models: CNN, GRU, and CGDNN. For this purpose, a dataset containing RF signals influenced by various impairments (e.g., I/Q-imbalance) and transmission conditions (e.g., multipath propagation) was created using MATLAB. Both the dataset and the source code have been made publicly available to support further research in this area. Preliminary results shown that the performance of DL-based approaches depends not only on the RF impairments considered but also on the preparation of the dataset.

关键词： Radio frequency Deep learning Source coding RF signals Noise Neural networks Rician channels Rayleigh channels Radio networks Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

A Miniaturized Monopole Antenna with Embedded Rectangular Notch for UWB Usage

A Miniaturized Monopole Antenna with Embedded Rectangular No...

引用

2022 IEEE Symposium on Industrial Electronics and Applications, ISIEA 2022

作者： Owusu, Joseph Aniewu, Lilian-Gloria Kyeremeh, Kwabena Amoako Loung, Vincent Yong Kai Owusu, Stephen Twenewaa, Melody University of Energy and Natural Resources Computer & Electrical Eng. Dept. Sunyani Ghana Universiti Teknologi Malaysia Wireless Communication Centre Faculty of Electrical Engineering Johor Malaysia

ISBN: (数字)9781665480123

ISBN: (纸本)9781665480123

Ultra-wideband applications have been an important part of wireless communication due to their low power consumption and high data rate. A small monopole antenna for ultra-wideband application is introduced and examined in this paper. The antenna comprises a rectangular patch with lower right angle edges cut for lower length high-frequency resonance. The Rogers RT/Duroid 5880 with an Er of 2.2 was employed as the substrate material. A partial ground plane configuration is used to ensure that the bandwidth of the antenna operation can be improved, and the quality factor reduced to increase back lobe radiation. The final dimensions attained after optimization is a low profile of 27 mm x 32 mm x 0.80 mm including the feeding mechanism. The monopole antenna has a low cost, high impedance bandwidth of 3.58 to 15.10 GHz at 10 dB return loss. The Antenna exhibits multiband characteristics at 20 dB return loss of 4.0 GHz to 5.5 GHz and 10.0 GHz to 11.0 GHz. The antenna achieved a VSWR of less than 2 in the operating frequency band, making the antenna very capable of wireless transmission. The proposed antenna will do well in ultra-wideband operations such as WLAN, WiMAX, and Wi-Fi. Furthermore, its low gain and wide-angle coverage makes it a good fit for urban centers, mobile devices, certain wearable technologies, and aircraft services that find their relevance in the UWB frequency spectrum. © 2022 IEEE.

关键词： Monopole antennas

来源：评论

学校读者我要写书评

暂无评论

Real-Time Mobile Crowd Sensing Model for Remote Detection of Flying Uavs

SSRN

引用

SSRN 2024年

作者： Ahmed, Ashfaq Alkadi, Ruba Belwafi, Kais Shoufan, Abdulhadi Dept. of Computer & Communication Engineering Khalifa University Abu Dhabi127788 United Arab Emirates Dept. of Computer Engineering College of Computing & Informatics University of Sharjah Sharjah United Arab Emirates Khalifa University Abu Dhabi127788 United Arab Emirates

Conformance monitoring is crucial for ensuring the safe operation of unmanned aerial vehicles (UAVs). It aims to alert relevant parties to any deviations from authorized flight plans. The European Union Aviation Safety Agency mandates conformance monitoring and suggests integrating it into UAV traffic management (UTM) systems. Although traditional monitoring systems, such as wireless sensor networks, can serve this purpose, the associated expenses for installation and maintenance make them impractical for large-scale implementations. To tackle this challenge, we propose a monitoring system that capitalizes on UAV remote identification technology and mobile crowd sensing. Remote identification (RID) is becoming a global regulatory requirement. It enables ground observers to identify drones using standard mobile devices. Our solution collects RID data by gathering reports from these observers to assess UAV operations in real-time. A significant component of this approach is determining the optimal number of reports that should be considered to allow reliable and quick evaluation. While processing more reports can enhance the evaluation accuracy, it increases the computational demands and may compromise the system’s real-time performance. Moreover, in a reward-based system, processing more reports incurs higher costs. Therefore, our system uses a mechanism that adjusts the number of received and processed reports based on airspace conditions and the crowd density in the area of interest. We validated the proposed model through Monte Carlo simulations. Results indicate that, compared to a naive model, our approach outperforms in terms of received RIDs, paid rewards, and real-time performance. © 2024, The Authors. All rights reserved.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Explainable AI for Enhanced Intrusion Detection systems

Explainable AI for Enhanced Intrusion Detection Systems

引用

Advancement in Technology (ICONAT), International Conference for

作者： G Ananya N Siri Ashwini Kodipalli Trupthi Rao Dept. of Computer Science and Engineering Global Academy of Technology Bengaluru Karnataka India Dept. of Electronic and Communication Engineering Global Academy of Technology Bengaluru Karnataka India Dept. of Artificial Intelligence & Data Science Global Academy of Technology Bengaluru Karnataka India

ISBN: (数字)9798350354171

ISBN: (纸本)9798350354188

As everything is turning digital there is a hike in the invasion of digital space, because of which advanced tools are needed. One such tool is the Intrusion Detection system (IDS). In this work, we have tried to detect and classify suspicious connections accurately. This is done by incorporating advanced computing into Intrusion Detection systems. To achieve this, we have used the Coburg Intrusion Detection Dataset. To achieve this, we used the Coburg intrusion detection dataset. We investigate the effectiveness of Single Classifiers and Bagging and Boosting in this context. We proposed a four-stage Ensemble model to classify the connections using its attributes. The proposed model uses four Single Classification models: Logistic Regression, KNN, Decision Tree, and SVM. Before applying the algorithms, the data was Preprocessed. Later, the models were hyper-tuned to increase the accuracy. The results showed that Random Forest outperforms other single classifiers and machine learning algorithms, with a mean accuracy of $\mathbf{9 9. 9 9 \%}$, a precision of $\mathbf{9 9. 9 9 \%}$, and an F1-score of $\mathbf{9 9. 9 9 \%}$. Furthermore, as models are usually hard to understand by using Explainable AI we can increase the transparency of the model. Explainable AI techniques are used to make the advanced computing models reliable and more understandable. This study aims to develop advanced and dependable intrusion detection systems

关键词： Support vector machines Machine learning algorithms Accuracy Explainable AI Computational modeling Intrusion detection Nearest neighbor methods Turning Reliability Random forests

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：