检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Communications, information, Electronic and Energy systems, CIEES 2023

作者： Mimenbayeva, Aigul Omirtay, Maylen Niyazova, Rozamgul Bekmagambetova, Gulmira Suleimenova, Raya Tursumbayeva, Ainur Astana It University Dept. of Computational and Data Sciences Astana Kazakhstan Astana It University Specialty Smart Technologies Astana Kazakhstan L. Gumilyov Eurasian National University Dept. of Artificial Intelligence Technologies Astana Kazakhstan S. Seifullin Kazakh Agrotechnical Research University Dept. of Computer Science Astana Kazakhstan Eurasian Technological University School of Engineering and Information Technology Almaty Kazakhstan S. Seifullin Kazakh Agrotechnical Research University Dept. of Information Systems Astana Kazakhstan

ISBN: (纸本)9798350336917

The paper analyzes and predicts the yield of grain crops of LLP 'North-Kazakhstan Agricultural Experimental Station' for the last 30 years. The class of artificial neural networks-multilayer perceptron (MLP) was used as a research tool. The process of training of a model of a neural network consisting of 30 networks was performed on the basis of 70% training and 30% control samples. Based on the analysis of residuals histogram and scatter plot of the target and output function, the best neural network models MLP-1-7-1 (p=0.92), MLP-1-8-1 (p=0.97), MLP-1-5-1 (p=0.82) were selected. Next, using the best MLP 1-8-1 network, the model was tested the given data. Using time series projection, a graph was illustrated and a table of predicted grain yield values for the coming years was tabulated. The absolute error showed the high accuracy of the obtained best MLP 1-8-1 network for forecasting the amount of grain crop yield. The obtained model of artificial network can be applied in research and monitoring of agricultural production development. © 2023 IEEE.

关键词： Multilayer neural networks

来源：评论

学校读者我要写书评

暂无评论

"MealShare: Using Blockchain Technology and a Reward-Based System to Combat Global Food Waste"

TechRxiv

引用

TechRxiv 2023年

作者： Kumara, H.A.P. manjula Jayakodi, J.K.R.P. Gamage, I.D. Wickramasinghe, R.G.M.N. De Zoysa, R.R.P. De Sliva, D.I. Dept. of Information Technology Sri Lanka Institute of Information Technology Malabe Sri Lanka Dept. of Computer Science and Software Engineering Sri Lanka Institute of Information Technology New Kandy RD Malabe Sri Lanka

"MealShare" is an upcoming internet application that aims to reduce food waste and promote sustainable dietary habits while supporting a more sustainable global food system. It uses blockchain technology and a rewards-based system to incentivize companies to donate their excess food. This innovative approach ensures transparency, traceability, security, and decentralization throughout the entire food donation process. The use of blockchain technology enables the monitoring and recording of each contribution of surplus food, providing an immutable record of the entire supply chain, increasing accountability, and reducing the possibility of food waste due to negligence or mismanagement. Furthermore, "MealShare" uses blockchain smart contracts to automate verification and identification, speeding up the processing of food donations while saving money. The automatic and open incentive structure offered by smart contracts encourages companies to take part in the food donation program and make frequent contributions, compensating them based on specified criteria such as the quantity or quality of leftover food supplied. This unique approach makes use of blockchain technology and a rewards-based system to promote sustainable food practices, reduce food waste, and motivate companies to donate extra food. It is a potential tool in the worldwide effort to reduce food waste due to its openness, traceability, security, and automated incentive structure. © 2023, CC BY.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Learning-Based Rich Feedback HARQ for Energy-Efficient Uplink Short Packet Transmission

arXiv

引用

arXiv 2023年

作者： Vejling, Martin V. Chiariotti, Federico Kalør, Anders E. Gündüz, Deniz Liva, Gianluigi Popovski, Petar Dept. of Electronic Systems Aalborg University Denmark Dept. of Information Engineering University of Padova Italy Dept. of Information and Computer Science Keio University Japan Dept. of Electrical and Electronic Engineering Imperial College London United Kingdom Wessling Germany

The trade-off between reliability, latency, and energy efficiency is a central problem in communication systems. Advanced hybrid automated repeat request (HARQ) techniques reduce retransmissions required for reliable communication but incur high computational costs. Strict energy constraints apply mainly to devices, while the access point receiving their packets is usually connected to the electrical grid. Therefore, moving the computational complexity from the transmitter to the receiver may provide a way to improve this trade-off. We propose the reinforcement-based adaptive feedback (RAF) scheme, a departure from traditional single-bit feedback HARQ, introducing adaptive rich feedback where the receiver requests the coded retransmission of specific symbols. Simulation results show that RAF achieves a better trade-off between energy efficiency, reliability, and latency, compared to existing HARQ solutions. Our RAF scheme can easily adapt to different modulation schemes and can also generalize to different channel statistics. Copyright © 2023, The Authors. All rights reserved.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Macula Swelling Detection using Retinal Fundus Images

Macula Swelling Detection using Retinal Fundus Images

引用

IEEE International Workshop on Imaging systems and Techniques (IST)

作者： Rukham Mumtaz Khan Fazal Saadat Ali Khan Fauzia Khan Rafia Hassan Dept. of Computer Engineering National University of Sciences and Technology Islamabad Pakistan Dept. of Information Security National University of Sciences and Technology Islamabad Pakistan Dept. of Computer Science University of Tartu Tartu Estonia Dept. of Software Engineering Bahria University Islamabad Pakistan

Diabetic Macular Edema (DME) is an advanced symptom of Diabetic Retinopathy (DR) and can lead to irreversible vision loss. Macular Edema (ME) is the swelling of the macula, the part of the eye accountable for thorough central vision. The utilization of image processing in the detection of diabetic macular edema (DME) plays a crucial role in the field of medical imaging, effectively reducing the time and manual effort required by medical specialists to identify this disease. In this paper, we proposed a method that uses digital fundus images to analyze the swelling of the macula. The proposed algorithm consists of four steps, i.e., (i) retinal image dataset collection, (ii) retinal image pre-processing, (iii) feature extraction, and (iv) classification to categorize the disease into three different stages, i.e., normal, stage 1 (mild) and stage 2 (severe). The proposed method is tested on three databases, i.e., MESSIDOR, DMED, and the local dataset AFIO obtained from the local hospital in Pakistan. We use three parameters to check the validity of the proposed algorithm, i.e., visual inspection, accuracy, and area under calculation time. Our method achieves an average accuracy of 96.07 % with a sensitivity of 93.74 % and specificity of 97.32%. We also compare our results with other proposed methods, which shows our method performs better.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generative Adversarial Networks for Anomaly Detection: A Systematic Literature Review

Generative Adversarial Networks for Anomaly Detection: A Sys...

引用

International Conference on Computing, Mathematics and engineering Technologies (iCoMET)

作者： Shah Noor Sibghat Ullah Bazai Muhammad Imran Ghafoor Shah Marjan Saira Akram Fatima Ali Dept. Computer Science Balochistan University of Information Technology Engineering and Management Sciences (BUITEMS) Quetta Pakistan Dept. of Computer Engineering Balochistan University of Information Technology Engineering and Management Sciences (BUITEMS) Quetta Pakistan Dept. of Electrical Engineering Superior University Pakistan Television Corporation Lahore Pakistan Dept. of Software Engineering Balochistan University of Information Technology Engineering and Management Sciences (BUITEMS) Quetta Pakistan

In numerous research areas, anomaly identification is a major problem. Identifying and properly classifying data as anomalous is a challenging task that is resolved in various manners over the years. Different approaches like traditional, supervised, unsupervised, and semi-supervised are used for anomaly detection. In the literature, various machine learning-based anomaly detection algorithms exist. It is challenging to choose one anomaly detection algorithm from the several available algorithms because each algorithm puts forward its good detection performance. In recent years, generative adversarial networks have shown remarkable results for anomaly classification. This paper aims to represent a systematic literature review of generative adversarial network-based approaches for anomaly detection and highlights their pros.

关键词： Data privacy Machine learning algorithms Systematics Bibliographies Machine learning Generative adversarial networks Mathematics

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning for Predicting Possibility of Bluetooth Low Energy Tag Signals

A Deep Learning for Predicting Possibility of Bluetooth Low ...

引用

International computer Symposium (ICS)

作者： Hao-Pei Teng Vincent S. Tseng Josh Jia-Ching Ying Dept. Management Information Systems National Chung Hsing University Taichung Taiwan Department of Computer Science and Information Engineering National Yang Ming Chiao Tung University Hsinchu City Taiwan

ISBN: (数字)9798331509071

ISBN: (纸本)9798331509088

With the rapid growth of IoT technology, using Bluetooth Low Energy (BLE) gateways to track the trajectory of elderly individuals can help prevent them from getting lost. However, BLE tag signals do not persist, and BLE gateways often enter standby mode for extended periods, resulting in unnecessary energy waste and reducing the lifespan of the devices. To address this issue, predicting the likelihood of BLE tag signals is essential to conserve energy. This paper presents a deep learning approach to enhance the operational efficiency and lifespan of BLE gateways deployed in an IoT system. The system consists of two major modules: the Number of BLE Tags Estimation Module and the Next Accessed BLE Gateway Prediction Module. The Number of BLE Tags Estimation Module leverages a CNN-GRU (Convolutional Neural Network - Gated Recurrent Unit) architecture to predict the time lapse between the sensing of signals from BLE tags. The Next Accessed BLE Gateway Prediction Module employs a self-attention mechanism to predict which specific BLE gateway will receive the BLE tag signal, further optimizing system performance. Experimental results show that the proposed prediction model effectively reduces unnecessary energy consumption, thereby improving the efficiency and service life of the entire IoT system.

关键词： Deep learning Urban areas Estimation Logic gates Transformers Sensors Convolutional neural networks Older adults Bluetooth Low Energy Protection

来源：评论

学校读者我要写书评

暂无评论

Robust Heart Disease Prediction: A Hybrid Approach to Feature Selection and Model Building 4

Robust Heart Disease Prediction: A Hybrid Approach to Featur...

引用

4th International Conference on Ubiquitous Computing and Intelligent information systems, ICUIS 2024

作者： Kodete, Chandra Shikhi Pasupuleti, Vikram Thuraka, Bharadwaj Sangaraju, Varun Varma Tirumanadham, N. S. Koti Mani Kumar Shariff, Vahiduddin School of Technology Eastern Illinois University CharlestonIL61920 United States School of Computer Science and Information Systems Northwest Missouri State University MaryvilleMO64468 United States University of the Cumberlands WilliamsburgKY4076 United States Sir C R Reddy College of Engineering Dept. of Cse Eluru India

ISBN: (纸本)9798331529635

This research work integrates advanced data preparation methods and advanced modelling approaches to offer a complete approach for creating a predictive model for heart disease. Data cleansing starts the procedure in order to fix disparities and manage missing values, thereby guaranteeing the dependability and accuracy of the dataset. By producing synthetic samples for the minority class, the Synthetic Minority Over-sampling Technique (SMOTE) solves class imbalances and improves the accuracy of the model to forecast minority class occurrences. The z-score approach helps to control outliers thereby preventing distortion in the study. Using a hybrid Filter-Recursive Feature Elimination (FRFE) approach-which combines filter and wrapper techniques to find the most pertinent features, therefore lowering multicollinearity and boosting model performance-feature selection is accomplished. Important characteristics found are age, kind of chest discomfort, maximal heart rate attained, ST depression brought on by exercise, and fluoroscopy-induced coloration of several major arteries. Using AdaBoost, an ensemble learning technique combining several weak classifiers to create a strong one, the improved dataset is utilised to develop a predictive model. The resultant model shows great accuracy (93%), precision (93%), recall (94%), and an amazing ROC AUC score (0.98), therefore highlighting its potential use in healthcare environments and heart disease prediction ability. © 2024 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Optimizing Energy and QoS in VANETs through Approximate Computation on Heterogeneous MPSoC

Optimizing Energy and QoS in VANETs through Approximate Comp...

引用

Emerging Smart Technologies and Applications (eSmarTA), International Conference on

作者： Ahmed A. J. Al-Hchaimi Abdul Hadi M. Alaidi Yousif Raad Muhsen Mohammed F. Alomari Nasri Bin Sulaiman Mamika Ujianita Romdhini Dept. of Electromechanical Systems Engineering Southern Technical University Basra Iraq Dept. of Computer Science and Information Technology Universiti Tenaga National Kuala Lumpur Malaysia Dept. of Computer Science Universiti Putra Malaysia Kuala Lumpur Selangor Malaysia Dept. of Electrical and Electronic Engineering Universiti Putra Malaysia Kuala Lumpur Malaysia Dept. of Mathematics University of Mataram Mataram Indonesia

ISBN: (数字)9798350354133

ISBN: (纸本)9798350354140

This paper proposes a new algorithm called Dynamic Optimization of Energy and QoS in VANETs (DOEQ-VANET), designed to maximize the energy efficiency and Quality of Service (QoS) of the Vehicular Ad-hoc Networks (VANETs). Through exploiting the heterogeneity of Multiprocessor System-on-Chip (MPSoC) employing an approximate computation, DOEQ-VANET is capable of dynamically adjusting the computational accuracy for non-critical applications which results in energy conservation without the risk of propagating the misinformation. Task assignment and scheduling are continuously dynamically adjusted as they respond to network fluctuation, vehicle dynamics and energy availability. The simulation result and validation proved the power of the proposed algorithm, which would mark a large advancement toward more green and smart vehicular networks within the field of Intelligent Transport systems (ITS). This algorithm is crucial for improving the sustainability and efficiency of future transportation systems.

关键词： Heuristic algorithms Green products Vehicular ad hoc networks Transportation Quality of service Approximation algorithms Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

A Sentiment Analysis Study of Twitter Users' Reactions to the COVID-19 Vaccine

A Sentiment Analysis Study of Twitter Users' Reactions to th...

引用

International Conference on information and Communication systems (ICICS)

作者： Suboh Alkhushayni Zakaria Alomari Du'a Al-Zaleq Dept. Information Systems Faculty of Information Technology and Computer Science Yarmouk University Irbid Jordan Dept. Computer Science New York Institute of Technology Vancouver BC Canada Dept. Robotics and Artificial Intelligence Engineering Al-Ahliyya Amman University Amman Jordan

This study investigates public attitudes towards the COVID-19 vaccine through Twitter data analysis. Using the Twitter API, tweets were collected, preprocessed, and labeled. Features were extracted using the Bag of Words representation, and sentiment analysis was conducted using Text Blob and Vader. Machine learning and deep learning models were trained and tested, revealing that deep learning models achieved the highest accuracy and F1 score. The research underscores the efficacy of machine learning and deep learning in analyzing COVID-19 vaccine-related tweets, shedding light on factors influencing vaccine resistance. These insights are crucial for pharmaceutical companies and public health officials, enabling them to address barriers to vaccine acceptance and enhance the societal benefits of widespread vaccination, contributing to the pandemic's resolution.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Case Study-Based Approach of Quantum Machine Learning in Cybersecurity: Quantum Support Vector Machine for Malware Classification and Protection

arXiv

引用

arXiv 2023年

作者： Akter, Mst Shapna Shahriar, Hossain Ahamed, Sheikh Iqbal Gupta, Kishor Datta Rahman, Muhammad Mohamed, Atef Rahman, Mohammad Rahman, Akond Wu, Fan Dept. of Computer Science Kennesaw State University Kennesaw United States Dept. of Information Technology Kennesaw State University Kennesaw United States Dept. of Computer Science Marquette University Wisconsin United States Dept. of Computer Science Clark Atlanta University GA United States Dept. of Information Technology Clayton State University Morrow United States Dept. of Information Technology Georgia Southern University Georgia Dept. of Electrical and Computer Engineering Florida International University Florida United States Dept. of Computer Science and Software Engineering Auburn University Auburn United States Dept of Computer Science Tuskegee University Tuskegee United States

Quantum machine learning (QML) is an emerging field of research that leverages quantum computing to improve the classical machine learning approach to solve complex real-world problems. QML has the potential to address cybersecurity-related challenges. Considering the novelty and complex architecture of QML, resources are not yet explicitly available that can pave cybersecurity learners to instill efficient knowledge of this emerging technology. In this research, we design and develop QML-based ten learning modules covering various cybersecurity topics by adopting student centering case-study based learning approach. We apply one subtopic of QML on a cybersecurity topic comprised of pre-lab, lab, and post-lab activities towards providing learners with hands-on QML experiences in solving real-world security problems. In order to engage and motivate students in a learning environment that encourages all students to learn, pre-lab offers a brief introduction to both the QML subtopic and cybersecurity problem. In this paper, we utilize quantum support vector machine (QSVM) for malware classification and protection where we use open source Pennylane QML framework on the drebin215 dataset. We demonstrate our QSVM model and achieve an accuracy of 95% in malware classification and protection. We will develop all the modules and introduce them to the cybersecurity community in the coming days. © 2023, CC BY.

关键词： Support vector machines

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：