检索结果-内蒙古大学图书馆

4th International Conference on Signal Processing and Communication, ICSPC 2023

作者： Abraham, Bibiya Susan Bhanu, Dalaali Gousiya Thomas, Anna Anitha, J. Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore India

ISBN: (纸本)9798350300772

Glaucoma is a retinal condition that harms the eye as a result of High Intraocular Pressure (IOP). Untreated glaucoma damages the Optic Nerve Head (ONH), which results in visual loss. This issue can be resolved by automating the glaucoma diagnosis so that it can be identified at an early stage and minimize damage to the patient's eyes by offering the right treatment early on. Detecting the advancement of glaucoma manually is a laborious and time-consuming process. HOG and GLCM features are utilized in this study to extract features, which are then passed on to machine learning classifiers including SVM, MLP, and Random Forest to evaluate the classification accuracy. Deep learning approaches like CNN, and pre-trained models such as Xception and EfficientNet are also implemented for automatic feature extraction and classification to categorize the image as glaucoma or normal. The results of the analysis indicate that the deep learning models outperform machine learning classifiers in the diagnosis of glaucoma using the DRISHTI-GS dataset with EfficientNet producing the highest accuracy of 99.72%. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Harris Hawk Optimization-Based Distributed Denial of Service Attack Detection in IoT Networks 4

Harris Hawk Optimization-Based Distributed Denial of Service...

引用

4th International Conference for Emerging technology, INCET 2023

作者： Chaudhari, Shilpa S Yamini, D A Deepthi Ramaiah Institute of Technology Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350335750

As Internet of Things (IoT) grows in popularity, cyber risks and distributed denial of service (DDoS) attacks have increased. DDoS attacks shut down genuine users by flooding a targeted network or service with a large volume of traffic from several hacked computers. DDoS attack can cause significant harm to a network and its users. By gathering benchmark network traffic statistics that come within the Bigdata category, the proposed method assesses and categories these attacks to detect DDoS network activities. DDoS Insights and trends that might not be immediately visible from the table are discovered and understood using an exploratory data analysis technique named Harris Hawk Optimization (HHO). The minimum fitness value based optimal fitness function helps to achieve optimal detection result is effectively. Using benchmark/NS3 DDoS data, the proposed technique is assessed and found to be successful in detecting attack features and offering defense-related knowledge. By providing more accurate and consistent detection and prevention of DDoS attacks, this technology will play a significant role in enhancing security for IoT networks. © 2023 IEEE.

关键词： Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

Machine Learning and Deep Learning Algorithms for Network Data Analytics Function in 5G Cellular Networks 6

Machine Learning and Deep Learning Algorithms for Network Da...

引用

6th International Conference on Inventive Computation Technologies, ICICT 2023

作者： Pavani, Ale Kathirvel, A. Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore India

ISBN: (纸本)9798350398496

Machine learning and deep learning algorithms have the potential to revolutionize network data analytics in 5G cellular networks. With the increase in the number of connected devices and the explosion of data generated by these devices, traditional methods of network data analytics are becoming increasingly inadequate. However, this function faces several challenges, including managing massive amounts of data, processing data in real-time, addressing privacy concerns, integrating with other network systems, and requiring skilled professionals. Overcoming these challenges will enable the network data analytics function to achieve its objectives and improve the overall performance and reliability of 5G cellular networks. Machine learning and deep learning algorithms enable the automatic identification of patterns and insights in large volumes of data, thereby facilitating real-time decision-making and proactive network management. These algorithms can be used for a wide range of network data analytics functions, including network optimization, anomaly detection, prediction of network failures, and dynamic spectrum management. Deep learning algorithms have shown significant promise in processing unstructured network data such as network logs, video, and images. As the 5G network continues to grow and evolve, the use of machine learning and deep learning algorithms in network data analytics is likely to become increasingly essential for ensuring network efficiency, reliability, and security. © 2023 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Travelling Guidance Using ACO and HBMO Techniques in COVID-19 Pandemics: A Novel Approach 7th

Travelling Guidance Using ACO and HBMO Techniques in COVID-1...

引用

7th International Conference on Emerging Applications of Information technology, EAIT 2022

作者： Saket, Shashwat Mishra, Shivam P. Bhattacharjee, Vandana Mishra, Kamta Nath Department of Computer Science and Engineering Birla Institute of Technology Jharkhand India

ISBN: (纸本)9789811951909

The dynamic implementation of meta-heuristic and evolutionary algorithms has transformed computational intelligence’s panoramic view. Considering the applicability of Nature-Inspired Algorithms in the view of the COVID-19 pandemic, the authors implemented the Honeybee Mating Optimization (HBMO), and Ant Colony Optimization (ACO) for efficiently travelling from different cities in vulnerability zone areas. The pheromone matrix and cost matrix were formulated using the HBMO algorithm and fed the aftermaths to map into the Ant Colony Optimization algorithm. The higher COVID-19 regions are denoted with less pheromone level, and the paths with a lower risk of getting infected comprise higher pheromone levels and vice versa. The authors featured the travel guide mapping of several cities of India and calculated the travelling probabilities for ensuring risk-free journeys. The four different threshold criteria maintained for the travelling probabilities are extremely safe conditions, moderately safe conditions, just safe conditions, and not safe conditions. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Viruses

来源：评论

学校读者我要写书评

暂无评论

A Communication System for the Incapacitated using Eye Blinks 9

A Communication System for the Incapacitated using Eye Blink...

引用

9th International Conference on Smart Computing and Communications, ICSCC 2023

作者： Nalini, N. Harshil Reddy, K.H. Tadkal, Dhruv R. Singh, Aditi Nitte Meenakshi Institute of Technology Computer Science & Engineering Bangalore India

ISBN: (纸本)9798350314090

In today's society, many differently abled people, especially ones with completely impaired movement, depend on others for their daily activities. Although their movement is restricted they are certainly capable of high thought. If only this ability was tapped, they will finally have a means to communicate and even end up doing more than ones who are not differently abled. The only major challenge being that the provision of a device that is of low cost, is affordable and interprets a person's choice accurately. Although techniques such as electroencephalography (EEG) signals for blink detection can be an effective solution for detecting brain activity and eye movement, and translating their choices, EEG-based devices can cause seizures. Instead, a person's series of eye blinks can be detected and converted into a meaningful sentence. By providing a predefined look up table with meaning sentences corresponding to various blink patterns, the blinks can act as a bridge and thus help the person not only communicate but also extend the application to control a variety of things such as the wheelchair, home appliances, etc without depending on others. © 2023 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Approach to Support the Detection of Autism Spectrum Disorder(ASD) through Machine Learning and Deep Learning Techniques 12

A Hybrid Approach to Support the Detection of Autism Spectru...

引用

12th IEEE International Conference on Advanced Computing, ICoAC 2023

作者： Manoj, Meghna Praveen, Joe I R Vellore Institute of Technology School of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350318210

Autism spectrum disorder is a significant contributor to developmental disabilities worldwide, and its estimated prevalence in India is more than 2 million people. Research has emphasized that early detection and treatment can help to improve a person with autism's level of language, communication, and overall well-being. The main objective is to automate the diagnosis process, compare and identify the best classifiers, and find out the most significant traits for supporting detection. We attempted to investigate the use of Logistic Regression, Decision Tree, Naive Bayes, Random Forest, Support Vector Machine, Linear Discriminant Analysis, K-Nearest Neighbors, XGBoost Classifier, Multi-Layer Perceptron for predicting if the person is susceptible to ASD. For the analysis, ASD data for toddlers, children, adolescents, and adults were employed, and the best classifier techniques were determined using measures like recall, precision, F-measures, etc. Feature engineering was performed to identify the most impactful and effective features of the datasets. We identified that LR and MLP models provide the best results in adult and toddler datasets. In case of adolescent data, LR classifier showed the highest performance whereas LR and XGBoost algorithms worked well for child dataset. The results obtained justify that ML and DL techniques showed promise in developing an improved system for supporting the detection of Autism. © 2023 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Developing Lexicons for Enhanced Sentiment Analysis in Software engineering:An Innovative Multilingual Approach for Social Media Reviews

引用

computers, Materials & Continua 2024年第5期79卷 2771-2793页

作者： Zohaib Ahmad Khan Yuanqing Xia Ahmed Khan Muhammad Sadiq Mahmood Alam Fuad AAwwad Emad A.A.Ismail School of Automation Beijing Institute of TechnologyBeijing100081China Department of Computer Science and Technology University of Science and Technology BannuKPKBannu28100Pakistan School of Computer Science and Engineering Central South UniversityChangsha410083China Department of Quantitative Analysis College of Business AdministrationKing Saud UniversityP.O.Box 71115Riyadh11587Saudi Arabia

Sentiment analysis is becoming increasingly important in today’s digital age, with social media being a significantsource of user-generated content. The development of sentiment lexicons that can support languages other thanEnglish is a challenging task, especially for analyzing sentiment analysis in social media reviews. Most existingsentiment analysis systems focus on English, leaving a significant research gap in other languages due to limitedresources and tools. This research aims to address this gap by building a sentiment lexicon for local languages,which is then used with a machine learning algorithm for efficient sentiment analysis. In the first step, a lexiconis developed that includes five languages: Urdu, Roman Urdu, Pashto, Roman Pashto, and English. The sentimentscores from SentiWordNet are associated with each word in the lexicon to produce an effective sentiment score. Inthe second step, a naive Bayesian algorithm is applied to the developed lexicon for efficient sentiment analysis ofRoman Pashto. Both the sentiment lexicon and sentiment analysis steps were evaluated using information retrievalmetrics, with an accuracy score of 0.89 for the sentiment lexicon and 0.83 for the sentiment analysis. The resultsshowcase the potential for improving software engineering tasks related to user feedback analysis and productdevelopment.

关键词： Emotional assessment regional dialects SentiWordNet naive bayesian technique lexicons software engineering user feedback

来源：评论

学校读者我要写书评

暂无评论

Cyber-Physical Security System in Smart Grid-A Review 14

Cyber-Physical Security System in Smart Grid-A Review

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Akshatha, Y. Poornima, A.S. Siddaganga Institute of Technology Department of Computer Science and Engineering Tumakuru India

ISBN: (纸本)9798350335095

The Smart Grid System (SGS) is a smart technology that is a combination of advanced technology and physical aspects that facilitates bidirectional communication of information exchange, power generation, and power distribution. The communication technology development in traditional power systems is by deploying cyber-physical systems in smart grid. SGS has a compound architecture consisting of several critical devices and infrastructure of the Internet of Things (IoT). The deployment of the devices is vulnerable to many cyber-attacks. Hence, it is required to do much research to secure the devices from attacks and environmental damage. So, this paper comprehensively reviews cyber-physical, cyber-security, and key components of cyber-attacks. Then we present each section in detail and thoroughly the standards and principles of cyber-physical and cyber-security attacks in smart grid systems. This paper gives a deep understanding of cyber-security systems in smart grid system applications. © 2023 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

A review of recommendation systems based on the fusion of new technologies 8

A review of recommendation systems based on the fusion of ne...

引用

8th International Conference on Intelligent Informatics and Biomedical sciences, ICIIBMS 2023

作者： Gao, Meizhu Yu, Wanjun Shanghai Institute of Technology Computer Science and Information Engineering Shanghai China

ISBN: (纸本)9798350369564

The huge amount of data has grown exponentially with the development of Internet technology, and we have thus entered the era of information explosion. It is very difficult to get the target information that users are interested in or need in the huge amount of data. To solve the problem of information overload, recommendation systems play an important role. At present, recommendation systems have become a popular research area and have received a lot of attention with many application areas. However, recommendation systems suffer from the problems of cold start, data sparsity and poor interpretability, and many researches have been conducted to alleviate these problems. In this paper, we first give a brief overview of recommendation systems and traditional recommendation algorithms, then summarize the improvements made by recommendation systems with the introduction of auxiliary information, and finally summarize the challenges faced by recommendation systems and give the future development hotspots. © 2023 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Genetic-Chicken Swarm Algorithm for Minimizing Energy in Wireless Sensor Network

引用

computer Systems science & engineering 2023年第2期44卷 1451-1466页

作者： A.Jameer Basha S.Aswini S.Aarthini Yunyoung Nam Mohamed Abouhawwash Department of Computer Science and Engineering Hindusthan Institute of TechnologyCoimbatore641032India Department of Computer Science and Engineering Soonchunhyang UniversityAsan31538Korea Department of Mathematics Faculty of ScienceMansoura UniversityMansoura35516Egypt Department of ComputationalMathematics Science and Engineering(CMSE) Michigan State University East LansingMI48824USA.

Wireless Sensor Network(WSN)technology is the real-time applica-tion that is growing rapidly as the result of smart *** power is one of the most signiﬁcant resources in *** enhancing a power factor,the clustering techniques are *** the forward of data in WSN,more power is *** the existing system,it works with Load Balanced Cluster-ing Method(LBCM)and provides the lifespan of the network with scalability and *** the existing system,it does not deal with end-to-end delay and deliv-ery of *** overcoming these issues in WSN,the proposed Genetic Algo-rithm based on Chicken Swarm Optimization(GA-CSO)with Load Balanced Clustering Method(LBCM)is *** Algorithm generates chromosomes in an arbitrary method then the chromosomes values are calculated using Fitness *** Swarm Optimization(CSO)helps to solve the complex opti-mization ***,it consists of chickens,hens,and *** divides the chicken into *** Balanced Clustering Method(LBCM)maintains the energy during communication among the sensor nodes and also it balances the load in the *** proposed GA-CSO with LBCM improves the life-span of the ***,it minimizes the energy consumption and also bal-ances the load over the *** proposed method outperforms by using the following metrics such as energy efﬁciency,ratio of packet delivery,throughput of the network,lifetime of the sensor ***,the evaluation result shows the energy efﬁciency that has achieved 83.56%and the delivery ratio of the packet has reached 99.12%.Also,it has attained linear standard deviation and reduced the end-to-end delay as 97.32 ms.

关键词： Energy efﬁciency sensor nodes chicken swarm optimization load balanced clustering method wireless sensor network cluster heads load-balancing ﬁtness function

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：