检索结果-内蒙古大学图书馆

Smart Data Intelligence (ICSMDI), International Conference on

作者： B.Sankara Babu G.Akshay Reddy D.Kushal Goud K. Naveen K.Sai Tharun Reddy Department of CSE Gokaraju Rangaraju Institute of Engineering & Technology Telangana India

The advancement in wireless communication technology has led to various security challenges in networks. To combat these issues, Network Intrusion Detection Systems (NIDS) are employed to identify attacks. To enhance their accuracy in detecting intruders, various machine learning techniques have been previously used with NIDS. This paper presents a new approach that utilizes machine learning techniques to identify intrusions. The findings of our model indicate that it outperforms other methods, such as Naive Bayes, in terms of accuracy. Our method resulted in a performance time of 1.26 minutes, an accuracy rate of 97.38%, and an error rate of 0.25%.

关键词： Wireless communication Support vector machines Measurement Runtime machine learning algorithms Error analysis Network intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Early Detection of Dendroctonus valens Infestation with machine learning algorithms Based on Hyperspectral Reflectance

引用

REMOTE SENSING 2022年第6期14卷 1373-1373页

作者： Gao, Bingtao Yu, Linfeng Ren, Lili Zhan, Zhongyi Luo, Youqing Beijing Forestry Univ Beijing Key Lab Forest Pest Control Beijing 100083 Peoples R China Beijing Forestry Univ Sch Ecol & Nat Conservat Beijing 100083 Peoples R China Beijing Forestry Univ Sino French Joint Lab Invas Forest Pests Eurasia French Natl Res Inst Agr Food & Environm INRAE Beijing 100083 Peoples R China

The red turpentine beetle (Dendroctonus valens LeConte) has caused severe ecological and economic losses since its invasion into China. It gradually spreads northeast, resulting in many Chinese pine (Pinus tabuliformis Carr.) deaths. Early detection of D. valens infestation (i.e., at the green attack stage) is the basis of control measures to prevent its outbreak and spread. This study examined the changes in spectral reflectance after initial attacking of D. valens. We also explored the possibility of detecting early D. valens infestation based on spectral vegetation indices and machine learning algorithms. The spectral reflectance of infested trees was significantly different from healthy trees (p < 0.05), and there was an obvious decrease in the near-infrared region (760-1386 nm;p < 0.01). Spectral vegetation indices were input into three machine learning classifiers;the classification accuracy was 72.5-80%, while the sensitivity was 65-85%. Several spectral vegetation indices (DID, CUR, TBSI, DDn(2), D-735, SR1, NSMI, R-NIR center dot CRI550 and RVSI) were sensitive indicators for the early detection of D. valens damage. Our results demonstrate that remote sensing technology could be successfully applied to early detect D. valens infestation and clarify the sensitive spectral regions and vegetation indices, which has important implications for early detection based on unmanned airborne vehicle and satellite data.

关键词： red turpentine beetle (Dendroctonus valens LeConte) early detection hyperspectral analysis spectral vegetation indices machine learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Doctormate- An Early Disease Prediction Approach using Multiple machine learning algorithms

Doctormate- An Early Disease Prediction Approach using Multi...

引用

Electronics and Renewable Systems (ICEARS), International Conference on

作者： S. Kiruthiga Department of Computer Science & Engineering School of Computing Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India

Prediction of Multiple Diseases using machine learning algorithms is a user-friendly ML model that is used to predict the disease based on the symptoms entered by the user and gives the best analysis of possible diseases. It is based on the symptoms collected from large datasets, which is taken from hospitals containing the textual discharge summaries of patient diseases. It is a model which gives tips to the user to maintain a healthy life and also it is used to find out possible diseases very earlier, the user is suffering from. Health industry plays a crucial role in curing patient’s diseases in today’s world. So our work is going to help the health industry in an indirect way where user does not need to go to hospital for checkup instead user get to know the accurate disease within few seconds by entering at least two symptoms. It can handle enormous amount of data. There are various procedures available for the treatment of various diseases across the world which may take more time for diagnosis and prediction. machine learning is one of the most emerging technology which helps in prediction as well as diagnosis of a disease. This work is completely done by using machine learning algorithms like Decision Tree Algorithm, Random Forest Algorithm, Naive Bayes Algorithm, K Nearest Neighbour algorithm where these algorithms are deployed on larger datasets, which is then preprocessed by using data mining techniques to achieve higher accuracy than the existing *** lack of accuracy in existing models may lead to failure of diagnosis of the diseases in early stages and cause threat to patient’s life. This study has used Tkinter interface in Python programming language. The objective to attain higher accuracy improves the reliability of the model and gains patient’s trust for the cost-effective utilization of the proposed model.

关键词： Industries Schedules Renewable energy sources machine learning algorithms Hospitals Prediction algorithms Data models

来源：评论

学校读者我要写书评

暂无评论

machine learning algorithms Evaluation for Phishing URLs Classification

Machine Learning Algorithms Evaluation for Phishing URLs Cla...

引用

International Symposium on Advanced Electrical and Communication Technologies (ISAECT)

作者： Habiba BOUIJIJ Amine BERQIA SSL Lab ENSIAS Mohammed V University in Rabat Rabat Morocco

ISBN: (纸本)9781665437745

Phishing URL is a type of cyberattack, based on falsified URLs. The number of phishing URL attacks continues to increase despite cybersecurity efforts. According to the Anti-Phishing Working Group (APWG), the number of phishing websites observed in 2020 is 1 520 832, doubling over the course of a year. Various algorithms, techniques and methods can be used to build models for phishing URL detection and classification. From our reading, we observed that machine learning (ML) is one of the recent approaches used to detect and classify phishing URL in an efficient and proactive way. In this paper, we evaluate eleven of the most adopted ML algorithms such as Decision Tree (DT), Nearest Neighbours (KNN), Gradient Boosting (GB), Logistic Regression (LR), Naïve Bayes (NB), Random Forest (RF), Support Vector machines (SVM), Neural Network (NN), Ex-tra_Tree (ET), Ada_Boost (AB) and Bagging (B). To do that, we compute detection accuracy metric for each algorithm and we use lexical analysis to extract the URL features.

关键词： Uniform resource locators Support vector machines Measurement Radio frequency machine learning algorithms Phishing Feature extraction

来源：评论

学校读者我要写书评

暂无评论

An Integrated Approach of MCDM Methods and machine learning algorithms for Employees' Churn Prediction

An Integrated Approach of MCDM Methods and Machine Learning ...

引用

International Conference on Robotics,Electrical and Signal Processing Techniques (ICREST)

作者： Shefayatuj Johara Chowdhury Mainul Islam Mahi Sadiqul Alam Saimon Aynur Nahar Urme Rashidul Hasan Nabil Department of CSE International Islamic University Chittagong Chittagong Bangladesh Department of Computer Science American International University-Bangladesh Dhaka Bangladesh Department of EEE International Islamic University Chittagong Chittagong Bangladesh

Employee churn is a notable nuisance for organizations to maintain a cost-effective position and brand strategy. This research has proposed an integrated approach to overcome this issue systematically. All employees in this study were divided into three categories using a combination of machine learning algorithms and Multi-Criteria Decision Making (MCDM) techniques. The techniques for Order of Preference by Similarity to Ideal Solution (TOPSIS) and the Analytical Hierarchy Process (AHP) have been consolidated. The dataset's feature importance was retrieved, and AHP was used to determine the criteria that caused the most turnover. TOPSIS was given the derived criterion weights from AHP to rank every personnel according to their propensity to depart the organization. To estimate staff turnover, seven machine learning algorithms were applied. After comparing the results, the Random Forest algorithm produces the best accuracy for assessing employee churn.

关键词： Industries machine learning algorithms Signal processing algorithms Companies Signal processing Prediction algorithms Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Heart Diseases Prediction Using machine learning algorithms

Heart Diseases Prediction Using Machine Learning Algorithms

引用

International Conference on Computer Communication and Informatics (ICCCI)

作者： E. Anupriya Manyam Thaile P. Chinnasamy M Laxmi Narayana Department of Computer Science Engineering MLR Institute of Technology Hyderabad India Department of CSE-AIML Malla Reddy Engineering College

Even in older people and those who lead unhealthy lifestyles, heart disease may be a common problem that can be quite serious. This project’s primary goal is to take action and decrease the prevalence of middle diseases in patients. Age, sex, sign, number of cigarettes smoked per day, and other medical data are used as inputs, and these features are then modelled for prediction. Abstract One of the most challenging issues in the medical industry today is the prognosis of heart condition. According to current fashion, one person develops heart disease every four people. An enormous amount of data is processed in the healthcare industry with the help of machine learning.

关键词： Heart Industries machine learning algorithms Medical services machine learning Predictive models Lead

来源：评论

学校读者我要写书评

暂无评论

Exploring the Potential of Quantum-Based machine learning: A Comparative Study of QSVM and Classical machine learning algorithms

Exploring the Potential of Quantum-Based Machine Learning: A...

引用

International Symposium on Digital Forensic and Security (ISDFS)

作者： Zeynep Özpolat Murat Karabatak Depatment of Software Engineering Firat University Elazig Turkey

Research using innovative, rapidly evolving quantum-based systems is becoming increasingly important. The acceleration provided by the real use of a few quantum computers in the world constitutes very important steps for the computer world. Quantum-based systems are also frequently used in data science and machine learning. In this study, Quantum Support Vector machine (QSVM), a quantum-based machine learning algorithm, is compared with classical machine learning algorithms. IBM - Studies on quantum computer simulation have been carried out. The data dimension is reduced by first applying Principal Component Analysis (PCA) to the dataset. Afterwards, analyzes were made and the results were presented comparatively. The highest performance of the QSVM algorithm was obtained at 92.3%. Compared to classical machine learning algorithms, the performance of the QSVM algorithm is slightly lower. It is thought that higher performance and speed will be achieved in QSVM by eliminating limitations such as limited qubit resources and system restrictions. It is clear that the results found are promising for quantum-based machine learning algorithms.

关键词： Support vector machines Performance evaluation Computers Quantum system machine learning algorithms Qubit machine learning

来源：评论

学校读者我要写书评

暂无评论

Maneuvering machine learning algorithms to Presage the Attacks of Fusarium oxysporum on Cotton Leaves

Maneuvering Machine Learning Algorithms to Presage the Attac...

引用

Delhi Section Conference (DELCON), IEEE

作者： Anurag Dutta Pijush Kanti Kumar Ankita De Padmanavan Kumar John Harshith Yash Soni Department of Computer Science Government College of Engineering & Textile Technology Serampore Calcutta Serampore India Department of Information Technology Government College of Engineering & Textile Technology Serampore Calcutta Serampore India Department of Computer Science Kalinga Institute of Industrial Technology Odisha Bhubaneswar India Department of Computer Science Vellore Institute of Technology Vellore Tamil Nadu India Department of Information Technology S. G. S. Institute of Technology & Science Indore India

Web technologies have reached unprecedented levels during this time of modernization. Significant and relevant technological stacks like IoT (Internet of Things), ML (machine learning), and AI-influenced crawling and cradling (Artificial Intelligence). These categories are beneficial. In this work, we would try to make use of the notion of machine learning algorithms to predict the attack of Fusarium oxysporum on the leaves of the Cotton plant. It’s a type of ascomycete fungi that forms an infrageneric grouping called a section. All of the species, variations, and forms discovered by Wollenweber and Reinking are Elegans. It belongs to the Nectriaceae family. Many strains of the F. oxysporum complex are soil-borne plant pathogens, especially in agricultural settings, although their primary function in native soils may be as benign or even advantageous as plant endophytes or soil saprophytes. Many textile products are made from cotton. Cotton is used in a variety of products besides the textile industry, including gill nets, coffee filters, tarpaulins, cotton paper, and bookbinding. The cotton used to be used to make fire hoses. India and China are the major cotton producers in 2017, with an annual production of approximately 18.53 million tonnes and 17.14 million tonnes, respectively. The vast majority of this output is used by their textile businesses. This contributes a major portion of the economy. To strengthen the same, we can make use of certain prediction techniques that could foresee if the leaves of cotton suffering from the attack by the pathogens, making use of algorithms like ’Support Vector machine’, ’Random Forest’, ’k - Nearest Neighbours’, and many more. Further, this work would also compare the efficacy of these algorithms in predicting the damage in the Cotton Leaves. All Codes, Data, and Supplementary Material are made available at https://***/Anurag-Dutta/Maneuvering-machine-learning-algorithms-to-presage-the-attacks-of-Fusarium-oxysporum-o

关键词： Support vector machines Training Pathogens machine learning algorithms Plants (biology) Artificial neural networks Soil

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of IDS against DDOS Attack using machine learning algorithms

Comparative Study of IDS against DDOS Attack using Machine L...

引用

Artificial Intelligence and Smart Systems (ICAIS), International Conference on

作者： Pasupuleti Karthik Viswanadhu Vaddadi Lasya Priya Vakkapatla Lasyasri Sridharala Suneetha Bulla S. Kavitha Department of CSE Koneru Lakshmaiah Education Foundation Vaddeswaram Guntur(DST) Andhra Pradesh India

Data storage, bandwidth, and processing speed are all growing in the IT industry. The resulting increase in cyberattacks and threats necessitates the use of cutting -edge technology to employ a creative and predictive security approach. Using the information available, a model will be built by analysing various data sets and monitoring trends. (DDoS) are one of the prevalent problems and assaults wreaking havoc on internet-connected computer equipment? This study compares the working of several ML-based classifiers for detecting DDoS attacks before they occur. This experiment analysed data from the benchmark KDD-Cup-1999 DDoS attack. I have three distinct types of selection techniques to select essential features in the context of DDoS detection. The results show that feature selection methods can help domain experts understand the intrusion system's main hidden patterns and features during DDoS detection. The main challenges they faced are that DDOS attacks are more complex and attacks are coming from many places which makes them difficult to detect. The proposed sample learns to recognize regular network traffic to detect ICMP, TCP, and UDP DDoS traffic as it arrives. Tests show that machine learning algorithms can correctly classify traffic into regular and DDoS. The finding has lasting implications for many industries, including defence, financial institutions, and healthcare, and because other businesses need sophisticated intrusion detection techniques. The future direction of the proposed method is to implement the model in different datasets.

关键词： Industries Support vector machines machine learning algorithms Rain Telecommunication traffic Semisupervised learning Feature extraction

来源：评论

学校读者我要写书评

暂无评论

An Exploratory Study of Masked Face Recognition with machine learning algorithms

An Exploratory Study of Masked Face Recognition with Machine...

引用

IEEE Southeastcon

作者： Megh Pudyel Mustafa Atay Department of Computer Science Winston-Salem State University Winston-Salem NC USA

Automated face recognition is a widely adopted machine learning technology for contactless identification of people in various processes such as automated border control, secure login to electronic devices, community surveillance, tracking school attendance, workplace clock in and clock out. Using face masks have become crucial in our daily life with the recent world-wide COVID-19 pandemic. The use of face masks causes the performance of conventional face recognition technologies to degrade considerably. The effect of mask-wearing in face recognition is yet an understudied issue. In this paper, we address this issue by evaluating the performance of a number of face recognition models which are tested by identifying masked and unmasked face images. We use six conventional machine learning algorithms, which are SVC, KNN, LDA, DT, LR and NB, to find out the ones which perform best, besides the ones which poorly perform, in the presence of masked face images. Local Binary Pattern (LBP) is utilized as the feature extraction operator. We generated and used synthesized masked face images. We prepared unmasked, masked, and half-masked training datasets and evaluated the face recognition performance against both masked and unmasked images to present a broad view of this crucial problem. We believe that our study is unique in elaborating the mask-aware facial recognition with almost all possible scenarios including half_masked-to-masked and half_masked-to-unmasked besides evaluating a larger number of conventional machine learning algorithms compared the other studies in the literature.

关键词： Training machine learning algorithms Image recognition Pandemics Face recognition Surveillance Static VAr compensators

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：