检索结果-内蒙古大学图书馆

Smart Systems for applications in Electrical Sciences (ICSSES), International Conference on

作者： Abbubukar Siddique K N Harikishan Mohammed Kaif Nachiketha N Gowda V.M Aparanji S Karthik Department of ECE Siddaganga Institute of Technology Tumakuru India Cyphertek solutions Bangalore India

ISBN: (数字)9798350364040

ISBN: (纸本)9798350364057

Agriculture, a vital element in nourishing the world’s growing population, faces significant challenges such as climate change, soil degradation, and water scarcity. Accurate crop prediction is essential for maximizing yield and efficient farming practices. However, traditional manual observation methods have limitations in accuracy, scalability, and timeliness. To address these issues, an automated solution integrating NPK sensors emerges as a viable option. These sensors measure key nutrients like Nitrogen, Phosphorus, and Potassium in the soil, providing real-time data on crop nutrition. By feeding NPK sensor data to machine learning models, accurate predictions can be generated. Implementation involves integrating NPK sensors with Raspberry Pi via RS485 to TTL converter and utilizing algorithms like Random Forest and Naïve Bayes for insights on crop suitability. Leveraging edge computing, it provides on-field accuracy, eliminating the need to transport soil samples to testing centers. This integration has the potential to transform modern agriculture, increasing yields while minimizing waste.

关键词： Accuracy machine learning algorithms Soil measurements Transforms Soil Phosphorus Agriculture

来源：评论

学校读者我要写书评

暂无评论

Benchmarking of machine learning algorithms for Indian Premier League matches

Benchmarking of Machine Learning algorithms for Indian Premi...

引用

International Conference on Computational Intelligence and Networks (CINE)

作者： Ramesh Kumar Thakur Jiten Agarwal Hardik Chauhan Saumyadeep Mahanta Uzaif Ali Shreya Mondal Centre of Artificial Intelligence NIT Bhopal Madhya Pradesh India School of Computer Engineering KIIT University Bhubaneswar Odisha India

ISBN: (数字)9798331516796

ISBN: (纸本)9798331516802

This paper presents a comprehensive overview of machine learning models for predicting results in sports events, such as the Indian Premier League (IPL). Using a dataset of past seasons, the study uses various algorithms, including Support Vector machines, Random Forest Classifier, Logistic Regression, K-Nearest Neighbours, Decision Trees, LightGBM, Naïve Bayes, and CatBoost. The Random Forest classifier outperforms other models with a training accuracy of 85.34%, whereas the Decision Tree supersede other models with a testing accuracy of 58%. The study highlights the potential of machine learning in sports and betting decision-making.

关键词： Training Support vector machines machine learning algorithms Accuracy Computational modeling Vectors Bayes methods Random forests Regression tree analysis Sports

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of machine learning algorithms for Emotion Classification

Comparative Analysis of Machine Learning Algorithms for Emot...

引用

IEEE Punecon

作者： Ashish Deshmukh Aniket Dhage Ritika Gadapa Sanika Butle Anuradha Yenkikar Nilesh P. Sable Department of CSE – Artificial Intelligence Vishwakarma Institute of Information Technology Pune India Department of Computer Engineering Vishwakarma Institute of Information Technology Pune India

ISBN: (数字)9798331527822

ISBN: (纸本)9798331527839

In this generation, social media platforms such as Twitter, Instagram and also e-commerce websites have become an integral part of our society. Social media is used for communication and it is also a platform where the users can express their thoughts and feelings. Also, users share their reviews on e-commerce websites. To analyze what exactly is the emotion of the user our machine learning models explores the sentiment analysis techniques for predicting emotions from the given text data. It follows a series of steps, starting with importing libraries, acquiring datasets, visualization, pre-processing, and model building. The data is used to train on a variety of models, including LSTM, Naive Bayes, Random Forest, Gradient Boosting, and SVM. The performance of each model is evaluated using metrics like accuracy, precision, recall, and F1-score. Comparative analysis is conducted to determine the most effective model for emotion prediction. Furthermore, the research investigates emotion prediction for huge datasets and provides a procedure for exporting trained models for future usage. It provides insights into the performance of various machine learning algorithms in sentiment analysis, hence contributing to the understanding and interpreting emotions from textual data on various platforms.

关键词： Support vector machines Sentiment analysis Analytical models Accuracy machine learning algorithms Social networking (online) Predictive models Data models Long short term memory Random forests

来源：评论

学校读者我要写书评

暂无评论

Comparison of Different machine learning algorithms in the Parameterization of Near-Surface Turbulent Fluxes

Comparison of Different Machine Learning Algorithms in the P...

引用

IEEE International Conference on Cloud Computing and Big Data Analysis (ICCCBDA)

作者： Qiang Fan Bo Gong Qili Zhang Hourong Zhang Xianyin Mao Haipeng Zhang Jianrong Wu Lusong Zhang Key Laboratory of Ice Prevention & Disater Reducing of China Electric Power Research Institute of Guizhou Power Grid Co. Ltd Southern Power Grid Co. Ltd Guiyang China Electric Power Research Institute of China Southern Power Grid Co. Ltd Guangzhou China

ISBN: (数字)9798350373554

ISBN: (纸本)9798350373561

The study of non-iterative schemes for near-surface tu rbulent flux parameterization is significant for model forecasting and climate prediction. In this paper, four machine learning algorithms (Random Forest, CatBoost, XGBoost and LightGBM) are used to design non-iterative schemes for near-surface turbulent flux parameterization. Through comparison, we find that the results obtained by XGBoost and LightGBM exhibit significant fluctuations, sensitivity to minor data changes, and poor stability, with lower accuracy compared to the BH&H scheme, making them unsuitable to design the parameterization model. While CatBoost shows less fluctuation, its results still possess minor irregularities compared to the Random Forest model. The results of Random Forest are smooth, stable, and highly accurate, making it the most suitable algorithm among the four algorithms for application in the parameterization of near-surface turbulent fluxes.

关键词： machine learning algorithms Fluctuations Accuracy Sensitivity Forestry Predictive models Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Detection of Parkinson's Disease using machine learning algorithms from Speech Signals

Detection of Parkinson's Disease using Machine Learning Algo...

引用

Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT), International Conference on

作者： Syed Anees Ahammad Anitha Sankaran Lakshmi Sutha Kumar Department of Electronics and Communication Engineering National Institute of Technology Puducherry Union Territory of Puducherry India

ISBN: (数字)9798331540685

ISBN: (纸本)9798331540692

Parkinson's disease is a long-term neurological con-dition that impacts 60 % of people above 50 years of age, it results in a decrease in voice in 90% of individuals and ranks as the second most prevalent illness among the elderly. It affects the gait, speech, and memory. The diagnosis and treatment requires physical visits which are extremely difficult and cumbersome for the older people. Making use of speech signals for the Parkinson's disease diagnosis provides a non-invasive, less time-consuming and painless experience to the patients. This paper's main objective is to build a feature vector that comprises of a time domain feature, Zero Crossing Rate, a frequency domain feature, the Spectral Centroid and the cepstral features from the 14 coefficients of Mel Frequency Cepstral Coefficients (MFCC), MFCC Delta and MFCC Delta-Delta. Support Vector machine (Linear and Polynomial kernels), Random Forest, and Logistic Regression are utilised to classify Parkinson's disease. Support Vector machine (both Linear and Polynomial kernels) achieved the maximum accuracy of 92.31 % as in contrast to the other machine learning algorithms considered in this paper. It is found from the comparison with the existing models that the proposed model with SVM classifier performed better than the other models.

关键词： Support vector machines machine learning algorithms Accuracy Parkinson's disease Biological system modeling Polynomials Vectors

来源：评论

学校读者我要写书评

暂无评论

Prediction and comparison of psychological health during COVID-19 among Indian population and Rajyoga meditators using machine learning algorithms

引用

Procedia computer science 2023年 218卷 697-705页

作者： Prashant Kumar Sushil Chandra CSIR-Central Scientific Instruments Organisation Chandigarh160030 India. Institute of Nuclear Medicine & Allied Sciences-DRDO New Delhi 110054 India.

Issues of providing mental health support to people with emerging or current mental health disorders are becoming a significant concern throughout the world. One of the biggest effects of digital psychiatry during COVID-19 is its capacity for early identification and forecasting of a person's mental health decline resulting in chronic mental health issues. Therefore, through this study aims at addressing the hological problems by identifying people who are more likely to acquire mental health issues induced by COVID-19 epidemic. To achieve this goal, this study includes 1) Rajyoga practitioners' perceptions of psychological effects, levels of anxiety, stress, and depression are compared to those of the non practitioners 2) Predictions of mental health disorders such as stress, anxiety and depression using machine learning algorithms using the online survey data collected from Rajyoga meditators and general the population. Decision tree, random forest, naive bayeBayespport vector machine and K nearest neighbor algorithms were used for the prediction as they have been shown to be more accurate for predicting psychological disorders. The support vector machine showed the highest accuracy among all other algorithms. The f1 score was also the highest for support vector machine.

关键词： COVID-19 DASS machine learning algorithms mental health

来源：评论

学校读者我要写书评

暂无评论

Harnessing machine learning algorithms to Revolutionize Crime Detection and Prevention

Harnessing Machine Learning Algorithms to Revolutionize Crim...

引用

International Conference on Trends in Electronics and Informatics (ICEI)

作者： E. Monika T.Rajesh Kumar Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institite of Medical and Technical Sciences Chennai India

ISBN: (数字)9798331544607

ISBN: (纸本)9798331544614

machine learning's (ML) quick development has opened up revolutionary possibilities for crime prevention and detection by making accurate, effective, and scalable solutions possible. In order to improve the precision of criminal behavior identification and prediction, this study investigates the integration of cutting-edge machine learning methods, such as gradient boosting machines, random forests, and convolutional neural networks (CNNs). Utilizing both structured and unstructured data sources, including social media analytics, surveillance footage, and past crime records, our approach makes use of enormous datasets. Accuracy, precision, recall, and F1 score are important evaluation criteria. According to experimental results, CNN-based models were able to identify criminal actions from video surveillance with 94.8% accuracy, 92.5% precision, 90.3% recall, and 91.4% F1 score. High-risk areas and persons were profiled using Random Forest algorithms, which produced an F1 score of 87.8%, accuracy of 89.7%, precision of 88.2%, and recall of 87.5%. When used to detect anomalies in financial transactions, gradient boosting machines demonstrated 93.2% accuracy, 91.8% precision, 90.6% recall, and 91.2% F1 score. The system's performance demonstrates how well it can handle a variety of crime scenarios, such as real-time monitoring, fraud detection, and predictive policing. The study also emphasizes how crucial it is to strike a balance between recall and precision in order to reduce false positives and negatives, which is crucial in practical applications. This study provides a scalable and flexible framework to transform crime detection and prevention by utilizing cutting-edge machine learning algorithms, giving law enforcement useful information.

关键词： Accuracy machine learning algorithms Prevention and mitigation System performance Soft sensors Transforms Boosting Video surveillance Convolutional neural networks Random forests

来源：评论

学校读者我要写书评

暂无评论

Real Time Fake news Detection Web App Enhanced by machine learning algorithms

Real Time Fake news Detection Web App Enhanced by Machine Le...

引用

Intelligent Technologies (CONIT), International Conference on

作者： V Gunasekaran D Karthikeyan School of Information and Technology Vellore Institute of Technology Vellore Tamil Nadu India

ISBN: (数字)9798350349900

ISBN: (纸本)9798350349917

In this era, the pervasive proliferation of fabricated news has come to light as a formidable adversary, corroding the credibility of journalistic sources, sowing confusion, and distorting public discourse. To counteract this escalating predicament, this research introduces a pioneering and comprehensive solution-an interactive web application engineered to detect and mitigate the impact of fabricated news. Through the strategic integration of sophisticated machine learning algorithms, this platform not only identifies spurious news content but also operates in real time, enabling swift responses to the proclamation of misinformation. The key aim of this study is to elevate the precision and efficiency of fabricated news identification. This is achieved through a meticulously devised amalgamation of advanced natural language processing (NLP) techniques, meticulous feature engineering strategies, and the robust framework of ensemble learning methods. The fusion of these techniques equips the system with an arsenal of tools to scrutinize news story, disentangling the intricate web of linguistic nuances that often obscure deceptive content. The real-time facet of the application is pivotal, ensuring that the detection process transpires in sync with the constant influx of news story across digital platforms. This immediacy minimizes the potential amplification of false narratives, thereby curbing the negative impact of fabricated news proclamation. The heart of the system lies in its fabricated news detection capability, fortified by the intricacies of modern machine learning. By training on vast repositories of verified news data and contrasting it with known instances of false information, the algorithms learn to recognize patterns that distinguish authentic news from falsified narratives. Accessed through standard web browsers, the web application interface offers an intuitive and accessible medium for users to engage with the detection process.

关键词： Training Heart machine learning algorithms Linguistics Real-time systems Natural language processing Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Predicting Water Safety: Harnessing the Power of Simple machine learning algorithms

Predicting Water Safety: Harnessing the Power of Simple Mach...

引用

Advances in Computing, Communication and Applied Informatics (ACCAI), International Conference on

作者： Dipali Dumbre Seeta Devi Ranjana Chavan Symbiosis College of Nursing (SCON) Symbiosis International (Deemed University) (SIU) Pune India

ISBN: (数字)9798350389449

ISBN: (纸本)9798350389456

One of the most valuable resources that is necessary for all life is water. Water pollution lowers the quality of the water, which affects the health of marine life and, consequently, that of humans who utilize it. Because of this, it’s imperative to monitor water quality and guarantee the survival of marine life. This research will use artificial intelligence and machine learning techniques to evaluate the efficacy of several models in forecasting water safety. Orange tools are used to apply several prediction models, including Decision Tree, Gradient Boosting, Naïve Bayes, Neural Network, SGD, kNN, and CN2 rule inducer. The review employs publicly available secondary data from Keggle, ensuring transparency and accessibility in the research methodology. The results demonstrate that the GB, Neural Network, and Tree achieved superior accuracy ratings of 0.992, 0.998, 0.997, and 0.997, respectively, with remarkable AUC values of 1.000, 1.000, and 0.969. In addition, their recall and accuracy scores are 0.998, 0.998, 0.998, and 0.997, confirming their outstanding performance in predicting water safety.

关键词： machine learning algorithms Accuracy Reviews Neural networks Water quality Predictive models Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Enhancing Financial Market Analysis Bitcoin vs Gold through machine learning algorithms: A Study on Risk Assessment and Portfolio Management

Enhancing Financial Market Analysis Bitcoin vs Gold through ...

引用

India Council International Subsections Conference (INDISCON), IEEE

作者： Richa Golash Kushagra Golash SCSET Bennett University Greater Noida India SCSET BITS Pilani Dubai

ISBN: (数字)9798350376753

ISBN: (纸本)9798350376760

Financial markets exhibit complex, nonlinear dynamic behavior that is often challenging to interpret using traditional linear analysis methods. Risk assessment and, accordingly, portfolio management are the most important tasks for investors in order to avoid big losses. Gold trading is considered a safe haven, but it shows slow growth. In contrast, bitcoin or cryptocurrency trading is being proliferated. Many established financial institutions, like PayPal and Fidelity, are making it easier than ever for individuals to buy and sell Bitcoin. While Bitcoin trading can be potentially lucrative, it’s crucial to understand the significant risks involved before diving The volatile nature of Bitcoin can be emotionally stressful, leading to anxiety and poor decision-making. High-risk activity like stock trading requires a strong understanding of the market, particularly in high-risk assets like Bitcoin and gold, which demands a deep comprehension of market dynamics and the ability to tolerate volatility. Through this study, we delve into the application of machine learning algorithms to comprehend correlations, causality, and predict volatility in stock trading. Specifically, we focus on analyzing the trading behavior of cryptocurrency (bitcoin) vs. physical assets (gold) in terms of their volatility and comparing them in correlation with the stock index of crude-oil, S&P 500, and the dollar. This structured study aims to shed light on the effectiveness of machine learning algorithms in understanding and predicting volatility in stock trading, with a specific focus on Bitcoin and gold as high-risk assets.

关键词： Gold machine learning algorithms Correlation Uncertainty Stability criteria Bitcoin Risk management Reliability Stock markets Portfolios

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：