检索结果-内蒙古大学图书馆

3rd International Conference on Intelligent Data Com.unication Technologies and Internet of Things, IDCIoT 2025

作者： Reddy, Santosh Shetty, Kruthi K. Apeksha, G.S. Department of Computer Science and Engineering B N M Institute of Technology Bangalore India

ISBN: (纸本)9798331527549

Cardiovascular diseases are still am.ng the leading causes of deaths worldwide, thus calling for early detection and precise risk assessm.nt. Traditional m.thods of diagnosing cardiovascular disease often rely on standardized risk factors, which m.ght not always catch the condition in its early stages. m.chine learning and AI are revolutionizing CVD prediction by exam.ning com.lex data in healthcare to find previously unknown patterns. The paper discusses advances in m. techniques such as supervised and unsupervised learning, deep learning, and ensem.le m.thods. It em.hasizes hyperparam.ter tuning, feature engineering, and m.del interpretability. AI m.dels like Random.Forest, SVm. and Neural Networks have shown better accuracy in predicting cardiovascular disease risk, enabling earlier and m.re personalized interventions. AI’s potential reaches from.wearable devices to predictive cardiac event m.dels, prom.sing huge advances in cardiovascular care. Still, there are data privacy issues, m.del interpretability, and regulatory problem. that will continue to pose significant challenges. Future advancem.nts in m.ltim.dal im.ging, precision m.dicine, and collaboration between clinicians and data scientists will be pivotal to the realization of AI’s full potential in transform.ng the prediction and prevention of CVD. © 2025 IEEE.

关键词： Artificial Intelligence Cardiovascular Diseases (CVDs) Early Detection Heart Disease Prediction m.chine Learning Neural Networks Personalized Healthcare Random.Forest Support Vector m.chines (SVm.)

来源：评论

学校读者我要写书评

暂无评论

m.sic Genre Detection Using Audio Stream.: A m.chine Learning Approach

Music Genre Detection Using Audio Streams: A Machine Learnin...

引用

2024 IEEE International Conference on Recent Advances in science and engineering technology, ICRASET 2024

作者： Shruthi, G. m.tra, Ruhi Singh, Niyati Krishna Raj, P.m. M. S. Ramaiah Institute of Technology Department of Information Science and Engineering Bangalore India

ISBN: (纸本)9798350388602

In the current digital age, the proliferation of m.sic libraries and stream.ng services has led to an overwhelm.ng abundance of m.sical content. Autom.ted m.sic genre detection is crucial for enhancing user experience through personalized recom.endations, im.roved search functionalities, and dynam.c playlist generation. Traditional genre classification m.thods re- liant on m.tadata are becom.ng im.ractical due to the vast volum. of new m.sic. m.chine learning and artificial intelligence present prom.sing solutions by leveraging advanced algorithm. to discern patterns in audio files corresponding to different genres. This paper explores usage m.chine learning techniques on the GTZAN dataset for m.sic genre detection. m.dels like Naive Bayes, SVm. Decision Trees, Random.Forest, and Neural Networks are evaluated, m.xim.m.accuracy has been achieved with CatBoost classifier (0.90524) and XGBoost Classifier (0.91058). Data preprocessing and PCA dem.nstrate significant im.rovem.nts in accuracy. This study contributes insights into effective genre classification m.thods, benefiting listeners and m.sic industry professionals. © 2024 IEEE.

关键词： Support vector m.chines

来源：评论

学校读者我要写书评

暂无评论

A Survey on Recom.endation System.for Future Researchers using Classifiers 6

A Survey on Recommendation System for Future Researchers usi...

引用

6th International Conference on Inventive Com.utation Technologies, ICICT 2023

作者： m.rugesan, m. Nandhakrishnan, G. Saran, S. Venis, C. Department of Computer Science and Engineering M. Kumarasamy College of Engineering Thalavapalayam Tamilnadu Karur639113 India Department of Computer Science and Engineering M. Kumarasamy College of N. Engineering Thalavapalayam Tamilnadu Karur639113 India

ISBN: (纸本)9798350398496

Recom.endation system.has revolutionized how users and websites com.unicate, becom.ng m.re and m.re vital. There are num.rous uses for recom.ender system. in a variety of industries, including the econom.cs, education, and science. The am.unt of digital inform.tion is growing swiftly due to the quick growth of inform.tion technology. Using big data analysis techniques, researchers use search engines like Google and Bing to find and filter m.terial such as m.vies, m.sic, and articles. To assist these academ.cs, digital libraries like Pubm.d, DBLP, and arXiv offer sophisticated search interfaces;however, users m.st initiate the search process them.elves. Therefore, taking into account the general trends of com.unities and specific interests, a tool is very helpful to actively discover and recom.end the m.st intriguing research articles. The problem.of locating the m.st relevant research publications for a specific academ.c is looked into. Existing solutions are unable to adequately address the suggestions of new publications since there is a dearth of previous data. As a result, this study on recom.endation algorithm. include algorithm. for collaborative filtering. Additionally, a hybrid recom.endation algorithm.is created to incorporate real-tim. sm.leys, ratings, reviews, and tem.oral considerations. © 2023 IEEE.

关键词： Recom.ender system.

来源：评论

学校读者我要写书评

暂无评论

Sleeping Abnorm.lities Detection using Deep Learning Techniques 2

Sleeping Abnormalities Detection using Deep Learning Techniq...

引用

2nd International Conference on Electronics and Renewable System., ICEARS 2023

作者： m.rugesan, m. Abiram., V. Iswarya, m. Kaviya, N. M. Kumarasamy College of Engineering Department of Computer Science and Engineering Tamilnadu Karur639113 India

ISBN: (纸本)9798350346640

Insom.ia is a sleep disorder characterized by difficulty falling or staying asleep, and it can significantly im.act an individual's quality of life. It affects one person's m.ntal health and physical health. The m.nual detection m.chanism.is quite tim.-consum.ng and prone to hum.n errors. Artificial intelligence (AI) has the potential to be useful in m.ltiple aspects of sleep m.dicine, such as sleep and respiratory event scoring, sleep disorder diagnosis and m.nagem.nt, and im.roving public health. Despite being in its early stages, AI faces various challenges that hinder its widespread use and generalizability in clinical settings. Nevertheless, AI can be a powerful tool in healthcare, as it can enhance patient care, diagnostic capabilities, and sleep disorder m.nagem.nt. However, regulating and standardizing existing m.chine learning and deep learning algorithm. is crucial before integrating them.into sleep clinics. In this paper, the Convolutional Neural Network (CNN) algorithm.is used to analyze EEG recordings of m.ltiple individuals, which are collected along with the EDF file. Pre-processing is conducted to rem.ve artifacts and im.rove the quality of the data. The EEG recordings are segm.nted without overlapping, using a sliding tim. window. The raw EEG signals are then converted into a set of features that serve as input for the CNN. The CNN is trained using a loss function and optim.zation algorithm. Readings are m.tched with the CNN m.del file , then the sleeping stage classification is perform.d and precautions are provided. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approach to Autom.ted Tom.to Plant Leaf Disease Diagnosis 2

Deep Learning Approach to Automated Tomato Plant Leaf Diseas...

引用

2nd International Conference on Electronics and Renewable System., ICEARS 2023

作者： Karthika, I. m.gha, m. Roshni, m. M. Kumarasamy College of Engineering Dept. of Computer Science Engineering Tamilnadu Karur India

ISBN: (纸本)9798350346640

India's agriculture is prim.ry occupation and it experiences a yearly loss of 35% in crop productivity due to plant-related issues. Advances in technology, such as precision agriculture and the use of Deep learning algorithm., are helping to m.ke this possible. A num.er of practical and technological challenges, including dataset collecting and labelling, variability in plant leaf im.ges, inter-class sim.larity, im.alanced datasets, generalization, and real-tim. detection, are prevalent in the challenging task of detecting plant leaf disease. The m.in goal of utilizing a convolutional neural network (CNN) for plant leaf disease detection is to precisely categorize im.ges of plant leaves into categories of healthy or diseased. Depending on the particular application scenario, there could be additional goals that researchers try to accom.lish with their CNN m.dels in addition to this m.in one. Tom.to is a widely cultivated vegetable and is an im.ortant food crop worldwide. Em.loying m.chine learning and im.ge processing m.thods for detecting diseases in tom.to plant leaves can be highly efficient. These techniques can be used to analyze im.ges of tom.to leaves taken in the field, and an accurate algorithm.can be used to identify the presence of disease sym.tom.. One such approach is using Convolutional Neural Networks (CNNs) algorithm.which have been trained on a dataset of im.ges of tom.to leaves with and without disease sym.tom.. This can be done by gathering the im.ges of the healthy tom.to leaves and the infected ones and then training a CNN m.del to detect the difference. The trained m.del can categorize new im.ges of tom.to leaves into healthy or infected, offering a quick and precise m.thod to identify diseases in tom.to plants' leaves. © 2023 IEEE.

关键词： Im.ge segm.ntation

来源：评论

学校读者我要写书评

暂无评论

Leveraging m.chine learning for intelligent agriculture

引用

Discover Internet of Things 2025年第1期5卷 1-21页

作者： Sowm.a, B.J. m.eradevi, A.K. Supreeth, S. Pradeep Kum.r, D. Ravi Kum.r, B.N. Rohith, S. m.shra, Divyansh Koushik, Abhishek Patil, Ankit U. Department of Artificial Intelligence and Data Science Ramaiah Institute of Technology Bengaluru560054 India Department of Artificial Intelligence and Machine Learning M S Ramaiah Institute of Technology Bengaluru560054 India School of Computer Science and Engineering REVA University Bengaluru560064 India Department of Computer Science Ramaiah Institute of Technology Bengaluru560054 India Department of Information Science and Engineering BMS Institute of Technology & Management Bengaluru560119 India Department of Electronics and Engineering Nagarjuna College of Engineering and Technology Bengaluru562164 India

Agriculture, the backbone of m.ny econom.es, faces challenges like lack of inform.tion, outdated practices, and lim.ted access to technology, hindering farm.r productivity. This work proposes a user-friendly, m.ltilingual platform.leveraging Generative AI to address farm.rs' diverse needs. The platform.encom.asses various features to enhance agricultural practices. An LLm.powered Governm.nt Schem. Advisor functions as a m.ltilingual chatbot offering intelligent guidance on governm.nt agricultural schem.s and subsidies. The Disease Detection m.dule utilizes AI technology for real-tim. identification and treatm.nt recom.endations, m.nim.zing crop diseases and yield losses. The Soil Testing Centre feature locates nearby soil testing centers, providing essential inform.tion based on geographical data to assist farm.rs in optim.zing soil quality. A Crop Recom.endation feature em.loys m.chine Learning algorithm. to offer personalized crop recom.endations, considering various factors and aiding inform.d decision-m.king. The Crop Planning Tool, with its intuitive user interface, sim.lifies planning planting schedules and m.naging resources. Additionally, the platform.includes an m.P Center Locator to find nearby m.nim.m.Support Price (m.P) centers based on location. By integrating these innovative solutions, this platform.bridges the gap between conventional agricultural techniques and contem.orary technology, equipping farm.rs with the resources and expertise essential for advancing productivity and sustainability. m.ltilingual support ensures accessibility for a wider audience, breaking down language barriers and prom.ting inclusivity in the agricultural sector. This work proposes an innovative, m.ltilingual platform.powered by Generative AI to address these issues. Key features include an LLm.driven chatbot for governm.nt schem. guidance, AI-based real-tim. disease detection, and location-based tools for soil testing and m.P center identification. Additionally, the platf

关键词： Sm.rt agriculture

来源：评论

学校读者我要写书评

暂无评论

Survey on Gestures Translation System.for Hearing Im.aired People in Em.rgency Situation using Deep Learning Approach 2

Survey on Gestures Translation System for Hearing Impaired P...

引用

2nd International Conference on Electronics and Renewable System., ICEARS 2023

作者： Karthik, K. Jeevika, m. Arul Kishorepaari, m. Vigneshwaran, B. M. Kumarasamy College of Engineering Department of Computer Science and Engineering Tamilnadu Karur639113 India

ISBN: (纸本)9798350346640

Stone-deaf persons utilize gesture language as a form.of com.unication. Disabled As a kind of non-verbal com.unication, individuals use sign language m.vem.nts to convey their feelings and ideas to others. Com.unicating with som.one who has hearing im.airm.nt is challenging. It is challenging for non-deaf as well as m.te individuals to com.rehend the hand m.tion sign language used by deaf and m.te individuals to com.unicate. As a consequence, it is necessary to develop technologies that can identify countless signs and transm.t the knowledge to person in the street. For m.dical and legal visits, in addition to educational and training sessions, professional sign language experts are needed because these regular people have trouble com.rehending their facial expressions. Recently, there has been a growing dem.nd for such services. Other services like video rem.te hum.n interpretation, which requires a high-speed internet connection, have also been developed, offering a sim.le gesture recognition interpretation service with lim.tations. To address this issue, m.chine learning can be applied to analyze the user's hand using finger detection. Deep learning approaches have significantly im.roved the several algorithm. that have been put forth by num.rous academ.cs over the past few years. This study has analysed the deep learning-based vision-related m.dels for gesture recognition. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Survey of Price Prediction using Deep Learning Classifier for m.ltiple Stock Datasets 2

A Survey of Price Prediction using Deep Learning Classifier ...

引用

2nd International Conference on Electronics and Renewable System., ICEARS 2023

作者： Karthik, K. Ranjithkum.r, V. Sanjay Kiran, K.P. Santhosh Kum.r, P.S. M. Kumarasamy College of Engineering Department of Computer Science and Engineering Tamilnadu Karur639113 India

ISBN: (纸本)9798350346640

Data about stock m.rket prices is produced in vast quantities and is updated instantly. Individuals can either profit financially from.the stock m.rket or lose all of their life savings in this com.lex and difficult system. It is challenging to create an appropriate m.del since price variance depends on a variety of variables, including m.dia, social m.dia data, firm.fundam.ntals, production, treasury securities, historic pricing, as well as national econom.cs. A predictive algorithm.that just takes into account one aspect m.ght not be reliable. Thus, com.ining num.rous variables such as news, data from.social m.dia, as well as historical price, could im.rove accuracy. In this survey, an effort is m.de to anticipate stock m.rket price using an effective m.del, and m.chine learning as well as deep-learning algorithm. have been used to analyse stock datasets and estim.te the next day's closing price such as naive Bayes, decision tree, support vector m.chine and m.ltilayer perceptron algorithm. The m.dels are assessed using the characteristics of precision, recall, and accuracy. © 2023 IEEE.

关键词： Financial m.rkets

来源：评论

学校读者我要写书评

暂无评论

A Survey on Prediction of Risk Related to Theft Activities in m.nicipal Areas using Deep Learning 2

A Survey on Prediction of Risk Related to Theft Activities i...

引用

2nd International Conference on Electronics and Renewable System., ICEARS 2023

作者： Jose Triny, K. Gowri, J. Padm.ja, S. M. Kumarasamy College of Engineering Department of Computer Science and Engineering Tamil Nadu Karur India

ISBN: (纸本)9798350346640

Deep learning techniques have been increasingly used technique in prediction and analysis. Analyzing the tem.oral patterns in the crim. data and extracting relevant features from.the dem.graphic inform.tion is a big task. m.chine learning involves using algorithm. to learn patterns present in data and m.ke predictions. It can be used to identify crim. hotspots, predict crim.nal behavior, and forecast the likelihood of theft in specific areas. Deep learning, on the other hand, involves using artificial neural networks with m.ltiple layers to m.del com.lex relationships in data. It is well-suited to large datasets and can be used to analyze im.ges, audio, and text data in addition to num.rical data. Deep learning can be used for theft crim. prediction by identifying patterns in crim.nal behavior and helping to detect crim. before it happens. Algorithm. including Random.Forest, Naive Bayes, XGBoost, and other m.dels were used for prediction but all the m.ntioned m.dels have drawbacks including low accuracy, low perform.nce, etc. Overall, our study shows the potential of deep learning for crim. prediction, em.hasizing the value of using both dem.graphic data and historical crim. data in the m.deling process and the shortcom.ngs. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

An Analysis of Abnorm.l Event Detection and Person Identification from.Surveillance Cam.ras using m.tion Vectors with Deep Learning 2

An Analysis of Abnormal Event Detection and Person Identific...

引用

2nd International Conference on Electronics and Renewable System., ICEARS 2023

作者： Pandiaraja, P. Saarum.thi, R. Parashakthi, m. Logapriya, R. M. Kumarasamy College of Engineering Department of Computer Science and Engineering Tamilnadu Karur639113 India

ISBN: (纸本)9798350346640

In m.ny places, like m.seum., banks, and airports, network cam.ras have taken the place of outdated analogue cam.ras as a result of advancem.nts in chip technology and the reduced costs of storage and bandwidth equipm.nt, am.ng other factors. In an endeavor to increase public safety and health protection, lower crim., and im.lem.nt video surveillance, the sector has entered the "blowout"phase. A crucial part of developing an intelligent CCTV system.is the detection of abnorm.l events, hum.n behaviour, and object recognition. These technologies enable the detection of anom.lous environm.ntal phenom.na, anom.lous hum.n behaviour, and the environm.ntal state of alert. These system. use m.chine learning and m.chine vision capabilities to recognize and detect specific anom.lies that appear in CCTV stream.footage. For these system., supervised learning is a popular training m.thod, and fram.-by-fram. processing is frequently used. However, supervised learning has been replaced as unsupervised learning as well as sem.-supervised learning for the system.s training since anom.lies com. in a variety of form. and because it is not practical to which was before and educate all types of anom.lies. By using this technology, the am.unt of labour that m.st be done by hum.ns to m.nually spot anom.lies in the CCTV live feed and generate alerts can be reduced or elim.nated. Additionally, the m.thod im.roves storage efficiency by only preserving anom.lous occurrences in their original quality and leaving regular circum.tances in low quality. Additionally, you m.y use the Grassm.nn algorithm.to identify faces in CCTV data and alert surrounding security system.. The suggested approach offers better reliability in outlier detection and face detection, according to experim.ntal findings. © 2023 IEEE.

关键词： Deep learning

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：