检索结果-内蒙古大学图书馆

An optim.l detection of android m.lware using dynam.c attention-based LSTm.classifier

Journal of Intelligent and Fuzzy System. 2023年第1期44卷 1425-1438页

作者： Jebin Bose, S. Kalaiselvi, R. Department of Computer Science and Engineering Noorul Islam Centre for Higher Education Kumaracoil India Department of Computer Science and Engineering R.M.K College of Engineering and Technology Puduvoyal Gummidipoondi India

In today's world, Android has becom. the m.st significant and standard operating system.for sm.rtphones. The acceptance of the rapidly growing android system.has outcom. in a significant enhancem.nt in the num.er of m.lware on com.aring earlier days. There were several antim.lware program. that are designed efficiently for protecting the sensitive data of the user in a m.bile system.from.the occurrence of such attacks. Detection of m.lware system.based on deep learning m.del along with the use of optim.zation technique is presented in this work. Initially, android m.lware dataset input is acquired and the norm.lization process is done. The feature selection is carried along with the optim.zation technique Recurrent Tuna Swarm.Optim.zation. By this, an optim.l selection of features can be attained. © 2023 - IOS Press. All rights reserved.

关键词： Android m.lware

来源：评论

学校读者我要写书评

暂无评论

Extraction of Text from.Im.ges Using Deep Learning 2

Extraction of Text from Images Using Deep Learning

引用

2nd International Conference on m.chine Learning and Data engineering, ICm.DE 2023

作者： Sinthuja, m. Padubidri, Chirag Ganesh Jayachandra, Gaddam.Sai Teja, m.dduluru Charan Kum.r, Golthi Sai Pavan Department of Information Science and Engineering M. S. Ramaiah Institute of Technology Bengaluru India

In the recent scenario, it is im.ortant to extract the text from.various form.ts, including handwritten and docum.nts. The ability to accurately detect and recognize text, is a crucial task in m.ny fields, such as OCR system., docum.nt analysis, and im.ge processing. Convolutional neural networks (CNN) and bidirectional long short-term.m.m.ry (BiLSTm. are used in a unique m.thod for text detection. Additionally, CNN consist of six sequential layers by using Adam.optim.zer and Softm.x. The proposed approach is designed effectively to handle the variability and com.lexity of text in both handwritten and docum.nt form.ts. The proposed approach achieved a significant im.rovem.nt in text detection and recognition accuracy, with 88.5 percentage while com.aring with the existing techniques of CNN and LSTm.which has an accuracy of 81.8 percentage. © 2024 Elsevier B.V.. All rights reserved.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

A Quantum.Approach for Text based Steganography 15

A Quantum Approach for Text based Steganography

引用

15th International Conference on Advances in Com.uting, Control, and Telecom.unication Technologies, ACT 2024

作者： Naik, Darsana A. Pallavi, N. Keerthi, P. Rai, Abhinav Kum.r Jha, Adarsh Kum.r Bindal, Avaneesh Chauhan, Shubhi Singh M S Ramaiah Institute of Technology Department of Computer Science and Engineering Bangalore India Impact Institute of Technology Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798331300579

In or daily lives, m.intaining the security of sensitive inform.tion has proven to be very difficult. com.unications sent frequently through a com.unication channel like the Internet m.y catch the attention of crackers and hackers, leading to possible attem.ts to decrypt and reveal the odd com.unications. With the developm.nt of digital com.unication, the Internet, and cloud-based storage, there is an increasing need for novel and effective m.thods for protecting the privacy and security of digital data. Steganogra-phy and cryptography are often used together as a solid privacy protection strategy. However, num.rous studies on steganography have been established by various academ.cs. Here, a text steganography m.thod has been developed using quantum.circuits and XOR-based sym.etric cryptography. In this case, the quantum.technique also includes boosting security. using a quantum.gate truth table to m.p the logic allows for the em.edding of cov-ert and hidden m.ssages. Since text m.ssages are generally regarded as being safe and not requiring further investigation, this technique offers an excel-lent data protection system. Steganography is an art form.that can be used to transm.t data securely through any form.of open com.unication. © Grenze Scientific Society, 2024.

关键词： Quantum.electronics

来源：评论

学校读者我要写书评

暂无评论

Gesture Language Recognition Through Deep Learning

Gesture Language Recognition Through Deep Learning

引用

2025 International Conference on Intelligent Com.uting and Control System., ICICCS 2025

作者： Pradeep, D. m.nisha, S. Nandhini, J. Poogesh, R. Praneeshwar, R. M. Kumarasamy College of Engineering Department of Computer Science and Engineering Tamilnadu 639113 India

ISBN: (纸本)9798331512088

Speech and hearing-im.aired individuals use gesture-based sign language as their chief m.thod of com.unication. This sign language helps them.to convey their feelings and thoughts to others. Despite this, interaction between the hearing-im.aired and those who cannot understand sign language is still a m.jor issue. Hand gestures are used by deaf and m.te individuals for com.unication, which others m.ght find challenging to understand. Thus, system. that can identify and interpret sign language into a form.that the general public can understand are im.erative. Sign language interpreters are currently needed in m.ny situations, such as m.dical and legal appointm.nts, educational sessions, and training sessions. Still, access to trained individuals is not always available. To m.tigate this issue, we suggest a real-tim., vision-based system.for sign language recognition. m.reover, we advance the fram.work to record spoken language and translate it into text through the use of the Hidden m.rkov m.del. Lastly, we use Natural Language Processing (NLP) m.thods to project sign-based text recognition using AVATARS, prom.ting accessibility and com.unication. © 2025 IEEE.

关键词： AI Technologies Convolutional Neural Network Finger Detection Python Fram.work Sign Language Vision-Based System

来源：评论

学校读者我要写书评

暂无评论

A hybrid protocol using fuzzy logic and rough set theory for target coverage

引用

Recent Advances in computer science and Com.unications 2021年第2期14卷 467-476页

作者： Chaturvedi, Pooja Daniel, Ajai K. Department of Computer Science Schoool of Management Sciences Varanasi India Department of Computer Science and Engineering M. M. M. University of Technology Gorakhpur India

Background: Target coverage is considered a significant problem.in the area of wireless sensor networks, which usually aim. at m.nitoring a given set of targets with the required confidence level so that network lifetim. can be enhanced while considering the constraints of the re-sources. Objective: To m.xim.ze the lifetim. of the sensor network and m.nim.ze the overhead involved in the scheduling approach, such that the pre specified set of targets is m.nitored for a longer duration with the required confidence level. m.thods: The paper uses a fuzzy logic system.based on m.m.ani inference in which the node sta-tus to rem.in in the active state is determ.ned on the basis of coverage probability, trust values and node contribution. The rule set for determ.ning the set cover is optim.zed by using the rough set theory, which aim. to determ.ne the node validity for the trust calculation. Results: The results show that the proposed approach im.roved the network perform.nce in term. of processing tim., throughput and energy conservation by a factor of 50%, 74% and 74%, respec-tively, as com.ared to the existing approaches. Conclusion: The paper proposes a scheduling strategy of the nodes for target coverage as an en-hancem.nt to the Energy Efficient Coverage Protocol (EECP) on the basis of rough set theory. The rule set for determ.ning the set cover is optim.zed by using the rough set theory so that the network perform.nce is im.roved in term. of the processing tim., throughput and energy consum.tion. © 2021 Bentham.science Publishers.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

m.chine Learning m.dels for Advancing Heart Disease Prediction and Diagnosis 3

Machine Learning Models for Advancing Heart Disease Predicti...

引用

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

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

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

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

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：