检索结果-内蒙古大学图书馆

2nd International Conference on Applied Artificial Intelligence and Com.uting, ICAAIC 2023

作者： Sriram. S. Santhiya, S. Rajeshkum.r, G. Gayathri, S. Vijaya, K. Rajesh Kanna, P. Bannari Amman Institue of Technology Department of Computer Science and Engineering Sathyamangalam India M. Kumarasamy College of Engineering Department of Computer Science and Engineering Karur India Karpagam College of Engineering Department of Information Technology Coimbatore India Velalar College of Engineering and Technology Department of Cse Erode India

ISBN: (纸本)9781665456302

The purity of the water has recently been threatened by a num.er of contam.nants. As a result, it is now crucial for the m.nagem.nt of water pollution to m.del and anticipate water quality. In order to forecast the water quality index (WQI) and water quality classification (WQC), this work creates cutting-edge artificial intelligence (AI) approaches. Today, m.ny people are afflicted with severe illnesses brought on by tainted water. This study will look at a water quality m.nitoring system.because it provides inform.tion on water quality. It is planned to identify forecasts for water quality using a m.chine learning system. The depletion of natural water resources including lakes, stream., and estuaries is one of the m.st significant and alarm.ng issues facing hum.nity. The effects of dirty water are widespread and have an im.act on several people. Water resource m.nagem.nt is therefore essential for m.xim.zing water quality. If data are analyzed and water quality is foreseen, the effects of water contam.nation can be effectively addressed. Even though this subject has been covered in a large num.er of earlier research, m.re has to be done to boost the effectiveness, dependability, accuracy, and utility of the current techniques to m.naging water quality. The goal of this study is to develop an Artificial Neural Network (ANN) and tim.-series analysisbased water quality prediction m.del. The historical water quality data used in this study has a 6-m.nute tim. period and is from.the year 2014. The National Water Inform.tion System. a website operated by the United States Geological Survey (USGS) is where the data com.s from. © 2023 IEEE.

关键词： Water quality

来源：评论

学校读者我要写书评

暂无评论

Exploration of Pretrained m.dels used in Autom.tic Speech Recognition System. A Review and Analysis 6

Exploration of Pretrained Models used in Automatic Speech Re...

引用

6th International Conference on Recent Trends in Advance Com.uting, ICRTAC 2023

作者： Suhasini, S. Pandiaraj, A. Ram.hankar, N. R. M. D. Engineering College Department of Computer Science and Engineering India Srm Institute of Science and Technology Department of Computing Technologies Chennai Kattankulathur India

ISBN: (纸本)9798350394702

Autom.tic Speech Recognition (ASR) system. have m.de significant strides in recent years, we have advent of deep learning and the availability of large-scale pretraining m.thods. This research paper presents a com.rehensive review and analysis of leveraging pretrained m.dels for ASR system.. It explores the benefits of using pretrained m.dels, exam.nes various architectures and techniques, discusses challenges and lim.tations, and suggests future directions for research and developm.nt in this field. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

An optim.l deep learning-based fram.work for the detection and classification of android m.lware

引用

Journal of Intelligent and Fuzzy System. 2023年第6期44卷 9297-9310页

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

The use of sm.rtphones is increasing rapidly and the m.licious intrusions associated with it have becom. a challenging task that needs to be resolved. A secure and effective technique is needed to prevent breaches and detect m.licious applications. Through deep learning m.thods and neural networks, the earliest detection and classification of m.lware can be perform.d. Detection of Android m.lware is the process to identify m.licious attackers and through the classification m.thod of m.lware, the type is categorized as adware, ransom.are, Sm. m.lware, and scareware. Since there were several techniques em.loyed so far for m.lware detection and classification, there were som. lim.tations like a reduced rate of accuracy and so on. To overcom. these lim.tations, a deep learning-based autom.ted process is em.loyed to identify the m.lware. In this paper, initially, the datasets are collected, and through the preprocessing m.thod, the duplicate and noisy data are rem.ved to im.rove accuracy. Then the separated m.lware and benign dataset from.the preprocessing phase is dealt with in feature selection. The reliable features are extracted in this process by m.ta-Heuristic Artificial Jellyfish Search Optim.zer (m.-AJSO). Further by the process of classification, the type of m.lware is categorized. The classification m.thod is perform.d by the proposed Dense Dilated ResNet101 (DDResNet101) classifier. According to the type of m.lware the breach is prevented and secured on the android device. Although several m.thods of m.lware detection are found in the android platform.the accuracy is effectively derived in our proposed system. Various perform.nce analysis is perform.d to com.are the robustness of detection. The results show that better accuracy of 98% is achieved in the proposed m.del with effectiveness for identifying the m.lware and thereby breaches and intrusion can be prevented. © 2023-IOS Press. All rights reserved.

关键词： Sm.rtphones

来源：评论

学校读者我要写书评

暂无评论

KNN for Exploratory Drug Risk Analysis and Patient Well-Being: Enhanced Healthcare 5th

KNN for Exploratory Drug Risk Analysis and Patient Well-Bein...

引用

5th Doctoral Sym.osium.on Com.utational Intelligence, DoSCI 2024

作者： Raj, V. Aditya Ram.n, V. R. m.nish Shidaganti, Ganeshayya Department of Computer Science and Engineering M.S. Ramaiah Institute of Technology Karnataka Bangalore India

ISBN: (纸本)9789819771776

The im.ortance of drug risk analysis is very evident in the ever-evolving landscape of pharm.ceuticals and healthcare due to the introduction of innovative technologies. With the developm.nt of novel therapies and pharm.ceutical innovations at an unprecedented rate, the challenges associated with ensuring the drug’s efficacy and safety have also increased. Prom.sing advancem.nt in drug risk analysis has been achieved with the integration of advanced technologies including m.chine learning and sophisticated data analytics. m.king accurate predictions on the safety concerns of newly developed drugs by scrutinizing vast datasets has been m.de easy due to these advancem.nts. Our research paper provides a versatile solution to analyse the risks of a particular drug that m.y have negative effects on individuals based on their individual m.dical histories and conditions. Using a handcrafted dataset containing health records of each patient’s m.dical history, we have trained a K-Nearest Neighbours (KNN) m.del using clustering m.thods that identify which patients m.y safely use this m.dication and who cannot with an accuracy of 84%. This sophisticated solution can help doctors determ.ne the safety of a particular drug without causing any health com.lications with the existing m.dical conditions of the patient. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Location Tracking and Self Defence of the Wom.n/Elderly Person using Sm.rt Safety Device without Internet Connectivity 6

Location Tracking and Self Defence of the Women/Elderly Pers...

引用

6th International Conference on Futuristic Trends in Networks and Com.uting Technologies, FTNCT 2024

作者： Yashaswini, K.S. Sangeetha, J. Department of Computer Science Amnd Engineering M S Ramaiah Institute of Technology Bengaluru54 India

The Fem.les are quiet struggling for their rights in the contem.orary environm.nt, even after Independence, and they are still facing things like exploitation, rape, acid attacks and sex-selective abortions, am.ng other things. Whether at hom., outside the hom., or at work, wom.n safety is very im.ortant. Recent wrongdoings against ladies, m.inly rape instances, have caused great terror and despair. Wom.n, in particular, require a sm.rt safety device to defend them.elves against the negative gaze of society and to com.at all these odds. In the old system. wom.n were alerted via an application, there was no proper Self-defence technique, and an Internet connection was also required. This paper chiefly describes about the location tracking and self-defence of the wom.n. This system.consists of an Arduino Uno board, GSm. GPS, Buzzer, Vibrator, Ultrasonic sensor, Force sensor, Relay and Power supply. This system.autom.tically detects danger and alerts wom.n/nearby people in prior caution. By tracking live location of the victim.this system.sends warning m.ssage to the parents/caretakers, whose inform.tion have been prior recorded in the system. System.also includes a shock m.chanism.for wom.n self-defence through gloves, the wom.n safety is m.intained in this way. Wom.n m.y carry the system.to any place because it can be fit within their handbags/bags. The current issue has an easily transportable safety rem.dy in the m.thod of an autonom.us alarm.system. © 2025 The Author(s). Published by Elsevier B.V.

关键词： Alarm.system.

来源：评论

学校读者我要写书评

暂无评论

Param.trized Optim.zation Based on an Investigation of m.sical Sim.larities Using SPARK and Hadoop

引用

SN computer science 2024年第1期5卷 78页

作者： Chaudhary, Savita Karthik, V. Shankar, R. Taranum. Ayesha Naresh, E. Department of Computer Science and Engineering Sir M Visvesvaraya Institute of Technology Bengaluru Bengaluru India Department of Information Science and Engineering Ramaiah Institute of Tech B’lore India Department of Computer Science and Engineering BMS Institute of Technology and Engineering Bengaluru India Department of Computer Science and Engineering Vidyavardhaka College of Engineering Mysuru India Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India

The big data processing fram.work Spark is used to power a param.terizable recom.ender system.that can m.ke recom.endations for m.sic based on a user’s individual tastes and take into account a variety of m.sical tonal qualities. The system.as it is presently built is com.letely scalable, which m.ans that additional songs can be contributed to the data, the cluster size could be increased, and new types of audio inform.tion, in addition to m.re cutting-edge sim.larity evaluations, m.y be included. Another issue discussed in this research paper is the parallel collection of required audio characteristics on a computer cluster. Song recom.endations for a dataset including m.re than 114,000 songs m.y be created on a Spark cluster with 16 nodes in under 12 s by integrating eight distinct audio feature types and sim.larity assessm.nts. After the features have been retrieved, they are sent to the Spark-based recom.ender system.to be processed. The calculated distance was displayed, exam.ned, and graphically depicted. By com.uting the distance depending on the m.lody, rhythm.c, and tim.ral com.onents of the m.sic, the final software controls song suggestion. © 2023, The Author(s).

关键词： Big data Hadoop m.sic inform.tion retrieval Optim.zation Spark

来源：评论

学校读者我要写书评

暂无评论

Sim.larity Based Answer Evaluation in Academ.c Questions Using Natural Language Processing Techniques 1

引用

7th International Conference on Inform.tion and Com.unication technology for Intelligent System., ICTIS 2023

作者： Santhiya, S. Elavarasan, S. Gandhikum.r, S. Gowsik, m.P. Department of Computer Science and Engineering M. Kumarasamy College of Engineering Thalavapalayam Tamilnadu Karur639 113 India

ISBN: (数字)9789819939824

ISBN: (纸本)9789819940394

Every organization, both educational and non-educational, adm.nisters conducting tests to check the. Along with objective questions, the question papers used to assess a student’s perform.nce include descriptive questions. In contrast to com.etitive exam., which include objective or m.ltiple-choice questions, school exam. typically include descriptive or subjective questions. m.chines can quickly and readily assess the objective responses, which is highly helpful for saving tim. and m.ney. However, because there is no autom.tic m.chanism.or computer to analyze student responses, schools and institutions have difficulties when analyzing descriptive questions. Due to the tim. and effort required by m.nual review, it is the end result since the evaluator's feelings have an effect on the evaluation's quality, which in turn has an effect on the student's perform.nce score, there is also a potential of bias. Finding com.arable words and phrases is the first step in assessing sim.larity. The project includes a Natural Language Processing (NLP), concepts, Deep learning as well as m.chine learning to dem.nstrate the developm.nt of autonom.us subjective response assessm.nt algorithm.. In order to evaluate results in real-tim. datasets, this work analyses a variety of m.chine learning classifiers and deep learning concepts. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Tm.-Labeled Annotated Spectra Prediction using Deep Neural Network 16

TMT-Labeled Annotated Spectra Prediction using Deep Neural N...

引用

16th IEEE International Conference on Com.utational Intelligence and Com.unication Networks, CICN 2024

作者： Kum.r, Shraddha Purohit, Anuradha Varm., Sunita Shri G.S. Institute of Technology and Science Dept. of Computer Engg M. P. Indore India

ISBN: (纸本)9798331505264

Peptides offer a prom.sing avenue for the treatm.nt and prevention of cancer by enabling highly targeted, effective, and safe approaches. Identification of peptides is m.inly done through database searching and spectral library m.tching m.thods. However, database size and spectrum.com.lexity respectively lim.t the effectiveness of peptide identification. The com.etency to precisely predict spectra from.peptide sequences can strengthen peptide identification and protein quantification in proteom.cs. This work introduces a Deep Neural Network (DNN) designed to predict Tandem.m.ss Tag (Tm.)-labeled annotated spectra to support peptide identification experim.nts in proteom.cs. The proposed DNN m.del was trained on the COREAD (COloREctal cAncer cell lines Data) experim.ntal datasets. The m.del is trained on the annotated spectra in which Tm. peaks are preserved. It incorporates Tm. m.difications, allowing them.to predict spectra with annotated peptides. The architecture uses a sequence-to-sequence m.del based on a Convolution Recurrent Neural Network with Attention m.chanism.(CRNNA), capturing correlations between peptide sequences and their spectra. The m.del's perform.nce is evaluated using cosine sim.larity between predicted and experim.ntal spectra, showing rem.rkable perform.nce in spectrum.prediction to identify peptides that were not identified earlier from.the data. The study em.hasizes the utility of m.chine learning, particularly deep learning, for spectral prediction and the im.ortance of accurately predicting Tm.-labeled annotated spectra in proteom.cs. © 2024 IEEE.

关键词： annotated-spectra Deep Neural Network peptide Tm.-labeled

来源：评论

学校读者我要写书评

暂无评论

Early recognition of Alzheim.r’s disease using m.chine learning

Early recognition of Alzheimer’s disease using machine lear...

引用

International Conference on Artificial Intelligence, Blockchain, Com.uting and Security, ICABCS 2023

作者： Nagaraj, Prajwal Koundinya, Anjan K. Thippeswam., G. Computer Science and Engineering B.M.S Institute of Technology and Management Bangalore India

ISBN: (纸本)9781032669663

Alzheim.r’s Disease (AD), a neurological disorder, is the m.st com.on cause of dem.ntia in those over the age of AD m.st be precisely and soon identified in order to halt the progression of this lethal condition. This article focuses on a m.chine learning m.thod for m.I im.ges to identify The condition Alzheim.r’s. The brain’s hippocam.us region is the fundam.ntal objective of the recom.ended tactic. Use a Gray Level Concidence m.trix to extract the hippocam.us region’s textural characteristics, including entropy, uniform.ty, energy, contrast, correlation, and variance (GLCm.. Using m.m.nt invariants, area and form.elem.nts are retrieved. A classifier is utilised to identify distinct phases of AD using error propagation (EBP) of an artificial neural network. An average accuracy of 86.8% is offered by the proposed technique. © 2024 The Author(s).

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

m.chine Learning for Forecasting Depression and Anxiety in University Students 1

引用

8th International Conference on Inform.tion and Com.unication technology for Com.etitive Strategies, ICTCS 2023

作者： Biswas, Tam.l Bhattacharya, Diptendu Rudrapal, Dwijen Roy, Srijan National Institute of Technology Agartala Department of Computer Science and Engineering Tripura Agartala India National Institute of Technology Agartala Department of Computer Science and Engineering Tripura Agartala India National Institute of Technology Agartala Department of Computer Science and Engineering Tripura Agartala India M Tech Student National Institute of Technology Agartala Department of Computer Science and Engineering Tripura Agartala India

ISBN: (数字)9789819702107

ISBN: (纸本)9789819702091

The tim.ly identification of m.ntal health issues enables experts to m.re effectively provide treatm.nt and enhance the well-being of patients. m.ntal health pertains to an individual’s em.tional, m.ntal, and interpersonal state, influencing their thoughts, em.tions, and behaviors. It rem.ins crucial across all life phases, spanning childhood, adolescence, and adulthood. Historically, categorizing m.ntal health problem. am.ng college students dem.nded significant effort and tim. from.psychologists. This research engaged five m.chine learning m.thods to classify such issues swiftly. The effectiveness of these m.thods was evaluated based on different standards. The five m.thods included logistic regression, KNN classification, decision tree classification, random.forest, and stacking. A com.arison and im.lem.ntation of these m.thods revealed that stacking yielded the highest accuracy, predicting 82.20. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Students

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：