检索结果-内蒙古大学图书馆

IoT-Based Water Quality Monitoring and Detection System 1

2nd International Conference on Emerging Trends in Expert Applications and Security, ICETEAS 2023

作者： Kanchana, M. Gopirajan, P.V. Sureshkumar, K. Sudharsanan, R. Suganthi, N. Department of Computing Technologies School of Computing SRM Institute of Science and Technology Kattankulathur Chennai603203 India Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Kattankulathur Campus Chennai603203 India Department of Information Technology Saveetha Engineering College Chennai602105 India Department of Information Technology SRM Institute of Science and Technology Ramapuram Chennai600089 India Department of Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Chennai600089 India

ISBN: (数字)9789819919093

ISBN: (纸本)9789819919086

This paper suggests Internet of things (IoT) and Arduino-based tele-water quality monitoring systems integrated with the web application. The most critical component of the Wireless Sensor Network includes a microcontroller for processing the circuit's sensor data, a communication system between and within node communication, and a few other sensors such as pH, Microbial Fuel Cell (MFC), humidity, and temperature. All data is collected at the Arduino (data which is sensed by the sensors) by using remote monitoring and Internet of things technology (ESP8622MOD). The real-time data is transmitted, and that data is displayed by sending through the cloud in a human interface format on a server device (pc/mobile) by the web or mobile applications. The main objective is to get a water monitoring system with high mobility (the ability to check water more freely, the ability to check wherever required), high frequency, and low power (as it is compatible, we can take and check quickly). Therefore, our main objective is that our system will immensely help people with small water reservoirs, water mines, and villagers/ framers with fields to become conscious/aware of polluted water and stop contaminating the water. The deciding parameters of water, whether toxic or drinkable, are decided by the potential level of hydrogen value. If the hydrogen value is less than five, it is acidic, and if the hydrogen value is above 7.5, then it is primary. The MFC sensor, if the analogy sensor, senses any electricity from the cathode and anode ends (0–200 indicates acidic water, 200–300 is normal water, and above 300 is essential to water);by this water, we decide whether water toxic in nature and temperature and humidity also plays a role in determining the quality, it can result in an effect on the level of O2. Also, the capacity of organisms to resist certain pollutants, so different conditions should have different water temperatures. © 2023, The Author(s), under exclusive license to Spr

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Estimation of Deforestation Rate and Forest Land Use Land Cover Change Detection

Estimation of Deforestation Rate and Forest Land Use Land Co...

引用

2023 International Conference on Artificial Intelligence and Knowledge Discovery in Concurrent engineering, ICECONF 2023

作者： Kalaiyarasi, M. Saravanan, S. Balaji, R. Karthi, S. Rao, D.S. Naga Malleswara Sireesha, D. Nagineni Venkata Department of Computational Intelligence Saveetha School of Engineering Simats Chennai India B v Raju Institute of Technology Narsapur Telangana India Department of Computer Science and Engineering V.S.B. Engineering College Karur India Gokaraju Rangaraju Institute of Engineering and Technology Hyderabad India Department of Information Technology Institute of Aeronautical Engineering Telangana Hyderabad India

ISBN: (纸本)9798350334357

Amazon area is important for global energy, hydrology, and carbon balance. Amazon covers 5.5 million km2. Between 1976-2003, 7.3% of the Amazon was deforested, and 2.6% amid 2000-2010, PRODES monitors Amazon deforestation using satellite imagery. The yearly deforestation rate is anticipated based on the growth of desertification in Brazilian Amazon satellite images. According to INPE and FAO, 768,935 km2 of Amazon Basin have been deforested. In this paper, the deforestation rate and the Forest Land Use Land Cover change has been detected using SAGA GIS. Business As Usual (BAU) Scenario is used to find the rate. As indicated by BAU scenario in the result, Amazon rainforest could be diminished to 43.26% and the overall timberland misfortune would be 38.45% towards the end of 2050. © 2023 IEEE.

关键词： Deforestation

来源：评论

学校读者我要写书评

暂无评论

Distributed Nash equilibrium for pursuit-evasion game with one evader and multiple pursuers

引用

science China(Information sciences) 2025年

作者： Libing WANG Zhixin LIU Shuo YUAN Zhiqiang PU Key Laboratory of Systems and Control Academy of Mathematics and Systems ScienceChinese Academy of Sciences School of Mathematical Sciences University of Chinese Academy of Sciences Department of Electrical and Computer Engineering Wayne State University Institute of Automation Chinese Academy of Sciences

This paper investigates the pursuit-evasion problem involving one evader and multiple pursuers with limited sensing capability, where the evader tries to maximize the distance with the pursuers, while the pursuers have different objectives based on whether they can receive the information of the evader. The subgroup of pursuers who can observe the evader(called leaders) tries to be close to the evader, and the other subgroup of pursuers(called followers) tries to synchronize with their neighbors. When the subgraph formed by all leaders is complete, sufficient conditions are given to guarantee that the pursuers capture the evader and the pursuit-evasion game composed of the evader and leaders reaches Nash equilibrium. Furthermore, for the incomplete subgraph case, the distributed observers are proposed to estimate the relative positions between the evader and all leaders. It is shown that the distributed control strategy based on the observers converges exponentially to the Nash equilibrium solution, and makes the pursuers capture the evader. Finally, simulation examples are provided to verify the effectiveness of the proposed strategies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Complexity of Approximate Pattern Matching on de Bruijn Graphs 26th

The Complexity of Approximate Pattern Matching on de Bruij...

引用

26th International Conference on Research in computational Molecular Biology, RECOMB 2022

作者： Gibney, Daniel Thankachan, Sharma V. Aluru, Srinivas School of Computational Science and Engineering Georgia Institute of Technology Atlanta United States Department of Computer Science University of Central Florida Orlando United States

ISBN: (纸本)9783031047480

Aligning a sequence to a walk in a labeled graph is a problem of fundamental importance to computational Biology. For finding a walk in an arbitrary graph with |E| edges that exactly matches a pattern of length m, a lower bound based on the Strong Exponential Time Hypothesis (SETH) implies an algorithm significantly faster than O(| E| m) time is unlikely [Equi et al., ICALP 2019]. However, for many special graphs, such as de Bruijn graphs, the problem can be solved in linear time [Bowe et al., WABI 2012]. For approximate matching, the picture is more complex. When edits (substitutions, insertions, and deletions) are only allowed to the pattern, or when the graph is acyclic, the problem is again solvable in O(| E| m) time. When edits are allowed to arbitrary cyclic graphs, the problem becomes NP-complete, even on binary alphabets [Jain et al., RECOMB 2019]. These results hold even when edits are restricted to only substitutions. Despite the popularity of de Bruijn graphs in computational Biology, the complexity of approximate pattern matching on de Bruijn graphs remained open. We investigate this problem and show that the properties that make de Bruijn graphs amenable to efficient exact pattern matching do not extend to approximate matching, even when restricted to the substitutions only case with alphabet size four. Specifically, we prove that determining the existence of a matching walk in a de Bruijn graph is NP-complete when substitutions are allowed to the graph. In addition, we demonstrate that an algorithm significantly faster than O(| E| m) is unlikely for de Bruijn graphs in the case where only substitutions are allowed to the pattern. This stands in contrast to pattern-to-text matching where exact matching is solvable in linear time, like on de Bruijn graphs, but approximate matching under substitutions is solvable in subquadratic O~(nm) time, where n is the text’s length [Abrahamson, SIAM J. Computing 1987]. © 2022, The Author(s), under exclusive license t

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Bottleneck-minimal indexing for generative document retrieval 24

Bottleneck-minimal indexing for generative document retrieva...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Xin Du Lixin Xiu Kumiko Tanaka-Ishii Waseda Research Institute for Science and Engineering Waseda University Department of Mathematical Informatics The University of Tokyo Department of Computer Science and Engineering Waseda University

We apply an information-theoretic perspective to reconsider generative document retrieval (GDR), in which a document x ∈ Χ is indexed by t ∈ Τ, and a neural autoregressive model is trained to map queries Q to Τ. GDR can be considered to involve information transmission from documents X to queries Q, with the requirement to transmit more bits via the indexes Τ. By applying Shannon's rate-distortion theory, the optimality of indexing can be analyzed in terms of the mutual information, and the design of the indexes Τ can then be regarded as a bottleneck in GDR. After reformulating GDR from this perspective, we empirically quantify the bottleneck underlying GDR. Finally, using the NQ320K and MARCO datasets, we evaluate our proposed bottleneck-minimal indexing method in comparison with various previous indexing methods, and we show that it outperforms those methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

User Detection in Smartphones Using Voting and Stacking Classifiers 1

User Detection in Smartphones Using Voting and Stacking Clas...

引用

1st IEEE International Interdisciplinary Humanitarian Conference for Sustainability, IIHC 2022

作者： Faheem Nikhat, H. Sait, Saad Yunus Vashist, Kartik Sharma, Mohit SRM Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Kattankulathur603203 India SRM Institute of Science and Technology Department of Computational Intelligence Tamil Nadu Kattankulathur603203 India

ISBN: (纸本)9781665456876

The objective is to facilitate restricted content delivery to users of age 3-12 years thereby ensuring irrelevant content is filtered out. Living in an era driven by technology where Smartphones take a lion's share of time, the probability of being served with harmful, sensitive, or obscene content is on the higher side. To bring this down, this research have come up with a model that can help assure relevant content is served upon request, when used by children. This study have leveraged Stacking and Voting algorithms to segregate the users based on tap, swipe, etc., Hyperparameter tuning has also been leveraged on these algorithms to achieve better results. It has been noticed that the ANN algorithm provides better accuracy of 97.43 % by considering all the features and stacking produces 96% accuracy using Euclidean distance on the features such as tap and swipe on the dataset. Stacking produces 94.4% accuracy by combining all the features from the task such as tap, swipe, slide, rotation, and zoom in and out on the dataset. © 2022 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Analyzing Adaptive Intrusion Detection Systems for Improved Network Security 2

Analyzing Adaptive Intrusion Detection Systems for Improved ...

引用

2nd International Conference on Advances in Computation, Communication and Information Technology, ICAICCIT 2024

作者： Sharma, Nandan Jaggi, Arjun Takkalapally, Prashamsh Hudani, Karim Natarajan, Yuvaraj BC Public Service VictoriaBC Canada HCLTech San DiegoCA United States Department of Engineering Computing and Mathematical Sciences Lewis University United States Tampa FL United States Department of Computer Science Engineering Sri Shakthi institute of engineering and technology Tamil Nadu Coimbatore India

ISBN: (纸本)9798331541217

Analyzing adaptive intrusion detection systems (AIDs) ought to doubtlessly growth network security doubtlessly by imparting businesses with early detection, mitigation, and threat response capabilities. AIDs uses diverse strategies to hit upon malicious conduct, which includes gadget mastering algorithms, signature-based evaluation, and anomaly detection. Moreover, AIDs can take additional action so as to block, quarantine, or alert the perfect events while malicious interest is recognized. This paper examines the modern state of AIDs, its blessings, and disadvantages, and proposes feasible methods to enhance current technology. A dialogue on how device studying can be used to enhance the accuracy of AIDs is blanketed, as well as recommendations for companies while building or deploying a machine. In the end, the paper outlines capability regions of future research that would cause further advances in AIDs and network security. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Improved Metaheuristics with Deep Autoencoders for COVID-19 Detection and Classification 2

Improved Metaheuristics with Deep Autoencoders for COVID-19 ...

引用

2nd International Conference on Electrical, Electronics, Information and Communication Technologies, ICEEICT 2023

作者： Assudani, Manish K Nirmala, B. Kanimozhi, N. Chandre, Shanker Sunalini, K.K. Gopatoti, Anandbabu G H Raisoni University Department of Computer Science and Engineering Maharashtra Amravati India Sri Ramachandra Institute of Higher Education and Research Sri Ramachandra Faculty of Engineering and Technology Department of Computer Science and Engineering Chennai India School of Computing SRM Institute of Science and Technology Department of Computational Intelligence Tamil Nadu Chennai India SR University Department of Computer Science & Artificial Intelligence Telangana Warangal India Koneru Lakshmaiah Education Foundation Department of English Andhrapradesh Guntur India Hindusthan College of Engineering and Technology Department of Electronics and Communication Engineering Tamil Nadu Coimbatore India

ISBN: (纸本)9798350397635

A healthcare monitoring system requires the support of current technologies like big data, artificial intelligence (AI), and machine learning (ML), particularly during the outbreak of COVID19. This pandemic caused millions of death worldwide. ML and AI are used to detect and combat COVID19 in the initial phase. Deep learning refers to a subdivision of ML that utilizes NN for making predictions and learning from data. In the context of COVID19 detection, deep learning (DL) methods can be trained for examining medical images like CT scans and chest X-rays and identify the presence of virus. This study presents an improved whale optimization algorithm with deep autoencoder (IWOA-DAE) algorithm for COVID-19 detection and classification. The presented IWOA-DAE technique makes use of DL model with metaheuristic hyperparameter optimizer for COVID-19 classification. To accomplish this, the IWOA-DAE technique employs bilateral filtering (BF) process to eliminate noisy data. Next, the IWOA-DAE technique uses NASNetLarge model for feature vector generation purposes. For COVID-19 detection, the IWOA-DAE technique uses deep autoencoder (DAE) model with IWOA based optimal hyperparameter adjustment process. To highlight the improved performance of the IWOA-DAE algorithm, a wide-ranging simulation analysis takes place. The simulation outcomes highlighted the enhanced performance of the IWOA-DAE technique over other methods. © 2023 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Melady Classification Enhancing Accuracy with Supervised Learning Methods

Melady Classification Enhancing Accuracy with Supervised Lea...

引用

Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), International Conference on

作者： M. S. Roobini Bodapati Sohan Chidvilas Gowri Manohari Babu K S. Praveen Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Department of Computational Intelligence SRM Institute of Science and Technology

About one person dies every minute from heart disease, consequently, it has surpassed war as the largest cause of death in the twenty-first century. This includes both the male and female demographics, as well as the ratio may fluctuate depending on age bracket & sex. Nothing here suggests that persons of various ages are immune to cardiovascular disease. Classifying the underlying causes and diseases associated with this condition has become more difficult in recent years. In this study, we explore the different classification methods and the Flask Framework used for cardiac illness. As a result, it is drawing attention as a "fatal disease" that may kill a person in the absence of any outward signs of illness. Particularly important in cardiology, early and accurate diagnosis of heart illness is a cornerstone of effective healthcare. Classifying cardiac illness might be difficult at times because of a general lack of funds in the healthcare profession. The medical community and their patients stand to gain a great deal by making use of appropriate technological help in this area. This problem may be handled by using Data science methodologies. There are now established tendencies in Data science, and a wide range of research is being conducted in this area. This research seeks to apply the RF, KNN, Naive Bayes algorithm techniques to create a classifier model for the of Cardiovascular disease. We opted for the Flask framework in bringing to life our ingenious plan. This makes it easier to label needed values straight on the page thanks to HTML and CSS, marrying our pre-created models accurately to selected variables. What's great is the website's inviting user-friendly structure. Its well-structured layout simplifies deciphering categorized values. Plus, one major charm of our optimized site is that it helps users promptly get an insight into the status of an illness even before it's fully blown.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AI-Driven CASGN Framework for Evaluating Descriptive Answers in Online Education

AI-Driven CASGN Framework for Evaluating Descriptive Answers...

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Sridevi Ponmalar, P. Vinodini, S. Srithar, V. Morankar, Gouri Jebaseelan, S. D. Sundarsingh Harikrishnan, R. School of Computing Srm Institute of Science and Technology Department of Computational Intelligence Kattankulathur Chennai India Chennai600119 India PeriyarManiammai Institute of Science & Technology Department of Computer Applications Vallam Thanjavur India Shri Ramdeobaba College of Engineering and Management Nagpur India Sathyabama Institute of Science and Technology Department of Eee Chennai119 India Symbiosis Institute of Technology Symbiosis International Deemed University Pune Campus Pune412115 India

ISBN: (纸本)9798331543617

There is an enormous demand for automated assessment systems, which can handle the bulk assessments efficiently and effectively. While existing systems perform well in grading objective questions, they break down with subjective or descriptive answers that require a deeper analysis of context and understanding. To address this challenge, we have proposed the AI-Enhanced Context-Aware Semantic Grading Network-state-of-the-art algorithm for instant auto-descriptive response scoring in e-assessments. The AI-CASGN utilizes state-of-the-art AI technologies, particularly NLP and deep learning models-very specifically transformer architectures-during context-based semantic analysis. Beyond mere keyword matching, the system scores what students say and how relevant it is. This takes the concept of grading to an even more fine-tuned art. Scores change with depth and accuracy in the answer given to show complete evaluation. With the dynamic grading framework, adaptation on scores both regarding the accuracy and depth of the answer for a precise evaluation is possible. Inbuilt adaptive learning within the system performance evolves day by day by learning from the new data. AI-CASGN is designed to handle biases in mitigation by considering that there may be different patterns for a response to ensure that responses with varied wording but conceptually correct are fairly graded. It will have to deal with the volumes at scale, hence it is envisaged to process large volumes of responses in minimum time and with high accuracy to be deployed in real time in any educational institution. In future, the system will also provide personalized feedback to students for the purpose of continuous learning and improvement. This represents a scalable, real-time, unbiased tool that assesses subjective answers in modern online learning environments. © 2024 IEEE.

关键词： Semantics

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：