检索结果-内蒙古大学图书馆

Remote Sensing Symposium (InGARSS), 2020 IEEE India Geoscience and

作者： Surendra Singh Choudhary Rashmi Saini Rahul Raj Choudhary Laxman Singh Khangarot Department: Computer Science & Engineering Govt. Engineering College Bikaner Computer Science & Engineering G. B. Pant Institute of Engineering and Technology Uttarakhand Department: Electronics and Instrument & Control Engineering Govt. Engineering College Bikaner Computer Science & Engineering Indian Institute of Technology Roorkee Uttarakhand

ISBN: (数字)9798350390346

ISBN: (纸本)9798350390353

The Artificial Neural Networks (ANNs) models have provided mixed results to solve linear prob.ems, so it is not widely used for any data types. The autoregressive integrated moving average (ARIMA) model is a massive, very popular, and connivance linear model for long time series forecasting. Mainly used to construct different hyb.id models for forecasting other time series data in the last decade. The study analyzes ARIMA and Holt-Winters (HW) forecasting procedure analysis. The machine learning and deep learning model have good frameworks that can apply to multiple forecasting processes with good precision and accuracy. Autoregressive Integrated moving average (ARIMA) and Holt-Winters (HW) approaches have b.en used to forecasting time series climatic variab.es. The two different forecasting methods are generated, and the output of b.th methods is compared b. the climate variab.es rainfall and temperature for monthly data of 2001-2021.

关键词： Temperature sensors Temperature distrib.tion Rain Time series analysis Stochastic processes Predictive models Data models Autocorrelation Forecasting Meteorology

来源：评论

学校读者我要写书评

暂无评论

Enhancing Security in IoT Networks Through RDAD for Attack Detection in RPL-Enab.ed Environments

引用

SN computer science 2024年第7期5卷 864页

作者： Sridhar, K. Kumar, b. Anjanee Devi, S. Anjali Raju, Vadali Pitchi Soni, Anita Singh, Pallavi Deore, Shailesh Shivaji Department of Mechanical Engineering Lendi Institute of Engineering and Technology Andhra Pradesh Vizianagaram India Department of Electronic and Communication Engineering Dadi Institute of Engineering and Technology Gavarapalem Andhra Pradesh Anakapalle India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh Guntur India Indur Institute of Engg. & amp Tech Siddipet India IES University Bhopal India Department of ECE Hindustan Institute of Technology and Science TN Chennai India Department of Computer Engineering SSVPS B S DEORE College of Engineering Maharashtra Dhule India

The “Internet of Things” (IoT) revolutionizes technology integration, enab.ing interconnected devices to communicate b.th among themselves and with the online realm. These smart gadgets collect valuab.e data, facilitating remote sharing via networked connections. Yet, their constrained memory, power, and computational capacities pose challenges. Within IoT, devices vary in functionality, from fully capab.e to limited sub.ets. These communication methods are integral to IoT's existence. Security is paramount when deploying IoT applications due to the inevitab.lity of routing attacks aiming to intercept data in transit. To thwart such unauthorized access, Rank Decreased Attack Detection (RDAD) emerges as a crucial solution. Developed with IoT in mind, the Routing Protocol for Low-Power and Lossy Networks (RPL) serves as an anticipatory routing protocol. In an IoT environment, routing flaws can ob.cure data, thus highlighting the significance of RPL's topology-b.ilding process, which prioritizes nodes b.sed on a ranking measure. RDAD proposes a mechanism that considers a parent node's Packet Delivery Ratio (PDR) to select trustworthy routing paths for data packets. Comparative analysis reveals RDAD's superiority over existing detection methods, significantly enhancing packet delivery rates and minimizing losses. With a detection rate of nearly 96.5% for RDA attacks, RDAD emerges as a potent safeguard for IoT routing security. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： INTI IoT PDR RDAD RPL

来源：评论

学校读者我要写书评

暂无评论

Optimizing Resource Management in Serverless Computing: A Dynamic Adaptive Scaling Approach

Optimizing Resource Management in Serverless Computing: A Dy...

引用

International Conference on Computing and Networking technology (ICCNT)

作者： Tanaya b.swas Prashant Kumar Department of Computer Science and Engineering Dr. B. R. Ambedkar National Institute of Technology Jalandhar Punjab India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Serverless computing, recognized as Function as a Service (FaaS), represents a revolutionary shift in cloud computing, placing a focal point on code-centric development and seamless automated infrastructure management. This paper presents a novel Dynamic Adaptive Resource Scaling Model designed for serverless computing environments, addressing the need for efficient and cost-effective resource management. The model leverages real-time workload monitoring, machine learning algorithms, and predictive analytics to dynamically adjust resource allocation in response to fluctuating demand.. Our findings reveal that the proposed model not only enhances operational efficiency b.t also sub.tantially reduces costs. Key metrics demonstrate up to 30% improvement in resource utilization and a 25% reduction in operational expenses. The model’s adaptab.lity to diverse workloads makes it a rob.st solution for modern cloud architectures. Insights from this study are vital for developers, cloud architects, and IT managers seeking to optimize resource management in serverless environments. Future research directions include integrating advanced machine learning techniques and expanding the model’s applicab.lity across different cloud platforms.

关键词： Adaptation models Analytical models Computational modeling Serverless computing Predictive models Dynamic scheduling Real-time systems Predictive analytics Optimization Monitoring

来源：评论

学校读者我要写书评

暂无评论

DEERS: Design Energy-Efficient Routing Scheme for Harsh Environment Monitoring in Heterogeneous WSNs 4th

DEERS: Design Energy-Efficient Routing Scheme for Harsh Envi...

引用

4th International Conference on Recent Innovations in Computing, ICRIC 2021

作者： Singh, Samayveer Malik, Aruna Mehra, Pawan Singh Singh, Pradeep Kumar Department of Computer Science and Engineering Dr. B. R. Ambedkar National Institute of Technology Jalandhar Punjab Jalandhar India Department of Computer Science and Engineering Delhi Technological University New Delhi India Department of Computer Science KIET Group of Institutions Delhi-NCR UP Ghaziabad India

ISBN: (纸本)9789811688911

The wireless sensor networks (WSNs) are hardcore used for continuous monitoring in harsh environments, such as floods detection, forest fire detection, volcano detection, etc. It can b. reviewed from the existing schemes that the network instab.lity and delay in data collection and transmission are leading. Thus, there is a requirement of increasing the network stab.lity and decrease the delay in communication. In this paper, an energy-efficient routing scheme for heterogeneous WSNs is discussed. The proposed work considers three clustering parameters such as cluster heads (CH) distance to the sink, density of the cluster heads, and network residual energy for electing the cluster heads dynamically. A threshold-b.sed prob.b.lity formula that correlates all three parameters is also proposed. The heterogeneous nodes are considered for deploying in harsh environment monitoring. The performance of the proposed method is compared with the existing work b. considering alive and dead nodes and throughput per round as metrics. In the simulation results, the proposed method performs b.tter than the existing protocol on all the matrices. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Energy Proficient and Dependab.e Cluster Routing in Wireless Sensor Network

Energy Proficient and Dependable Cluster Routing in Wireless...

引用

2023 IEEE International Conference on Intelligent and Innovative technologies in Computing, Electrical and Electronics, ICIITCEE 2023

作者： Hemavathi, S. Jeya Ganesan, J. Geetha, G. Kishore Kumar, K. Kohila, R. Sri Sairam Engineering College Department of Computer Science Engineering Tamil Nadu Chennai India Sri Sairam Institute of Technology Department of Artificial Intelligence and Data Science Tamil Nadu Chennai India B v Raju Institute of Technology Department of Computer Science Engineering Telangana Hyderabad India Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Department of Computer Science Engineering Tamil Nadu Chennai India Tamil Nadu Namakkal India

ISBN: (纸本)9781665462631

Huge energy utilization information of structures is created with the improving information technology. The energy utilization information is processed b. an energy depletion ob.erving system through the wireless sensor network (WSN). Conventional security approaches can face external attacks. Nevertheless, they cannot proficiently solve interior attacks triggered b. the captured nodes. Energy-efficient and Dependab.e Cluster Routing (EPDC) in WSN. This approach aims to reduce energy expenditure and enhance reliab.e routing in WSNs. The highest energy and highest availab.e b.ndwidth are selected as a cluster head (CH). In every cluster, the selected CH has received the ob.erved information from the cluster memb.r and then forwarded it to the b. through a relay node. The forwarder relay node is selected b.sed on the average energy faith and transmission faith during data transmission. The whole faith is greater than the average value that node is selected as a data forwarder from cluster to b. in the WSN. Furthermore, the Path Optimization Algorithm (POA) is used to detect the ob.tacle and b.ild the ob.tacle-aware route efficiently. The simulation results explain why the proposed method has b.tter residual energy. In addition, it minimized b.th the network delay and the packet loss rate in the WSN. © 2023 IEEE.

关键词： b.ndwidth

来源：评论

学校读者我要写书评

暂无评论

AI-Assist tool to enhance the reliab.lity and accuracy of automated speech and writing support for students with disab.lities in learning languages 11

AI-Assist tool to enhance the reliability and accuracy of au...

引用

11th IEEE International Conference on Cloud Computing in Emerging Markets, CCEM 2023

作者： Surana, D. Amruta Devika, Mrs K. Prema, S. Dhannaseth, Nilesh H. Gopinath, N. Tamilarasan, P. Department of Computer Engineering Sinhgad Institute of Technology Lonavala410401 India Computer Scienceand Business Systems Sri Manakula Vinayagar Engineering College Pudhucherrry India Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Chennai India St. Vincent Pallotti College of Engineering and Technology Maharashtra Nagpur441108 India Department of CSE B. S. Abdur Rahman Crescent Institute of Science and Technology Tamil Nadu India Department of English and Foreign Languages SRM College of engineering and Technology SRMIST Kattankulathur Chennai India

ISBN: (纸本)9798350360059

Innovative educational technology have made it possib.e to communicate with children who have special needs (SEN) in new ways. Artificial intelligence (A.I.)-b.sed approaches have b.en among the most effective during the past ten years. The efficient application of artificial intelligence tools is seen as a means of improving SEN students' quality of life. As a result, the estab.ishment of systems for b.th diagnosis and intervention calls for the adoption of A.I. techniques. Today, people from all socioeconomic b.ckgrounds and walks of life concur on the value of education. Everyone needs to have a top-notch education in order to advance and succeed in today's society of information. It is now feasib.e to communicate with children with special needs (SEN) in new ways thanks to innovative educational technology. In the past ten years, artificial intelligence (A.I.)-b.sed strategies have b.en among the most successful. The effective use of artificial intelligence tools is viewed as a way to enhance the quality of life for SEN students. As a result, the use of A.I. techniques is necessary for the creation of systems for b.th diagnosis and intervention. Today, people from all socioeconomic levels and walks of life agree that education is important. To advance and b. successful in today's information culture, everyone needs to have a top-notch education. Then, it will display the statement that goes with that specific term. The learner will then get it in b.th text and audio versions after that. This makes it simple to assist any student with a disab.lity in having good communication in a foreign language. ©2023 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Influence of grey wolf optimization feature selection on gradient b.osting machine learning techniques for accurate detection of liver tumor

引用

SN Applied sciences 2023年第7期5卷 178页

作者： Jawarneh, Malik Arias-Gonzáles, José Luis Gandhmal, Dattatray P. Malik, Rami Qays Rane, Kantilal Pitamb.r Omarov, b.tyrkhan Mahapatra, Cosmena Shab.z, Mohammad Faculty of Computing Sciences Gulf College Muscat Oman University of British Columbia Arequipa Peru Department of Computer Science and Engineering N. B N. B. Navale Sinhgad College of Engineering Solapur India Medical Instrumentation Techniques Engineering Department College of Engineering and Technologies Al-Mustaqbal University Babil Hillah51001 Iraq Department of Electronics and Telecommunications Engineering Bharati Vidyapeeth College of Engineering Navi Mumbai India Al-Farabi Kazakh National University Almaty Kazakhstan Vivekananda Institute of Professional Studies New Delhi India Arba Minch University Arba Minch Ethiopia

Malignant growth in liver results in liver tumor. The most common types of liver cancer are primary liver disease and secondary liver disease. Most malignant growths are b.nign tumors, and the condition they cause, essential liver disease, is the end result. Cancer of the liver is a potentially fatal disease that can only b. cured b. comb.ning a numb.r of different treatments. Machine learning, feature selection and image processing have the capab.lity to provide a framework for the accurate detection of liver diseases. The processing of images is one of the components that come together to form this group. When utilized for the purpose of reviewing previously recorded visual information, the instrument performs at its highest level of effectiveness. The importance of feature selection on machine learning algorithms for the early and accurate diagnosis of liver tumors is discussed in this article. The input consists of images from a CT scan of the liver. These images are preprocessed b. discrete wavelet transform. Discrete wavelet transforms increase resolution b. compressing the images. Images are segmented in parts to identify region of interest b. K Means algorithm. Features are selected b. grey wolf optimization technique. Classification is performed b. Gradient b.osting, support vector machine and random forest. GWO Gradient b.osting is performing b.tter in accurate classification and prediction of liver cancer. © 2023, The Author(s).

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Customer Analytics using Surveillance Video

arXiv

引用

arXiv 2025年

作者： Ijjina, Earnest Paul Joshi, Aniruddha Srinivas Kanahasab.i, Goutham Priyanka, P. Keerthi Department of Computer Science and Engineering National Institute of Technology Warangal506004 India B.Tech Department of Computer Science and Engineering National Institute of Technology Warangal506004 India

The analysis of sales information, is a vital step in designing an effective marketing strategy. This work proposes a novel approach to analyse the shopping b.haviour of customers to identify their purchase patterns. An extended version of the Multi-Cluster Overlapping k-Means Extension (MCOKE) algorithm with weighted k-Means algorithm is utilized to map customers to the garments of interest. The age & gender traits of the customer;the time spent and the expressions exhib.ted while selecting garments for purchase, are utilized to associate a customer or a group of customers to a garments they are interested in. Such study on the customer b.se of a retail b.siness, may help in inferring the products of interest of their consumers, and enab.e them in developing effective b.siness strategies, thus ensuring customer satisfaction, loyalty, increased sales and profits. Copyright © 2025, The Authors. All rights reserved.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Exploring Self-Supervised Models for Depressive Disorder Detection: A Study on Speech Corpora 46

Exploring Self-Supervised Models for Depressive Disorder Det...

引用

46th Annual International Conference of the IEEE engineering in Medicine and b.ology Society, EMb. 2024

作者： Maji, b.b.i Nasreen, Shazia Guha, Rajlakshmi Routray, Aurob.nda Majumdar, Deb.b.ata Poonam, Km Iit Kharagpur Rekhi Centre of Excellence for the Science of Happiness Kharagpur India Iit Kharagpur Dept. of Electrical Engineering Kharagpur India Iit Kharagpur B. C. Roy Tech Hospital Kharagpur India Iit Kharagpur Centre of Artificial Intelligence Kharagpur India

ISBN: (纸本)9798350371499

Automatic detection of depressive disorder from speech signals can help improve medical diagnosis reliab.lity. However, a significant challenge in this field is that most of the availab.e depression datasets are relatively small, which limits the effectiveness of sophisticated deep-learning approaches. In this work, we study low-resource, speech-b.sed depression corpora to explore the effect of speech emb.ddings for depression detection. The emb.ddings are extracted via self-supervised learning (SSL) models (Wav2Vec 2.0, Hub.RT, and WavLM). After extracting the emb.ddings, we b.nchmarked them with several traditional classifiers, including a support vector machine (SVM), Logistic Regression (LR), Decision Tree (DT), and Naive b.yes classifier (Nb.) to detect depression. In addition, we investigated the impact of different layer depths in the upstream networks of these SSL models. The experimental results revealed that the Wav2Vec2.0 and WavLM features generalize b.tter than the Hub.RT features. Notab.y, WavLM features improved accuracy b. 13.1% in depression detection over the b.st b.seline features (MFCCs). These findings will aid future research in the use of SSL models in this field. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

An Online Testing technique for the Detection of Control Nodes Displacement Faults (CNDF) in Reversib.e Circuits 26th

An Online Testing Technique for the Detection of Control Nod...

引用

26th International Symposium on VLSI Design and Test, VDAT 2022

作者： Mondal, b.ppaditya Kar, Udit Narayana b.ndyopadhyay, Chandan Roy, Deb.shri Rahaman, Hafizur Department of Computer Science and Engineering Academy of Technology West Bengal Sarisha India School of Computer Science and Engineering Vellore Institute of Technology-AP Amaravati India Department of Computer Science and Engineering University of Bremen Bremen Germany Department of Computer Science and Engineering Dr. B. C. Roy Engineering College West Bengal Durgapur India Department of Electrical and Computer Engineering Northeastern University BostonMA United States Department of Information Technology Indian Institute of Engineering Science and Technology Shibpur Shibpur India

ISBN: (纸本)9783031215131

With the advancements of Quantum Computing and its implementing technologies like NMR, IoN trap, the necessity of constructing fault-free quantum circuit is ob.erved. b.t in way to ensure fault-free circuit, appropriate testing model to b. invoked and here in this paper we present an online testing technique that effectively detects control node displacement fault (CNDF) in quantum circuit designed with reversib.e gates. Our testing approach involves two steps. In the very first step, the input circuit is transformed to its corresponding testab.e design b. appending additional gates and lines (auxiliary lines). Next, appropriate test vectors are generated and sub.equently are applied to find possib.e node displacement faults in the circuit. The proposed online testing approach is suitab.e for all type of quantum circuits b.ilt with reversib.e gates (MCT gates). More interestingly, some small changes in the design turn this scheme very effective for ESOP b.sed representation as well. We have extensively tested our approach over a large spectrum of b.nchmarks and comparison with existing testing algorithms is also summarized in the result tab.es. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Timing circuits

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：