检索结果-内蒙古大学图书馆

4th International Conference on Ubiquitous Computing and Intelligent Information systems, ICUIs 2024

作者： Naik, Archana sooda, Kavitha Nitte Meenakshi Institute of Technology Department of Computer Science and Engineering Bangalore India B.M.S. College of Engineering Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798331529635

This study investigates CPU utilization prediction in cloud environments using the Informer model, a deep learning framework optimized for long-sequence forecasting. by leveraging its ability to capture complex temporal patterns, the Informer model is benchmarked against GRU, LsTM, Prophet, and XGboost across diverse CPU utilization datasets. Performance is evaluated using RMsE, MsE, MAE, and MAPE metrics. Experimental results demonstrate that the Informer model significantly outperforms the comparison models, excelling in capturing both gradual trends and abrupt fluctuations. specifically, the Informer achieved a 47.51% reduction in RMsE over GRU, 49.90% over LsTM, 67.36% over Prophet, and 50.46% over XGboost. These findings underscore the Informer model's superior adaptability and precision, making it a robust solution for dynamic resource utilization prediction in cloud environments. Its predictive accuracy is pivotal for enhancing workload management and optimizing resource allocation. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Generalization of Relay Node Deployment Problem for Wireless sensor Network on jMetal 15th

Generalization of Relay Node Deployment Problem for Wirele...

引用

15th International Conference on Genetic and Evolutionary Computing, ICGEC 2023

作者： Kong, Lingping Gajdos, Petr Pan, Jeng-shyang snášel, václav Faculty of Electrical Engineering and Computer Science VŠB-Technical University of Ostrava Ostrava Czech Republic College of Computer Science and Engineering Shandong University of Science and Technology Qingdao China

ISBN: (纸本)9789819700677

In Wireless sensor Networks (WsNs), the relay nodes deployment problem is essential, as the relay nodes serve as cluster heads aggregating the data packages from sensors. Further, the relay nodes transmit collected packets to the sink node (central processing point) via wired or wireless paths, thus forming a connected network. various sensor networks tools, such as NetTopo, PiccsIM integrated with Ns2, and Atarraya, improve the performance of simulation and protocols in WsNs. Those tools are not easy to start with for researchers whose research field is uncorrelated to the sensor network. Moreover, the studies based on heuristic algorithms on this problem focus more on a two-dimensional plane or an entire three-dimensional space with homogeneous nodes and omnidirectional sensors. Few pieces of research concentrate on relay nodes on three-dimensional terrain contour deployment, which simulates more natural circumstances to a real-life situation. besides, due to the diverse optimization objectives, arrangement strategies, and sensor node requirements for distinct networks, conducting experiments to compare with existing deployed methods become more challenging. A generalization tool integrating the problem, network environment, and optimization objectives into a framework is essential, where a user can plug in blocks easily with framework interfaces, which makes the comparison more convenient. This design concentrates on users unfamiliar with network settings/models, such as Ns2, adopting heuristic algorithms to solve WsN-related problems. In this study, we fill this gap by implementing a generalization framework based on the jMetal toolbox, which makes the WsN problem a benchmark, and benefits its solving by metaheuristic algorithms. © 2024, The Author(s), under exclusive license to springer Nature singapore Pte Ltd.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

A Parallel DNA Crypto Algorithm for Medical Image

引用

Journal of The Institution of Engineers (India): series b 2024年第2期105卷 183-190页

作者： biradar, sumangala Akkasaligar, Prema T. biradar, sunanda Department of Information Science and Engineering BLDEA’s V.P. Dr. P. G. Halakatti College of Engineering and Technology Karnataka Vijayapur586103 India Department of Computer Science and Engineering KLE Technological University’s Dr. M.S. Sheshgiri College of Engineering and Technology Belagavi Campus Karnataka Belgaum590006 India BLDEA’s V.P. Dr. P. G. Halakatti College of Engineering and Technology Karnataka Vijayapur586103 India

In health care, due to COvID-19 pandemic, doctors and patients are preferring online tele consultancy. In online tele consultancy, diagnosis of the disease is on the basis of online communication and digital images. Wireless communication is good, but the security breach is a crucial problem. To prevent a security breach, various cryptography algorithms are used. The computational complexity of these algorithms is excessive. Hence, the major research issue in health care is the embellishment of security with lowered time complexity. In this paper, we proposed a parallel DNA crypto algorithm to afford substantial security with decline in time complexity. The parallel task processing and parallel instructions processing with multithreads are exercised for parallel process. The medical image is segregated into four subparts, and parallelly, each subpart is remodelled into DNA strands using bit-level dynamic DNA coding pattern selection. Parallelly, all DNA strands pixels are scuffled by sequences of four-dimensional Chen’s and Lorenz chaos theories to get confusion matrices. The DNA XOR is applied to obtain transform matrices. All transform matrices are concatenated to conquer a encipher image. Our algorithm’s simulation exhibits incredible enhancement in the operational speedup. The findings of experiment also proved that the proposed security-level methodology is higher than other conventional algorithms. © The Institution of Engineers (India) 2023.

关键词： DNA

来源：评论

学校读者我要写书评

暂无评论

Challenges and Future scope in Fake News Detection: A survey 1

引用

International Conference on Recent Evolutions in Energy, Drives and E-vehicles, REED-Ev 2022

作者： Rathod, Nachiket A. Ramteke, Prabhakar L. Department of Computer Science and Engineering H.V.P. Mandal’s College of Engineering and Technology Maharashtra Amaravati India

ISBN: (数字)9789819707638

ISBN: (纸本)9789819707621

Post-millennium has seen advent of use of social media in people with sharing articles and interaction. social media has become an important source of information like news for people. Researchers have identified fake news as serious issue which needs to be worked. In this paper, we have reviewed many papers based on studying the techniques employed by authors for fake news detection. We presented tabular format which consists of method, datasets used, and future scope of all reviewed papers. Approaches and challenges are identified from literature survey which are also presented. © The Author(s), under exclusive license to springer Nature singapore Pte Ltd. 2024.

关键词： social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Adaptive Proximity Alert and Currency Detection

Adaptive Proximity Alert and Currency Detection

引用

2023 International Conference on the Confluence of Advancements in Robotics, vision and Interdisciplinary Technology Management, IC-RvITM 2023

作者： Manjeshwar, Chirag Koushik, s. Potta, Kushal Kumar sindhu, K. B.M.S. College of Engineering Department of Computer Science and Engineering Bengaluru India B.M.S. College of Engineering Department of Information Science and Engineering Bengaluru India

ISBN: (纸本)9798350306088

This research presents a cutting-edge mobile application that leverages real-time GPs technology, the Google Maps API, and innovative geo-fencing techniques to tackle the common problem of passengers missing public transportation stops. Unlike traditional alarms, our app provides precise, personalized alerts, enhancing accessibility through features such as voice-enabled search and Optical Character Recognition (OCR). by addressing the challenges of inattention, this user-centric solution significantly improves the overall travel experience for commuters, especially those with diverse needs. Geo-fencing triggers alarms as users approach their stops, ensuring timely notifications. The OCR functionality aids visually impaired users, promoting inclusivity. Future enhancements, including advanced voice features, dynamic geo-fencing, and innovative voice-based ads, promise to further elevate travel experiences and accessibility within public transportation systems. Our research marks a significant step towards revolutionizing the way passengers engage with public transportation, enhancing convenience, and fostering a more inclusive transportation environment for all. © 2023 IEEE.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

LoRaWAN and biosensor-Assisted smart City Framework to Mitigate the Effects of Lung Diseases

LoRaWAN and Biosensor-Assisted Smart City Framework to Mitig...

引用

2024 IEEE International Conference on Modeling, simulation and Intelligent Computing, MosICom 2024

作者： Abubeker, K.M. Roberts, Michaelraj Kingston Prajitha, C. Rinesh, s. shafeena Karim, A. Jeevanandham, s. Department of Electronics and Communication Engineering Kerala India Sri Eshwar College of Engineering Centre for Advances in Signal Processing and Wireless Sensor Networks Department of Electronics and Communication Engineering Coimbatore India Karpagam Academy of Higher Education Centre for Interdisciplinary Research Department of Electronics and Communication Engineering Coimbatore India V.S.B College of Engineering Technical Campus Department of Computer Science and Engineering Coimbatore India Sri Ramakrishna Engineering College Department of Information Technology Coimbatore India

ISBN: (纸本)9798331533311

Urbanization and industrialization in cities present substantial obstacles to air quality, resulting in detrimental effects on public health, including respiratory health. This research introduces an Internet of Things (IoT) framework for a smart city environment using LoRaWAN and sensor networks. The framework utilizes the EsP32 LoRaWAN module to provide real-time monitoring of essential air quality metrics, such as carbon monoxide (CO), nitrogen dioxide (NO2), ozone (O3), temperature, and humidity. Integrating biosensors enhances accuracy by identifying distinct biological indicators linked to respiratory well-being. The proposed work aims to use the framework in an urban setting within a global context, demonstrating its capacity to reduce the effects of lung disorders. The EsP32 LoRaWAN module enables effective communication within the sensor network up to 20 kilometers, guaranteeing a robust and adaptable solution for smart city applications. The developed framework provides a scalable and novel method for developing healthier and more sustainable cities, decreasing respiratory disorders as urban settings develop. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Deep Learning Architecture with Ensemble Learning in Cranial and Mediolateral view Images

Comparative Analysis of Deep Learning Architecture with Ense...

引用

2023 International Conference on Integrated Intelligence and Communication systems, ICIICs 2023

作者： sushma, H.s. sooda, Kavitha B.M.S. College of Engineering Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350315455

The study explores the field of anomaly detection employing advanced methods. Mammography analysis for the identification of anomaly is examined in terms of the effectiveness of ensemble learning when combined with the powerful EfficientNet-b7 deep learning architecture. This study attempts to enhance anomaly identification accuracy by utilizing the abilities of these methods. Comparative experimental results show significant enhancements corresponding to the proposed ensemble learning model. The integrated technique outperforms the standalone EfficientNetb7 model's 95.81% and 94.89% training and validation accuracies while attaining 98.86% and 98.29% with the proposed approach, respectively and the memory consumption has increased by approximately 18.28% with the proposed approach and 22.84% without the proposed approach. With better generalization and reduced overfitting characteristics, the ensemble model consistently shows higher accuracy over training and validation datasets. These results demonstrate the possibility of ensemble learning to improve the stability and accuracy of detection of anomalies. selecting the right model and considering ensemble learning into account while analyzing medical images are crucial choices that could impact the diagnostic system's reliability, effectiveness, and accuracy. © 2023 IEEE.

关键词： Anomaly Detection EfficientNet-b7 Ensemble learning K-Nearest Neighbors (KNN) Mammogram Images Random Forest (RF)

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Object Detection Algorithms for Waste segregation 3

Performance Analysis of Object Detection Algorithms for Wast...

引用

3rd International Conference on Artificial Intelligence and smart Energy, ICAIs 2023

作者： singh, Naman sastry, Pranav Niharika, b.s. sinha, Arka Umadevi, v. B.M.S. College of Engineering Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9781665462167

The amount of waste generated in urban cities is increasing at an alarming rate and its effective and efficient management has become nearly impossible. To combat this issue, this study has compared different object detection algorithms applied on data containing trash with no cluttered background, so as to first evaluate the different algorithms only on the basis of their inherent performance. The algorithms used for training are YOLOv5, EfficientDet and Faster RCNN. Using mAP(Mean Average Precision) as the evaluating metric, this study has found that YOLOv5 with mAP of 0.92 has outperformed EfficientDet and Faster RCNN, whose mAP was 0.846 and 0.836 respectively. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

NEP based smart Education system 14

NEP based Smart Education System

引用

14th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2023

作者： Reddy, Aswath Ram Pavith Raj, Mithil Ramachandran, Amit Gowda, Anvitha K. Pallavi, G.b. shyamala, G. B.M.S. College of Engineering Department of Computer Science and Engineering Bangalore India

With the growing requirements of our current education system in accordance to the demands of the students and training faculty, it is found that many educational institutions are underfunded, which has led to a lack of resources for teachers as well as students, under qualified facilities. The education system often perpetuates social and economic inequalities, with disadvantaged students receiving a lower-quality education and fewer opportunities. The education system often places more emphasis on rote learning and memorization than on developing critical thinking and creativity skills. Children from rural areas have yet to have access. The National Education Policy (NEP) provides for reforms at all levels of education, from school to higher education. This model will enhance the accessibility of education as well as restructure the system. The model allows for teachers across the country to connect with students, teach them various subjects and conduct assignments remotely. students have easy access to primary education by using the model created to enter their credentials and learn from the content posted by the teachers. students take up the assignments allotted for the subject which is further graded by the accredited teachers. This project aims to develop an e-learning-based model that utilizes full-stack technology to create a decentralized and secure system for storing and sharing educational data, such as student records and credentials. © Grenze scientific society, 2023.

关键词： students

来源：评论

学校读者我要写书评

暂无评论

Kannada Words sense Disambiguation using Regular Expression

Kannada Words Sense Disambiguation using Regular Expression

引用

2023 International Conference on Evolutionary Algorithms and soft Computing Techniques, EAsCT 2023

作者： Harshith, H. Patil, seema B.M.S College of Engineering Department of Computer Science & Engineering Bengaluru India

ISBN: (纸本)9798350313413

Word sense disambiguation is a crucial task in natural language processing that involves determining the correct sense of a word in a given context. This paper focuses on Kannada word sense disambiguation using regular expression. Regular expression involves pattern-matching technique that allows the identification of specific patterns in text. In this paper, propose a method to disambiguate Kannada words using regular expression, where identify the most appropriate sense of a word based on its context in the sentence. The approach leverages the syntactic and semantic features of words to identify the most appropriate sense. Evaluate the performance of proposed method on a benchmark dataset and compare it with existing state-of-the-art techniques. The outcome include that the method achieves high accuracy and outperforms existing approaches. © 2023 IEEE.

关键词： Accuracy benchmark Dataset Kannada Language Natural Language Processing Pattern Matching Regular Expression semantic Features state-Of-The-Art Techniques syntactic Features Word sense Disambiguation

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：