检索结果-内蒙古大学图书馆

5th IEEE Global Conference for Advancement in Technology, GCAT 2024

作者： Oak, Omkar Nazre, Rukmini Budke, Rujuta Mahatekar, Yogita Coep Technological University Department of Computer Science and Engineering India Coep Technological University Department of Mathematics India

ISBN: (纸本)9798350376685

Prediction models are crucial in the stock market as they aid in forecasting future prices and trends, enabling investors to make informed decisions and manage risks more effectively. In the Indian stock market, where volatility is often high, accurate predictions can provide a significant edge in capitalizing on market movements. While various models like regression and Artificial Neural Networks (ANNs) have been explored for this purpose, studies have shown that Long Short-Term Memory networks (LSTMs) are the most effective. This is because they can capture complex temporal dependencies present in financial data. This paper presents a Bidirectional Multivariate LSTM model designed to predict short-term stock prices of Indian companies in the NIFTY 100 across four major sectors- ICICI Bank, NTPC, Ambuja Cement and Wipro. The study utilizes eight years of hourly historical data, from 2015 to 2022, to perform a comprehensive analysis of the proposed methods. Both Univariate LSTM and Univariate Bidirectional LSTM models were evaluated based on R2 score, RMSE, MSE, MAE, and MAPE. To improve predictive accuracy, the analysis was extended to multivariate data. Additionally, 12 technical indicators, having high correlation values with the close price(greater than 0.99) including EMA5, SMA5, TRIMA5, KAMA10 and the Bollinger Bands were selected as variables to further optimize the prediction models. The proposed Bidirectional Multivariate LSTM model, when applied to a dataset containing these indicators, achieved an exceptionally high average R2 score of 99.4779% across the four stocks, which is 3.9833% higher than that of the Unidirectional Multivariate LSTM without technical indicators. The proposed model has an average RMSE of 0.0103955, an average MAE of 0.007485 and an average MAPE of 1.1635%. This highlights the model's exceptional forecasting accuracy and emphasizes its potential to improve short-term trading strategies. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Random Adaptive Cache Placement Policy 31

Random Adaptive Cache Placement Policy

引用

31st IEEE International Conference on High Performance Computing, Data, and Analytics Workshops, HiPCW 2024

作者： Ahire, Vrushank Menon, Pranav Muley, Aniruddh Prasad, Abhinandan S. Department of Computer Science and Engineering IIT Ropar Punjab India Department of Mathematics IIT Ropar Punjab India

ISBN: (纸本)9798331509118

This paper presents a new hybrid cache replacement algorithm that combines random allocation with a modified V-Way cache implementation. Our RAC adapts to complex cache access patterns and optimizes cache usage by improving the utilization of cache sets, unlike traditional cache policies. The algorithm utilizes a 16-way set-associative cache with 2048 sets, incorporating dynamic allocation and flexible tag management. RAC extends the V-Way cache design and its variants by optimizing tag and data storage for enhanced efficiency. We evaluated the algorithm using the ChampSim simulator with four diverse benchmark traces and observed significant improvements in cache hit rates up to 80.82% hit rate. Although the improvements in the instructions per cycle (IPC) were moderate, our findings emphasize the algorithm’s potential to enhance cache utilization and reduce memory access times. © 2024 IEEE

关键词： Cache memory

来源：评论

学校读者我要写书评

暂无评论

Integrating Machine Learning (ML) and Deep Learning (DL) Methods to Produce Reliable Wind Power Predictions 2

Integrating Machine Learning (ML) and Deep Learning (DL) Met...

引用

2nd International Conference Computational and Characterization Techniques in engineering and sciences, IC3TES 2024

作者： Birudaraju, Hyma Sailaja, K. Sreedevi, Vaitla Viswanathan, R. Vandaarkuzhali, S. Guru Nanak Institutions Technical Campus Department Computer Science and Engineering Hyderabad India Gurunanak Institutional Technical Campus Department Computer Science and Engineering Hyderabad India Department Computer Science and Engineering Secunderabad India Kongu Engineering College Department of Mathematics Erode India Mailam Engineering College Department of Mechanical Engineering Mailam India

ISBN: (纸本)9798350364699

Wind energy forecasting is crucial for effective implementation due to weather instability and unpredictability. Seamless incorporation into contemporary electricity systems. Various methodologies and strategies have been used and utilized to achieve precise wind power prediction over a wide range of timeframes. Every approach has advantages and disadvantages. This study first examines the current uses of Machine Learning and Deep Learning methods in wind power and wind speed predictions. An extensive examination and classification of the most significant forecasting techniques has been conducted. Simultaneously, thought-provoking conversations are offered to facilitate the examination of all the topics presented. Two algorithms, one from machine learning (ML) and the other from deep learning (DL), have been chosen and used to anticipate wind power. The findings have shown the strong capacity of both algorithms to accurately capture the characteristics of the produced power. Additional analyses of the outcomes about their correctness and prospects are being contemplated. © 2024 IEEE.

关键词： Wind forecasting

来源：评论

学校读者我要写书评

暂无评论

Enhancing Immersive Streaming CDN through MEC-EdgeAI in NG-EPON & 6G-Xhaul Access Network 15

Enhancing Immersive Streaming CDN through MEC-EdgeAI in NG-E...

引用

15th International Conference on Information and Communication Technology Convergence, ICTC 2024

作者： Kharga, Razat Hwang, I.-Shyan Nikoukar, AliAkbar Liem, Andrew Tanny Yuan Ze University Department of Computer Science and Engineering Taoyuan Taiwan College of Science Yasouj University Department of Mathematics Yasouj Iran Universitas Klabat Department of Computer Science Manado Indonesia

ISBN: (纸本)9798350364637

The integration of Multi-access Edge Computing (MEC) and Edge Artificial Intelligence (EdgeAI) in Next-Generation Passive Optical Networks (NG-EPON) and 6G-Xhaul access networks presents an innovative method to improve immersive live video streaming. EdgeAI offers a potential solution for addressing the quality of service (QoS), dynamic bandwidth management, and reduced latency needs of these contents. The primary motivation behind this research is to enhance the efficiency and performance of Content Delivery Networks (CDNs) when delivering immersive live content. The proposed architecture utilizes Long Short-Term Memory (LSTM) networks to predict bandwidth requirements and dynamically adjust link rates. This ensures the efficient and reliable delivery of immersive live video content with reduced latency. The simulations conducted to evaluate system performance demonstrate substantial improvements in mean packet delay, packet drop probability, and system throughput, thus confirming the effectiveness of the proposed approach. © 2024 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

An Enhancement Of Online Drug Recommendation System Using BGFT-DBi-LSTM And PRFFC Approaches 1

An Enhancement Of Online Drug Recommendation System Using BG...

引用

1st International Conference on Technological Innovations and Advance Computing, TIACOMP 2024

作者： Dhawan, Shubhang Kumar, Krishan Srivastava, Shilpee Chandigarh University Department of Mathematics Mohali India Chandigarh University Department of Computer Science and Engineering Mohali India

ISBN: (纸本)9798350392111

For drug recommendations for all types of health issues, majority of the people have utilized online consultations in recent times. However, drugs' side effects differ from person to person. In existing research works, online drug recommendation systems according to people are not concentrated. Thus, this paper presents the Bayes Functional with Gaussian Tanh-based Deep Bidirectional Long Short Term Memory (BFGT-DBi-LSTM)-based drug recommendation system. Initially, the tweets are gathered;by using Palma Ratio Farthest First Clustering (PRFFC), users are grouped according to their age. Next, from the user comment, the audio, video, and text are extracted. Primarily, the text data are pre-processed. By utilizing the WordNet effect and Sentiword Net, the emotion and score are labeled from the pre-processed data. Moreover, pre-processed data are inputted to the Bidirectional Encoder Representations from Transformers (BERT) word embedding. In the meantime, the features are extracted from the pre-processed data;by utilizing Congruence Coefficient-based AnasPlatyrhynchos Optimization (CC-APO), important features are chosen. Next, to predict drug safety, all the output is given as input to BFGT-DBi-LSTM. Subsequently, according to the output, the drug is recommended for the user. Conversely, the noise is removed from the audio data using Correlated Kalman Filter (CKF). After that, the audio is transformed into text and given for pre-processing. In addition, the audio is separated from the video and given as input to the noise-removal process of audio. Lastly, in experimental analysis, the proposed technique achieves superior outcomes. © 2024 IEEE.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Discrete GWO Optimized Data Aggregation for Reducing Transmission Rate in IoT

引用

computer Systems science & engineering 2023年第3期44卷 1869-1880页

作者： S.Siamala Devi K.Venkatachalam Yunyoung Nam Mohamed Abouhawwash Department of Computer Science and Engineering Sri Krishna College of TechnologyCoimbatore641042India Department of Applied Cybernetics Faculty of ScienceUniversity of Hradec KrálovéHradec Králové50003Czech Republic Department of Computer Science and Engineering Soonchunhyang UniversityAsan31538Korea Department of Mathematics Faculty of ScienceMansoura UniversityMansoura35516Egypt Department of Computational Mathematics Scienceand Engineering(CMSE)Michigan State UniversityEast LansingMI48824USA

The conventional hospital environment is transformed into digital transformation that focuses on patient centric remote approach through advanced *** diagnosis of many diseases will improve the patient *** cost of health care systems is reduced due to the use of advanced technologies such as Internet of Things(IoT),Wireless Sensor Networks(WSN),Embedded systems,Deep learning approaches and Optimization and aggregation *** data generated through these technologies will demand the bandwidth,data rate,latency of the *** this proposed work,efficient discrete grey wolf optimization(DGWO)based data aggregation scheme using Elliptic curve Elgamal with Message Authentication code(ECEMAC)has been used to aggregate the parameters generated from the wearable sensor devices of the *** nodes that are far away from edge node will forward the data to its neighbor cluster head using *** scheme will reduce the number of transmissions over the *** aggregated data are preprocessed at edge node to remove the noise for better *** node will reduce the overhead of cloud *** aggregated data are forward to cloud server for central storage and *** proposed smart diagnosis will reduce the transmission cost through aggrega-tion scheme which will reduce the energy of the *** cost for proposed system for 300 nodes is 0.34μ*** energy cost of existing approaches such as secure privacy preserving data aggregation scheme(SPPDA),concealed data aggregation scheme for multiple application(CDAMA)and secure aggregation scheme(ASAS)are 1.3μJ,0.81μJ and 0.51μJ *** optimization approaches and encryption method will ensure the data privacy.

关键词： Discrete grey wolf optimization data aggregation cloud computing IoT WSN smart healthcare elliptic curve elgamal energy optimization

来源：评论

学校读者我要写书评

暂无评论

Incipient motion of sediment by turbulent kinetic energy in the presence of emergent vegetation in the outer sidewall of a bend

引用

ISH Journal of Hydraulic engineering 2025年第2期31卷 139-147页

作者： Rismani, Nasim Afzalimehr, Hossein Asghari-Pari, Seyed-Amin Nazari-Sharabian, Mohammad Karakouzian, Moses Department of Civil Engineering Iran University of Science and Technology Tehran Iran Department of Civil Engineering Behbahan Khatam Alanbia University of Technology Behbahan Iran Department of Mathematics Engineering and Computer Science West Virginia State University Institute WV United States Department of Civil and Environmental Engineering and Construction University of Nevada Las Vegas NV United States

This study examines the influence of vegetation on sediment movement in a 180° river bend with rigid emergent vegetation on the outer side. Using an Acoustic Doppler Velocimeter, researchers collected 504 velocity profiles under conditions with and without vegetation, across four different vegetation densities. The findings indicate that vegetation reduces the critical velocity needed for sediment movement by 59%. Additionally, the presence of vegetation increases turbulent kinetic energy, with the highest levels observed at the lowest vegetation density, and decreasing as vegetation density increases. This pattern suggests that vegetation not only modifies flow dynamics but also affects the threshold conditions for sediment transport, especially on the outer side of the bend. For example, turbulent kinetic energy is amplified 18 times at a 150-degree angle. In contrast, the bare bed exhibited minimal turbulent kinetic energy, underscoring the significant role of vegetation in altering flow structures. This study highlights the critical importance of emergent vegetation in river management and sediment control, demonstrating a more pronounced effect on the outer bend than the inner side, thus contributing to the sustainability and management of natural streams. © 2024 Indian Society for Hydraulics.

关键词： Kinetic energy

来源：评论

学校读者我要写书评

暂无评论

Breather waves, analytical solutions and conservation laws using Lie–Bäcklund symmetries to the (2 + 1)-dimensional Chaffee–Infante equation

引用

Journal of Ocean engineering and science 2023年第2期8卷 145-151页

作者： Abdullahi Yusuf Tukur Abdulkadir Sulaiman Alrazi Abdeljabbar Marwan Alquran Department of Computer Engineering Biruni University IstanbulTurkey Faculty of Science Federal University DutseJigawaNigeria Department of Mathematics Khalifa University for Science and TechnologyAbu DhabiUAE Department of Mathematics and Statistics Jordan University of Science and TechnologyIrbidJordan

The(2+1)-dimensional Chaffee–Infante has a wide range of applications in science and engineering,including nonlinear fiber optics,electromagnetic field waves,signal processing through optical fibers,plasma physics,coastal engineering,fluid dynamics and is particularly useful for modeling ion-acoustic waves in plasma and sound *** this paper,this equation is investigated and analyzed using two effective *** well-known tanh-coth and sine-cosine function schemes are employed to establish analytical solutions for the equation under *** breather wave solutions are derived using the Cole–Hopf *** addition,by means of new conservation theorem,we construct conservation laws(CLs)for the governing equation by means of Lie–Bäcklund *** novel characteristics for the(2+1)-dimensional Chaffee–Infante equation obtained in this work can be of great importance in nonlinear sciences and ocean engineering.

关键词： Extended tanh-coth method Sine-cosine function method Soliton solutions Breather wave solutions Conservation laws

来源：评论

学校读者我要写书评

暂无评论

Securing unmanned aerial vehicle—heterogeneous networks using functional encryption scheme

引用

Multimedia Tools and Applications 2025年 1-19页

作者： Gupta, Sachin Kumar Gupta, Parul Singh, Pawan Department of Electronics and Communication Engineering Central University of Jammu UT of Jammu and Kashmir Jammu181143 India Computer Science of Engineering J.B. Institute of Technology Uttarakhand Dehradun248197 India Department of Computer Science School of Mathematics Statistics and Computational Sciences Central University of Rajasthan Ajmer- 305817 Rajasthan India

In today's scenario, as the internet expands at a faster pace, the number of data consumers also increases at an exponential rate. As the range and number of users increased, a change from traditional homogeneous networks to heterogeneous networks is in demand. However, heterogeneous networks' primary focus is to give a higher quality of service criteria to users. Furthermore, in a heterogeneous network enabled by unmanned aerial vehicles, a large number of users and devices are active. In such a diverse environment, intruder nodes may efficiently operate and transmit numerous harmful actions throughout the network. As a result, the network's entire communication is open to many types of security threats. Therefore, to secure the communication, we used the functional encryption scheme, which allows us to protect the data against intrusion attacks. The whole procedure of establishing a functional encryption scheme in unmanned aerial vehicles integrated heterogeneous network is proposed in this study in two phases: the first phase between user equipment and micro base station, and the second phase between micro base station and unmanned aerial vehicles. The proposed approach is validated using the simulation tool namely Automated Validation of Internet Security Protocols and Applications. The outcome of the security validation ensures that the proposed methodology provides the desired security and robustness to the network. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Approximation Schemes for Geometric Knapsack for Packing Spheres and Fat Objects 51

Approximation Schemes for Geometric Knapsack for Packing Sph...

引用

51st International Colloquium on Automata, Languages, and Programming, ICALP 2024

作者： Acharya, Pritam Bhore, Sujoy Gupta, Aaryan Khan, Arindam Mondal, Bratin Wiese, Andreas Department of Mathematics Indian Institute of Science Education and Research Pune India Department of Computer Science and Engineering Indian Institute of Technology Bombay India Department of Computer Science and Automation Indian Institute of Science Bengaluru India Department of Mathematics Technical University of Munich Germany

ISBN: (纸本)9783959773225

We study the geometric knapsack problem in which we are given a set of d-dimensional objects (each with associated profits) and the goal is to find the maximum profit subset that can be packed non-overlappingly into a given d-dimensional (unit hypercube) knapsack. Even if d = 2 and all input objects are disks, this problem is known to be NP-hard [Demaine, Fekete, Lang, 2010]. In this paper, we give polynomial time (1 + Ε)-approximation algorithms for the following types of input objects in any constant dimension d: disks and hyperspheres, a class of fat convex polygons that generalizes regular k-gons for k ≥ 5 (formally, polygons with a constant number of edges, whose lengths are in a bounded range, and in which each angle is strictly larger than π/2), arbitrary fat convex objects that are sufficiently small compared to the knapsack. We remark that in our PTAS for disks and hyperspheres, we output the computed set of objects, but for a OΕ(1) of them we determine their coordinates only up to an exponentially small error. However, it is not clear whether there always exists a (1 + Ε)-approximate solution that uses only rational coordinates for the disks’ centers. We leave this as an open problem which is related to well-studied geometric questions in the realm of circle packing. © Pritam Acharya, Sujoy Bhore, Aaryan Gupta, Arindam Khan, Bratin Mondal, and Andreas Wiese.

关键词： Approximation algorithms

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：