检索结果-内蒙古大学图书馆

Next Generation Communication & Information Processing (INCIP), International Conference on

作者： L. Jerart Julus S.N. Syed Naweed D. Aadhavan S. Sudhakara Sankar R.S. Rampriya T. Kavitha Department of IT School of Computer Science Engineering and Information System Vellore Institute of Technology Vellore India School of Computer Science Engineering and Information System Vellore Institute of Technology Vellore India Department of ECE Vel Tech University Chennai Tamilnadu India

ISBN: (数字)9798331528140

ISBN: (纸本)9798331528157

Investing and researchers alike have long been fascinated by the volatile and dynamic nature of financial markets. For the prediction and analysis of stock market movements, we present a hybrid approach that combines Long Short-Term Memory (LSTM) and Moving Average Convergence Divergence (MACD). Leveraging the power of deep learning and technical analysis, this hybrid model offers a comprehensive solution for forecasting and understanding market trends. The LSTM component, a type of recurrent neural network, provides the model with the ability to capture and learn intricate patterns in historical stock price data, thus enabling accurate short and long-term predictions. The MACD indicator, a widely used tool in technical analysis, supplements the LSTM by identifying potential reversal points and providing valuable insights into market momentum. A hybrid approach will provide a stronger and more reliable forecasting framework by combining both LSTM and MACD. To validate the model's efficacy, we apply it to historical stock market data and conduct a thorough analysis of its predictive performance. Our findings suggest that the Hybrid LSTM-MACD approach outperforms traditional methods and offers a promising solution for investors, traders, and financial analysts seeking to navigate the complex world of stock market trading.

关键词： Analytical models Accuracy Predictive models Market research Data models Internet Stock markets Forecasting Long short term memory Convergence

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Based Personality Classification for Carpooling Application

Machine Learning Based Personality Classification for Carpoo...

引用

2023 International Conference on Intelligent systems for Communication, IoT and Security, ICISCoIS 2023

作者： Anas, Mohd Gunavathi, C. Kirubasri, G. School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore India Sona College of Technology Department of Computer Science and Engineering Tamil Nadu Salem India

ISBN: (纸本)9798350335835

Sharing a ride in vehicle is known as carpooling and many businesses are adapting this system. Carpooling is an effective way to control air pollution since it decreases the number of automobiles on busy roads. It also helps to reduce traffic roadways, allowing automobiles to drive faster. Carpooling reduces the pollution even further because vehicles use less gas when they travel without much stopping in the traffic. People may also drive their automobiles whenever they choose, with no need for cheaper maintenance and parking charges for each vehicle. According to studies, each car in a carpooling system takes up to 11 vehicles off the road. This cuts yearly pollution by 13 metric tonnes. In India, if carpooling done correctly, one single car will take around 25 automobiles off the road. To make carpooling easier, in this work, a machine learning (ML) model is utilized to identify the personality types of customers based on the tweets and to group them for the same car with similar personalities. The idea intends to break down this barrier between people who don't like to travel with the people who have different personality. In this model, Natural Language Processing (NLP) is used to deal with the dataset before passing it to the model to train. The proposed work is done using XG-Boost, Decision Tree Classifier, Support Vector Machine, and Stochastic Gradient Decent optimizer. Pre-processing the dataset employed the NLP techniques such as Tokenization, Lemmatization and Stemming. After evaluating all the algorithms, we found out that XG-Boost is outperforming all the remaining three algorithms by achieving 68% accuracy easily with 5-fold cross validation. © 2023 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

M3Hop-CoT: Misogynous Meme Identification with Multimodal Multi-hop Chain-of-Thought

M3Hop-CoT: Misogynous Meme Identification with Multimodal Mu...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Kumari, Gitanjali Jain, Kirtan Ekbal, Asif Department of Computer Science and Engineering India Indian Institute of Technology Patna India School of AI and Data Science Indian Institute of Technology Jodhpur India

ISBN: (纸本)9798891761643

In recent years, there has been a significant rise in the phenomenon of hate against women on social media platforms, particularly through the use of misogynous memes. These memes often target women with subtle and obscure cues, making their detection a challenging task for automated systems. Recently, Large Language Models (LLMs) have shown promising results in reasoning using Chain-of-Thought (CoT) prompting to generate the intermediate reasoning chains as the rationale to facilitate multimodal tasks, but often neglect cultural diversity and key aspects like emotion and contextual knowledge hidden in the visual modalities. To address this gap, we introduce a Multimodal Multi-hop CoT (M3Hop-CoT) framework for Misogynous meme identification, combining a CLIP-based classifier and a multimodal CoT module with entity-object-relationship integration. M3Hop-CoT employs a three-step multimodal prompting principle to induce emotions, target awareness, and contextual knowledge for meme analysis. Our empirical evaluation, including both qualitative and quantitative analysis, validates the efficacy of the M3HopCoT framework on the SemEval-2022 Task 5 (MAMI task) dataset, highlighting its strong performance in the macro-F1 score. Furthermore, we evaluate the model's generalizability by evaluating it on various benchmark meme datasets, offering a thorough insight into the effectiveness of our approach across different datasets. © 2024 Association for Computational Linguistics.

关键词： Chains

来源：评论

学校读者我要写书评

暂无评论

UAMP-Based Delay-Doppler Channel Estimation for OTFS systems

引用

China Communications 2023年第10期20卷 70-84页

作者： Zhongjie Li Weijie Yuan Qinghua Guo Nan Wu Ji Zhang Department of Electronic and Electrical Engineering Southern University of Science and TechonologyShenzhen 518055China School of Electrical Computer and Telecommunications EngineeringUniversity of WollongongWollongongNSW 2522Australia School of Integrated Circuits and Electronics Beijing Institute of TechnologyBeijing 100081China School of Mathematics and Statistics Henan University of Science and TechnologyLuoyang 471000China

Orthogonal time frequency space(OTFS)technique,which modulates data symbols in the delay-Doppler(DD)domain,presents a potential solution for supporting reliable information transmission in highmobility vehicular *** this paper,we study the issues of DD channel estimation for OTFS in the presence of fractional *** first propose a channel estimation algorithm with both low complexity and high accuracy based on the unitary approximate message passing(UAMP),which exploits the structured sparsity of the effective DD domain channel using hidden Markov model(HMM).The empirical state evolution(SE)analysis is then leveraged to predict the performance of our proposed *** refine the hyperparameters in the proposed algorithm,we derive the update criterion for the hyperparameters through the expectation-maximization(EM)***,Our simulation results demonstrate that our proposed algorithm can achieve a significant gain over various baseline schemes.

关键词： orthogonal time frequency space(OTFS) channel estimation hidden Markov model(HMM) unitary approximate message passing(UAMP)

来源：评论

学校读者我要写书评

暂无评论

Optimal Sizing and Placement of BESS in Distribution Grid with High PV Penetration Considering BESS Optimal Operation 11

Optimal Sizing and Placement of BESS in Distribution Grid wi...

引用

11th International Conference on Power and Energy systems engineering, CPESE 2024

作者： Ta-Duy, Bach Nguyen-Tuan, Anh Nguyen-Duc, Tuyen Fujita, Goro Hanoi Uni. of Science and Technology School of EEE Dept. Electrical Engineering Hanoi Viet Nam Department of Power System Department of EE Tokyo Japan

ISBN: (纸本)9798350377439

Battery Energy Storage systems (BESSs) are an effective solution in preventing overvoltage caused by the high penetration rate of renewable energy sources (RES). This paper proposes a new strategy to achieve voltage regulation in distributed power systems in the presence of solar sources and BESSs. The goal is to find the minimum size of the BESSs and their corresponding position in the network based on the size and location of the integrated solar generation. The proposed method formulates the problem by combining grid sensitivity coefficient analysis and modeling second-order cone programming (SOCP) in power flow analysis. Using reactive power to adjust voltage regulation is not always the optimal solution in distribution systems in which R/X is large. Therefore, the study only considers the minimum size and best BESS location achieved by optimizing the amount of solar-curtailed active power through BESS based on the grid topology and R/X ratios in the distribution system. Simulation results on the modified IEEE-33 bus verify the effectiveness of the proposed method. © 2024 IEEE.

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Cloud-Based Deep Learning for Weather Forecasting

Cloud-Based Deep Learning for Weather Forecasting

引用

2025 International Conference on Pervasive Computational Technologies, ICPCT 2025

作者： Sharma, Rupak Tyagi, Pallavi Vajpayee, Pooja Gangwar, Deepti Tyagi, Umang Saraswat, Birendra Kumar Srm Institute of Science and Technology Department of Computer Applications NCR Campus UP Modinagar India Raj Kumar Goel Institute of Technology Computer Science & Engineering UP Ghaziabad India Galgotias University School of Computer Science and Engineering Greater Noida India Raj Kumar Goel Institute of Technology Department of Ece UP Ghaziabad India

ISBN: (纸本)9798331508685

Deep learning is a robust framework for solving complex prediction and forecasting problems from multiple fields, such as weather sciences. Due to the abundance and higher resolution of data available, cloud-based deep learning offers a compelling approach for achieving promising gains in accuracy and efficiency regarding weather forecasting. A more pressing priority in the face of worsening weather events requires faster and more reliable forecasting. Deep learning in the cloud is implemented by training deep neural networks on large datasets stored in a public or private cloud and subsequently using these pre-trained models to predict new data. This encourages using large-scale computational resources, such as those necessary to tackle the heavy data needed for precise meteorological forecasts. Such deep learning models have the flexibility and scalability required to adapt and tune them for specific weather patterns, which can then run on a cloud, enabling readiness as demanded. In this work, 3, x, y present a scalable deep learning-based approach to extended-range temperature prediction on high-performance cloud resources. We use the model to train on historical weather data combined with real-time observed weather from various sources. © 2025 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Self-Attention based ResNet model for Cervical Cancer Detection 2

Self-Attention based ResNet model for Cervical Cancer Detect...

引用

2nd International Conference on Informatics, ICI 2023

作者： Ganguly, Tania Singh, Rimjhim Padam Kumar, Priyanka Department of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham India Department of Computer Science University of Texas at San Antonio Texas USA

ISBN: (纸本)9798350343830

One of the life taking disease in the trait of cancer is Cervical cancer. It is very sensitive case not only to females but also to males. Therefore, due to lack of comfort to talk about in society and unavailability of medial equipments for treatment bring in the need for computation in action to help the society with correct prediction of cervical cancer cases based on the cervix images and detecting the major area of focus. This study advances a unique method for detecting cervical cancer using images from the ICAR-WHO dataset overcoming a number of difficulties, such as the lack of labeling and dataset availability. To address these challenges, the proposed methodology employs convolution neural networks along with clustering technique to automatically detect and classify cervical cancer images using pseudo labeling. The work relies on standard ResNet50 model and encourages self-learning of the features using attention mechanism for better detection and classification of cervical cancer images tested using different methods. Overall, the proposed method demonstrates promising results for cervix cancer detection and holds potential for improved diagnosis and treatment planning. © 2023 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

A Numerical Model Oriented Large-scale Parallel I/O Optimization Method 6

A Numerical Model Oriented Large-scale Parallel I/O Optimiza...

引用

6th International Conference on Data Storage and Data engineering, DSDE 2023

作者： Zhang, Lei Wu, Tao Zhou, Zheng Wang, Dong Chen, Xi School of Computer Science Chengdu University of Information Technology Chengdu China Tsinghua University Department of Earth System Science Beijing China College of Computer Southwest Minzu University Chengdu China

ISBN: (纸本)9798350333145

Numerical models usually contain a large number of data reading and writing, which generally takes a long time. At present, massively parallel technology has accelerated the speed of computing in model, but due to the limitation of computer I/O ability, the acceleration effect is limited, and there is a serious load imbalance during the model operation process, resulting in a waste of computing resources. To deal with that, this paper proposes a new I/O scheme, which can dynamically optimize task allocation during program operation, make full use of computing resources, and increase the mutual coverage of computing and I/O processes, so as to effectively shorten the model running time. Finally, the test in the earth simulator shows that the new I/O scheme improves the operation speed of the regional high-precision air pollution model by 25.45%. © 2023 IEEE.

关键词： Numerical models

来源：评论

学校读者我要写书评

暂无评论

Empowering the Blind: AI-Assisted Solutions for Visually Impaired People 9

Empowering the Blind: AI-Assisted Solutions for Visually Imp...

引用

9th IEEE International Smart Cities Conference, ISC2 2023

作者： Oureshi, Muhammad Shuaib Khan, Inam Ullah Qureshi, SMuhammad Bilal Khan, Fida Muhammad Aleshaiker, Sama Chungnam National University Department of Computer Engineering Daejeon Korea Republic of University of Lakki Marwat Department of Computer Science & It KPK Pakistan University of Science & Technology Department of Computer Science Bannu Pakistan School of Computing and Engineering University of West London United Kingdom

ISBN: (纸本)9798350397758

Physical disability has an influence on individuals everywhere. One of these disabilities that significantly affect a large number of individuals is visual loss. Basic mobility problems, including as crossing the street, reading, driving, and socializing, are commonly a problem for blind people. To go around or complete other daily duties, they typically need on particular assistance devices, including walking sticks. There is still more work to be done in the field of blindness treatment, despite ongoing scientific research. In addition, research has suggested solutions to the problems faced by blind individuals, but these solutions need the necessary technology support. The goal of this research project is to employ smart devices to make daily routines simpler for blind persons of all categories. This smart gadget can recognize faces, different objects, and colors by employing artificial intelligence and picture processing. The notification of the visually impaired individual results from the detecting procedure and might take the form of a vibration or sound alarm. This study also includes a tangible survey that includes local residents who are blind or visually handicapped. In order to program and implement the project, Open CV and Python are both used. This project prototype's effort looks into the methods that are employed for object detection. It also shows how this smart gadget can recognize certain physical objects and how it may alert the user when faced with hurdles. By helping blind individuals with the use of smart technology, this research will, overall, be a helpful contribution to the field of healthcare. © 2023 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

LIME: Long-Term Forecasting Model for Desalination Membrane Fouling to Estimate the Remaining Useful Life of Membrane 1

引用

36th International Conference on Industrial, engineering and Other Applications of Applied Intelligent systems, IEA/AIE 2023

作者： Eltanbouly, Sohaila Erradi, Abdelkarim Tantawy, Ashraf Said, Ahmed Ben Shaban, Khaled Qiblawey, Hazim Computer Science and Engineering Department College of Engineering Qatar University Doha Qatar School of Computer Science and Informatics De Montfort University Leicester United Kingdom Chemical Engineering Department College of Engineering Qatar University Doha Qatar

ISBN: (数字)9783031368226

ISBN: (纸本)9783031368219

Membrane fouling is one of the major problems in desalination processes as it can cause a severe drop in the quality and quantity of the permeate water. This paper presents a data-driven approach for long-term forecasting of fouling behavior in membrane-based desalination processes. The proposed Long-term forecastIng ModEl (LIME) consists of two intertwined machine learning models trained separately by historical operating conditions of ultrafiltration for pretreatment of reverse osmosis seawater where transmembrane pressure is used as a fouling indicator. The first model predicts the increase in fouling due to filtration. This output is fed to the second model to predict the fouling reduction due to membrane cleaning. In turn, this output is used as the initial fouling condition for predicting the next filtration cycle. The forecasted fouling is used to estimate the membrane’s remaining useful life (RUL), which ends when cleaning no longer reduces the fouling below a safety threshold. Evaluation results show that the model can predict the membrane fouling for 1400 cycles with an R-squared score of 0.8. Moreover, the RUL is estimated for various thresholds with an average percentage error of 7%. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Desalination

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：