检索结果-内蒙古大学图书馆

Twitter Media Sentiment Analysis to Convert Non-Informative to Informative Using QER

Intelligent Automation & Soft Computing 2023年第3期35卷 3545-3555页

作者： C.P.Thamil Selvi P.Muneeshwari K.Selvasheela D.Prasanna Department of Computer Science and Engineering Sri Ranganathar Institute of Engineering and TechnologyCoimbatore641009TamilnaduIndia Department of Artificial Intelligence and Machine Learning Saveetha School of Engineering Chennai602105Tamil NaduIndia Department of Computer Science and Engineering Sreesakthi Engineering CollegeKaramadai641104Tamil NaduIndia Department of Computer Science and Engineering Mahendra Engineering CollegeNamakkal637503Tamil NaduIndia

The term sentiment analysis deals with sentiment classiﬁcation based on the review made by the user in a social *** sentiment classiﬁcation accuracy is evaluated using various selection methods,especially those that deal with algorithm *** this work,every sentiment received through user expressions is ranked in order to categorise sentiments as informative and *** order to do so,the work focus on Query Expansion Ranking(QER)algorithm that takes user text as input and process for sentiment analysis andﬁnally produces the results as informative or *** challenge is to convert non-informative into informative using the concepts of classiﬁers like Bayes multinomial,entropy modelling along with the traditional sentimental analysis algorithm like Support Vector machine(SVM)and decision *** work also addresses simulated annealing along with QER to classify data based on sentiment *** the input volume is very fast,the work also addresses the concept of big data for information retrieval and *** result com-parison shows that the QER algorithm proved to be versatile when compared with the result of *** work uses Twitter user comments for evaluating senti-ment analysis.

关键词： Sentiments QER SVM bayes multinomial big data analysis simulated annealing

来源：评论

学校读者我要写书评

暂无评论

Collective Diagnostic Prototypical in Internet of Medical Things for Depression Identification using Deep learning Algorithm

引用

Recent Patents on Engineering 2024年第9期18卷 24-33页

作者： Selvarajan, Shitharth Thirumalaisamy, Manikandan Manoharan, Hariprasath Devendiran, Ramkumar Lakshmi Narayanan, S. Kumar, Ashwani Department of Computer Science Kebri Dehar University Kebri Dehar250 Ethiopia School of Computer Science Engineering and technology Bennett University U.P India Department of Artificial Intelligence and Machine Learning Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamil Nadu Chennai India Department of Electronics and Communication Engineering Panimalar Engineering College Poonamallee Tamil Nadu Chennai600 123 India School of Computer Science and Engineering VIT-AP UNIVERSITY Andhra Pradesh Amaravathi522237 India Gojan School of Business and Technology Chennai India Department of Computer Science and Engineering School of Engineering and Technology Sharda University Greater Noida India

Background: The majority of wearable technology that is present in various patents for Internet of Medical Things (IoMT) health monitoring systems is introduced to recognize various bodily indicators. The enumerated patents indicate that monitored values are sent to a central server, where they are all treated by experts at the appropriate moment. Therefore, a new patent technique by expanding the use of wireless devices, has been discovered that such communication technologies can recognize specific depression traits and mood swings. Objectives: The major objective of the proposed method is to analyze the disputes that arise in the characteristics of an individual by observing the leveling periods that are identified from the processed image. In addition, the rate of data transfer in case of any dispute is maximized therefore recognition problem is solved at a minimized distance. Further, the steady state probability values are achieved at low delay thus minimizing the dropout packets in the monitored system using IoMT and LSTM. Methods: A balanced record with four distinct parameters—such as livelihood, self-reliance, correlation, and precision—is employed with the projected model on IoMT for depression identification. As a result, high data transfer rates and low distance separation are used to process the identification framework. Additionally, by combining an original matrix representation with the input feature set using LSTM, a novel framework with great efficiency is created. Results: In order to assess the results of IoMT using LSTM, four situations are split apart and their probability ratios are calculated. The results of each situation are then contrasted with the current methodology, and it is found that when there is a low dropout ratio, depression in a person is quickly diagnosed. Conclusion: The comparison analysis demonstrates that the proposed method, when compared to the current method, offers the best-compromised outcomes at roughly 64%. © 2024 B

关键词： Data transfer

来源：评论

学校读者我要写书评

暂无评论

learning discrete latent variable structures with tensor rank conditions 24

Learning discrete latent variable structures with tensor ran...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Zhengming Chen Ruichu Cai Feng Xie Jie Qiao Anpeng Wu Zijian Li Zhifeng Hao Kun Zhang School of Computer Science Guangdong University of Technology and Machine Learning Department Mohamed bin Zayed University of Artificial Intelligence School of Computer Science Guangdong University of Technology Department of Applied Statistics Beijing Technology and Business University Machine Learning Department Mohamed bin Zayed University of Artificial Intelligence and Department of Computer Science and Technology Zhejiang University Machine Learning Department Mohamed bin Zayed University of Artificial Intelligence School of Computer Science Guangdong University of Technology and College of Science Shantou University Shantou Guangdong China Machine Learning Department Mohamed bin Zayed University of Artificial Intelligence and Department of Philosophy Carnegie Mellon University

ISBN: (纸本)9798331314385

Unobserved discrete data are ubiquitous in many scientific disciplines, and how to learn the causal structure of these latent variables is crucial for uncovering data patterns. Most studies focus on the linear latent variable model or impose strict constraints on latent structures, which fail to address cases in discrete data involving non-linear relationships or complex latent structures. To achieve this, we explore a tensor rank condition on contingency tables for an observed variable set Xp, showing that the rank is determined by the minimum support of a specific conditional set (not necessary in Xp) that d-separates all variables in Xp. By this, one can locate the latent variable through probing the rank on different observed variables set, and further identify the latent causal structure under some structure assumptions. We present the corresponding identification algorithm and conduct simulated experiments to verify the effectiveness of our method. Our results elegantly expand the application scope of causal discovery with latent variables.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Spatial Attention Mechanism Integrated Ensemble machine learning for Real Time Prediction and Classification in Precision Agriculture

Spatial Attention Mechanism Integrated Ensemble Machine Lear...

引用

2024 International Conference on Intelligent Algorithms for Computational intelligence Systems, IACIS 2024

作者： Adnan, Myasar Mundher Vijay Kumar, Bura Madhura, G.K. Mohammed, G. Das, Abhijeet The Islamic University Engineering College of Technical Engineering Department of Computers Techniques Najaf Iraq Sr University School of Computer Science and Artificial Intelligence Warangal India Nitte Meenakshi Institute of Technology Department of Artificial Intelligence and Machine Learning Bengaluru India Ahl Al Bayt University Karbala Iraq Department of Civil Engineering Bhubaneswar India

ISBN: (纸本)9798350360660

Generating spatial and temporal features for real time prediction and classification in precision agriculture is challenging due to inaccurate estimation of features from the remote sensing images. Using Geographical Information System (GIS) and systematic data regarding spatial and temporal data for monitoring and management of agricultural activities. The proposed research integrated GIS and used satellite image processing with Ensemble machine learning (EML) algorithms. Initially, the remote sensing data is pre-processed with normalization technique to remove noise. The pre-processed data is given as input to the Improved Speeded Up Robust Features (ISURF) for fast computation and identification of relevant features. The EML algorithms such as Random Forest (RF), Support Vector machine (SVM), and artificial Neural Network (ANN) are used as a prediction and classification models considering the ISURF features as input. Additionally, the Spatial Attention Mechanism (SAM) is integrated with the EML algorithm to particularly focus on the spatial features of the remote sensing data. The experimental results showed that the proposed SAM-EML achieved precise prediction and classification with 98.30% accuracy, and 97.19% precision when compared to the existing methods Random Forest Regression (RFR) and RF-SVM. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

LaCK: Lung Cancer Classification and Detection using Convolutional Neural Network-based Gated Recurrent Unit Neural Network Model

LaCK: Lung Cancer Classification and Detection using Convolu...

引用

2024 Asia Pacific Conference on Innovation in Technology, APCIT 2024

作者： Thara, Machakanti Navya Chatterjee, Kalyan Raju, Muntha Rout, Sandip Priyadharshini, M. Prasad, Kokkula Shiva Suraj Kumar, Samala Reddy, Mandadi Sriya Nalla Malla Reddy Engineering College Artificial Intelligence & Machine Learning Hyderabad India Nalla Malla Reddy Engineering College Computer Science & Engineering Hyderabad India Government of Odisha Mathematics Government Autonomous College Dept. of Higher Education Odisha Angul India

ISBN: (纸本)9798350361537

Cancer instills fear in people worldwide, with millions succumbing to its grasp each year. Among the various types, lung cancer stands as a prominent contributor to this alarming statistic. Therefore, this novel research Lung Cancer Classification and Detection using Convolutional Neural Network-based Gated Recurrent Unit Neural Network Model (LaCK) has focused on classifying lung cancer, notably Non-Small Cell Lung Cancer, which constitutes the majority of cases. We employed five units of gated recurrent unit neural network (GRU-NN) together to achieve this classification, utilizing logistic regression (LR) and support vector classifier (SVC) models for comparisons. Among all models, the LaCK model demonstrated remarkable accuracy, achieving approximately 98% success rate, outperforming its counterparts. Implementing this model in clinical settings enables medical professionals to establish a precise and automated approach to diagnosing lung cancer. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Predicting Stock Market Trends Using Deep learning: A Case Study of Pakistan Stock Exchange 18

Predicting Stock Market Trends Using Deep Learning: A Case S...

引用

18th International Conference on Open Source Systems and Technologies, ICOSST 2024

作者： Balouch, Maaz Hamayat, Faizan Abbasi, Humza Fazal Javed, Muhammad Qasim Mehrban, Ali Ahmad, Rana Fayyaz Department of Business Studies Namal University Mianwali Pakistan National Center for Physics Machine Learning and Deep Learning Lab Artificial Intelligence Technology Center Islamabad Pakistan Department of Computer Science Bahria University Islamabad Pakistan School of Electrical and Electronics Engineering Newcastle University Newcastle United Kingdom

ISBN: (纸本)9798331508692

This research investigates the short-term stock price prediction in the Pakistan Stock Exchange (PSX) using Deep learning (DL) techniques. By integrating historical stock data, economic indicators, and market news, the research aims to address the limitations of traditional stock analysis methods. Data was collected and pre-processed from various sources, including the PSX, economic indicators, and market news. Four techniques were implemented: ARIMA, LSTM, BI-LSTM, and a hybrid CNN-BI-LSTM. Their performance was evaluated using RMSE, MAE, and MAPE metrics. Comparative analysis revealed that BILSTM outperformed the other techniques, with RMSE, MAE, and MAPE scores of 0.9298, 0.6099, and 13.9443, respectively. Despite ARIMA's lower accuracy, it had the fastest inference time, followed by LSTM, CNN-BI-LSTM, and BI-LSTM. Results indicate that using comprehensive data with DL models significantly improves stock price forecast accuracy, highlighting the potential of technological innovation in enhancing financial market decision-making. These DL algorithms can provide valuable insights for investors and analysts in the PSX, leading to better decision-making and more accurate economic predictions. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

An Optimal Scheduling of Energy Storage Units in Renewable Energy Systems Using Strength-Pareto Evolutionary Algorithm

An Optimal Scheduling of Energy Storage Units in Renewable E...

引用

2024 International Conference on Intelligent Algorithms for Computational intelligence Systems, IACIS 2024

作者： Kumari, Nalli Vinaya Kumar, Komuravelly Sudheer Alsalami, Zaid Harshitha, P. Ramadan, Ghazi Mohamad Jntuh Malla Reddy Engineering College for Women Department of Computer Science and Engineering Hyderabad India Sr University School of Computer Science & Artificial Intelligence Warangal India The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq Nitte Meenakshi Institute of Technology Department of Artificial Intelligence and Machine Learning Bengaluru India Ahl Al Bayt University College of Mlt Karbala Iraq

ISBN: (纸本)9798350360660

Dual-stage optimization scheduling model by hybrid energy storage for grid-connected renewable energy systems, is proposed in this paper which focuses on both intra-day and day-ahead phases. In day-ahead phase, model improves economic efficiency by considering of price values at its peak value difference. In intra-day phase, its motive is to decrease renewable energy usage and it's related with the day-ahead schedules using accurate, short-term predictions. Strength-pareto evolutionary algorithm 2 (SPEA2) algorithm for optimization is for multiple objective optimizations, achieving optimal and balanced solutions across multiple objectives. This SPEA2 optimization algorithm efficient handles and it enables system to cost-effectively and firmly operate and optimizing scheduling of grid-connected systems by addressing both the aspects of economic and operational. Overall, the model improves economic efficiency, reduces 6.3% the usage of renewable energy, and improves the sustainability power grid through effective integration and utilization of renewable energy sources. © 2024 IEEE.

关键词： Clean energy

来源：评论

学校读者我要写书评

暂无评论

Utilising SkyScript for Open-Vocabulary Categorization, Extraction, and Captioning to Enhance Multi-Modal Tasks in Remote Sensing

引用

Remote Sensing in Earth Systems sciences 2024年第3期7卷 149-158页

作者： Nagaraj, Saranya Sivakumar, Shanmuga Priya Annabel, Lawrence Sherly Puspha Joshi, Vilas Ramrao Patil, Mithun Baswaraj Patil, Vishal Ratansing SRM Institute of Science and Technology School of Computing SRM Institute of Science and Technology Department of Artificial Intelligence and Machine Learning St. Joseph’s College of Engineering Department of Computer Engineering ISBM College of Engineering Department of Computer Science and Engg N K Orchid College of Engg and Technology Solapur Department of CSE (AIML) Pimpri Chinchwad College of Engineering Nigdi

The SkyScript dataset was developed by integrating large-scale remote sensing images from Google Earth Engine with geo-tagged semantic data from OpenStreetMap. This open-access dataset, consisting of 2.6 million image-text pairs covering 29,000 unique tags, facilitates various remote sensing tasks such as cross-modal retrieval, image captioning, and classification. The dataset ensures global representation and semantic diversity, although it exhibits a higher concentration of high-resolution images from the USA and Europe due to licencing constraints. The images, sourced from multiple collections with varying ground sampling distances, are paired with captions generated using a combination of rule-based methods and logistic regression models for tag classification. Experiments demonstrate that models pre-trained on SkyScript outperform those trained on other datasets in zero-shot classification and fine-grained attribute recognition, highlighting its potential for advancing vision-language models in remote sensing applications. Future improvements could involve enhancing geographic coverage and refining caption quality using advanced language models. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Image captioning Remote sensing Sampling distance Vision language

来源：评论

学校读者我要写书评

暂无评论

A Classification of Face Recognition System Using Faster Region-Based Convolutional Neural Network 2

A Classification of Face Recognition System Using Faster Reg...

引用

2nd IEEE International Conference on Data science and Network Security, ICDSNS 2024

作者： Maheswari, M. Alabdeli, Haider Aruna, T.M. Reddy, R. Archana Revathi, R. School of Computing Srm Institue of Science and Technology Department of Computational Intelligence Kattankulathur India College of Technical Engineering The Islamic University Department of Computers Techniques Engineering Najaf Iraq Nitte Meenakshi Institute of Technology Artificial Intelligence and Machine Learning Bengaluru India School of Computer Science and Engineering Sr University Warangal India Karpagam Academy of Higher Education Department of Computer Science Echanari Coimbatore India

ISBN: (纸本)9798350373110

In recent times, face recognition is a kind of biometric authentication which is widely used for security purpose in many areas like image processing, pattern recognition. However, recognizing the human face was very difficult as the poses in the input images vary, various conditions of light, brightness, expressions, ages. To overcome from it, a proposed method was introduced in this paper known as Faster Region-based Convolutional Neural Network (RCNN). The main advantage of using the proposed method is it will minimize the training process time as it consisting of two fully connected layers namely classifier and regression layer. Initially, the proposed method was implemented on ORL database consisting of 40 classes, then the images in the database undergoes image resizing and enhancing in the preprocessing stage. Where, Image resizing id done to reduce images size so that every image is same in size that will minimize the processing time and image enhancing was done to adjust the brightness of the image. In further, for extracting the features from preprocessed images, CNN is used, so that extracted features are given to the classification stage to detect the face of human or not. In detecting the faces, proposed Faster RCNN achieved high accuracy of 98.64% when compared with other existing methods like IFC, EFRA and VGG16. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An Effective Expectation of Diabetes Mellitus via Improved Support Vector machine through Cloud Security

An Effective Expectation of Diabetes Mellitus via Improved S...

引用

2023 IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2023

作者： Lal N, Dayanand Hema, K. Spoorthi, T. Chegoni, Ramesh Madhura, K.G. Gitam School of Technology Gitam University Department of Computer Science & Engineering India Cmr Technical Campus Department of It Kandlakoya India Nitte Meenakshi Institute of Technology Department of Artificial Intelligence and Machine Learning Bengaluru India

ISBN: (纸本)9798350398465

Nerve pain, eye difficulties, skin issues, renal problems, heart disease, depression, and a host of other illnesses are all linked to diabetes if left untreated. In an effort to lengthen the human lifespan, scientists all around the world have applied a variety of methods for early disease prediction. Diseases of the eyes, heart, and kidneys are prioritised because they can cause serious consequences and even death if left untreated. After conducting an in-depth analysis of the strategies used by several researchers, the following models were constructed and tested using the datasets most frequently favoured by leading scientists throughout the world. Diabetic retinopathy (DR) is an eye condition, and this research seeks to construct a hybrid learning model for early prediction of DR. The proposed approach combines elements of both machine learning and Deep learning. Score Level Fusion is the last arbiter of the model's precision. Images from the first dataset of its sort reflecting the Indian population, the Indian Diabetic Retinopathy Imaging Dataset, were used to make the prediction. Predicting the DR and recommending the necessary treatment to patients is possible based on severity levels, which ultimately leads to the elimination of blindness. © 2023 IEEE.

关键词： Forecasting

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：