检索结果-内蒙古大学图书馆

2023 International Conference on Evolutionary Algorithms and Soft Computing Techniques, EASCT 2023

作者： Aluvala, Srinivas Balamurugan, V. Jeyasudha, J. Kumar, R. Dinesh Pradeep Kumar, S. Sr University School of Computer Science & Artificial Intelligence Warangal India Sathyabama Institute of Science and Technology Department of Ece Chennai India Srm Insitute of Science and Technology Department of Computational Intelligence Chennai India Saveetha School of Engineering Department of Ece Thandalam India Nitte Meenakshi Institute of Technology Department of Electronics and Communication Engineering Bengaluru India

ISBN: (纸本)9798350313413

Predicting stock prices accurately is a challenging task due to various influencing factors. This paper addresses the need for precise stock price prediction by presenting an enhanced sentiment analysis methodology using deep learning, particularly focusing on the Bi-LSTM model. The challenge of accurate sentiment analysis in stock prediction is overcome through advanced data preprocessing techniques tailored to maintain sentiment context effectively. The proposed Bi-LSTM (Bidirectional long Short-Term Memory) and CNN (Convolutional Neural Network) model demonstrates superior performance in classifying sentiments with high precision, recall, F1-score, and accuracy. The numerical validation demonstrates the effectiveness of the Bi-LSTM model in achieving a balance across various metrics, highlighting its potential for practical implementation in stock market prediction. The Bi-LSTM and CNN model achieves remarkable precision 90.00%, recall 90.00%, F1-score 90.00%, and accuracy 91.00%. In comparison to established methods, such as Multivariate Sequential Long Short-Term Memory Autoencoder (MSLSTMA), long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), the Bidirectional long Short-Term Memory (Bi-LSTM) model exhibits its competitive edge in stock price prediction as supported by evaluation metrics. The results emphasize the importance of tailored data preprocessing and deep learning techniques, showcasing the efficiency of the proposed methodology in enhancing stock price prediction accuracy while maintaining high percentages of precision, recall, and F1-score, along with impressive accuracy. © 2023 IEEE.

关键词： Bidirectional long Short-Term Memory Convolutional Neural Network Deep Learning Sentiment Analysis Stock Price Prediction

来源：评论

学校读者我要写书评

暂无评论

An Effective Automated Framework for Oral Cancer Detection by Enhanced Convolutional Neural Networks 12

An Effective Automated Framework for Oral Cancer Detection b...

引用

12th IEEE International Conference on Advanced Computing, ICoAC 2023

作者： Santhiya, M. Sindhuja, M. Jegatha, R. Manikandan, J. Rajalakshmi Engineering College Thandalam Department of Computer Science and Engineering Chennai India Faculty of Engineering and Technology Srm Institute of Science and Technology Kattankulathur Department of Computational Intelligence Chennai India Sri Sai Ram Institute of Technology Department of Information Technology Chennai India St. Joseph's College of Engineering Omr Department of Information Technology Chennai India

ISBN: (纸本)9798350318210

Oral cancer, an aggressive form of cancer affecting the mouth and throat, has been on an alarming worldwide increase due to tobacco use and smoking. Oral cancer presents various challenges such as high incidence rates, delayed diagnosis, inadequate treatment plans and late prognoses and outcomes;early detection is crucial in improving prognosis outcomes and survival prospects. Machine learning techniques have gained prominence for improving cancer diagnosis while decreasing mortality and morbidity;in recent years they were used to detect oral cancer, providing highly accurate classification tasks yet limited capabilities in terms of feature extraction capabilities. To address these limitations, we are currently employing a deep-learning approach. To this end, we have devised an automated framework encompassing feature extraction, preprocessing and classification. Contrast-limited adaptive Histogram Equalization (CLACHE), used for effective pre-processing purposes to increase image contrast and resolution, is one form of pre-processing while Gray Level Cooccurrence Matrix extracts statistical texture-based features;finally, a Modified Convolutional Neural Net (MCNN) was employed for accurate classification of oral cancer cases. Utilizing Kaggle Repository dataset, we used it to assess the performance of our framework, while comparing it against other high-performance methods. Our proposed framework had an accuracy rating of 99.13% which surpasses current state-of-the art approaches. © 2023 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Effect on Public Health Due to Environment Condition- Role of IoT 14

Effect on Public Health Due to Environment Condition- Role o...

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Joshi, Kapil Rastogi, Ritesh Singh, Anupam Kaushik, Vishal Anandaram, Harishchander Kumar, Anil Uttaranchal University Uttaranchal Institute of Technology Department of Cse Dehradun India Niet Department of Computer Science & Engineering Greater Noida India Graphic Era Hill University Department of Computer Science and Engineering Uttarakhand Dehradun India Upes School of Computer Science Dehradun India Amrita Vishwa Vidyapeetham Centre for Computational Engineering and Networking Tamil Nadu Coimbatore India Dit University School of Computing Dehradun India

ISBN: (纸本)9798350335095

The biggest environmental issues are poor air quality, polluted water, contaminated food, polluted transportation, and radiation contamination. In order to ensure sustainable growth and preserve a stable social structure, adequate monitoring is required. With the development of contemporary sensors and advancements in the internet of things (IoT), environmental surveillance has evolved into a smart environment monitoring (SEM) platform in recent decades. The emergence and widespread use of Internet of Things (IoT) devices and its supporting technologies are the driving forces behind the growth of ubiquitous systems, as shown in this study. This study analysisIoT has great promise in the environment, health, & safety (EHS) industries that involve high risk. The social health can be improved with the use of technology that manages and organises information about individuals. IoT may actually serve as the foundation for a society that is health. In this study, we discussed how the Internet of Things (IoT) may benefit individuals and how it can be used for public health. and also highlight IoT-related problems and a suggested remedy. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A GPU Algorithm for Detecting Strongly Connected Components 23

A GPU Algorithm for Detecting Strongly Connected Components

引用

2023 International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2023

作者： Alabandi, Ghadeer Sands, William Biros, George Burtscher, Martin Department of Computer Science Texas State University San MarcosTX United States Oden Institute for Computational Engineering and Sciences The University of Texas at Austin AustinTX United States

ISBN: (纸本)9798400701092

Detecting strongly connected components (SCCs) is an important step in various graph computations. The fastest GPU and CPU implementations from the literature work well on graphs where most of the vertices belong to a single SCC and the vertex degrees follow a power-law distribution. However, these algorithms can be slow on the mesh graphs used in certain radiative transfer simulations, which have a nearly constant vertex degree and can have significant variability in the number and size of SCCs. We introduce ECL-SCC, an SCC detection algorithm that addresses these shortcomings. Our approach is GPU friendly and employs innovative techniques such as maximum ID propagation and edge removal. On an A100 GPU, ECL-SCC performs on par with the fastest prior GPU code on power-law graphs and outperforms it by 7.8× on mesh graphs. Moreover, ECL-SCC running on the GPU outperforms fast parallel CPU code by three orders of magnitude on meshes. © 2023 ACM.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

On the Parameterized Complexity of Odd Coloring

arXiv

引用

arXiv 2025年

作者： Bhyravarapu, Sriram Kumari, Swati Reddy, I. Vinod The Institute of Mathematical Sciences HBNI Chennai India Department of Computer Science and Engineering IIT Bhilai India

A proper vertex coloring of a connected graph G is called an odd coloring if, for every vertex v in G, there exists a color that appears odd number of times in the open neighborhood of v. The minimum number of colors required to obtain an odd coloring of G is called the odd chromatic number of G, denoted by χo(G). Determining χo(G) known to be NP-hard. Given a graph G and an integer k, the Odd Coloring problem is to decide whether χo(G) is at most k. In this paper, we study the parameterized complexity of the problem, particularly with respect to structural graph parameters. We obtain the following results: – We prove that the problem admits a polynomial kernel when parameterized by the distance to clique. – We show that the problem cannot have a polynomial kernel when parameterized by the vertex cover number unless NP ⊆ Co-NP/poly. – We show that the problem is fixed-parameter tractable when parameterized by distance to cluster, distance to co-cluster, or neighborhood diversity. – We show that the problem is W[1]-hard parameterized by clique-width. Finally, we study the complexity of the problem on restricted graph classes. We show that it can be solved in polynomial time on cographs and split graphs but remains NP-complete on certain subclasses of bipartite graphs. Copyright © 2025, The Authors. All rights reserved.

关键词： Parameterization

来源：评论

学校读者我要写书评

暂无评论

Hybrid2 neural ODE causal modeling and an application to glycemic response 24

Hybrid2 neural ODE causal modeling and an application to gly...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Bob Junyi Zou Matthew E. Levine Dessi P. Zaharieva Ramesh Johari Emily B. Fox Institute for Computational and Mathematical Engineering Stanford University Broad Institute of MIT and Harvard Department of Pediatrics Stanford University Department of Management Science and Engineering Stanford University Department of Statistics and Department of Computer Science Stanford University and Chan Zuckerberg Biohub — San Francisco

Hybrid models composing mechanistic ODE-based dynamics with flexible and expressive neural network components have grown rapidly in popularity, especially in scientific domains where such ODE-based modeling offers important interpretability and validated causal grounding (e.g., for counterfactual reasoning). The incorporation of mechanistic models also provides inductive bias in standard blackbox modeling approaches, critical when learning from small datasets or partially observed, complex systems. Unfortunately, as the hybrid models become more flexible, the causal grounding provided by the mechanistic model can quickly be lost. We address this problem by leveraging another common source of domain knowledge: ranking of treatment effects for a set of interventions, even if the precise treatment effect is unknown. We encode this information in a causal loss that we combine with the standard predictive loss to arrive at a hybrid loss that biases our learning towards causally valid hybrid models. We demonstrate our ability to achieve a win-win, state-of-the-art predictive performance and causal validity, in the challenging task of modeling glucose dynamics post-exercise in individuals with type 1 diabetes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unleashing the Potential of IoT in Tackling Ocean Pollution: A Data-Driven Approach for Marine Ecosystem Conservation 2

Unleashing the Potential of IoT in Tackling Ocean Pollution:...

引用

2nd International Conference on Smart Technologies for Smart Nation, SmartTechCon 2023

作者： Srinivasan, S. Vimala Ithayan, J. Devi, A. Sangeerani Saravanan, T.R. Ganesh, E.N. Department of Biomedical Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Tamil Nadu Chennai India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Tamil Nadu Chennai India Department of Computer Science and Engineering Sri Sairam Engineering College Tamil Nadu Chennai India Department of Computational Intelligence SRM Institute of Science and Technology Kattankulathur Tamil Nadu Chennai India Avadi Tamil Nadu Chennai India

ISBN: (纸本)9798350305418

This study investigates the potentially revolutionary role that the Internet of Things (IoT) may play in combating the urgent ocean pollution problem and promoting the growth of ecologically sound marine ecosystems. An approach that is data-driven has become essential in light of the fact that pollution poses a risk to the delicate balance of marine life and puts the future of the seas in jeopardy. The user can get real-time data on water quality, pollutant levels, and plastic trash dispersion if the user installs sensors and devices that the IoT enables. This will allow us to gain a greater knowledge of the patterns and causes of pollution. Using the plethora of information at people’s disposal, the system can develop innovative intervention tactics that successfully and efficiently combat ocean pollution. In addition, early warning systems powered by the Internet of Things might make it easier to respond quickly to oil spills, reducing the negative effects on the environment. This research highlights the importance of cooperation among stakeholders and underlines the need for public awareness and education to create changes in behavioral patterns. The adoption of technologies related to the Internet of Things is the most important step that can be taken to protect marine biodiversity and to create a brighter, more sustainable future for seas. © 2023 IEEE.

关键词： Critical Ocean Pollution Internet of Things (IoT) Marine Conservation Initiative Marine Ecosystems Real-Time Data

来源：评论

学校读者我要写书评

暂无评论

Projective Exploration on Individual Stress Levels using Machine Learning 2

Projective Exploration on Individual Stress Levels using Mac...

引用

2nd International Conference on Artificial Intelligence and Smart Energy, ICAIS 2022

作者： Nagendra Prabhu, S. Singh, Amarjeet Bhavya, B. Sreeja, K. Bhargavi, P. Srm Institute of Science Technology School of Computing Department of Computational Intelligence Kattankulathur Chennai603203 India New Horizon College of Engineering Department of Computer Science and Engineering Department Bangalore India

ISBN: (纸本)9781665400527

Recently, Stress Prediction in every individual based on their profile and behaviour is a challenging task in the current sector. Current system is a manual process where it is difficult to identify the stress in the college students or employees. There is no automation for any stress prediction. System uses machine learning algorithms or AI algorithms to find out the stress levels, these technologies are used for application development. The purpose of this project is to reduce stress in students and employees. computer science has come a long way in the last few years. It is massive and multifaceted. It has been used in a variety of applications to meet the basic needs of human society. In the field of healthcare, machine learning has made significant progress. Stress is a deadly disease that kills a large number of people worldwide. How machine learning techniques can assist in reducing the risk of stress prediction, is examined in this study. © 2022 IEEE.

关键词： Personnel

来源：评论

学校读者我要写书评

暂无评论

Secure Data Reduplication System with Efficient and Reliable Multi-Key Management in Cloud Storage 3

Secure Data Reduplication System with Efficient and Reliable...

引用

3rd International Conference on Innovative Practices in Technology and Management, ICIPTM 2023

作者： Jayaram, B. Suguna, T. Fairooz, Shaik Arul Selvam, P. Vimal, S. Rmk Engineering College Department of Computer Science and Business Systems Tamil Nadu Kavaraipettai India Panimalar Engineering College Department of Electronics and Communication Engineering Tamil Nadu Chennai India Malla Reddy Engineering College Department of Cse -AIML Telangana Secunderabad India Hindusthan College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Coimbatore India School of Computing Srm Institute of Science and Technology Department of Computational Intelligence Tamil Nadu Kattankulathur India

ISBN: (纸本)9798350336238

Malicious hackers may compromise hundreds or millions of machines with little effort, allowing them to shut down networks, steal sensitive data, and compromise critical infrastructure. Data is stolen and used for malicious purposes by hackers who exploit security flaws in the network. And the sophisticated technology they use, like the bucks they do, are continually feeding them the information they needed, not just once. Moreover, even if Internet firewalls have improved, cybercrime has been on the rise. Then, we have a long way to go before we approach the limit, what with all the different kinds of cloud server devices that can connect to the internet nowadays. It's certain that in the future, little devices, no matter how helpful they are really in our everyday lives, will become the preferred tool of villains. In this research, we offer a novel security technique for protecting sensitive data on cloud servers. This intelligent cloud server was protected from any hacking with the aid of this algorithm. The system's output was measured against those of pre-existing algorithms. More than 96% of inputs are authenticated by the proposed technique, while password cracking operations are reduced by about 3%. The source code security management is improved to 99% and the updating issues for various devices entries is reduced 0.02%, and further the privacy breach is reduced up to 0.32%. Hence the proposed method was more secured from cyber security issues. © 2023 IEEE.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

A Skeleton-Based Approach For Rock Crack Detection Towards A Climbing Robot Application

A Skeleton-Based Approach For Rock Crack Detection Towards A...

引用

IEEE International Conference on Robotic Computing (IRC)

作者： Josselin Somerville Roberts Paul-Emile Giacomelli Yoni Gozlan Julia Di Department of Computer Science Stanford University Department of Aeronautics and Astronautics Stanford University Institute for Computational and Mathematical Engineering Stanford University Department of Mechanical Engineering Stanford University

Conventional wheeled robots are unable to tra-verse scientifically interesting, but dangerous, cave environments. Multi-limbed climbing robot designs, such as ReachBot, are able to grasp irregular surface features and execute climbing motions to overcome obstacles, given suitable grasp locations. To support grasp site identification, we present a method for detecting rock cracks and edges, the SKeleton Intersection Loss (SKIL). SKIL is a loss designed for thin object segmentation that leverages the skeleton of the label. A dataset of rock face images was collected, manually annotated, and augmented with generated data. A new group of metrics, LineAcc, has been proposed for thin object segmentation such that the impact of the object width on the score is minimized. In addition, the metric is less sensitive to translation which can often lead to a score of zero when computing classical metrics such as Dice on thin objects. Our fine-tuned models outperform previous methods on similar thin object segmentation tasks such as blood vessel segmentation and show promise for integration onto a robotic system.

关键词：

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：