检索结果-内蒙古大学图书馆

2020 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2020

作者： Pan, Lei Christophe, Francois Mikkonen, Tommi Li, Zhu Bhattacharyya, Shuvra S. University of Maryland Dept.of ECE and UMIACS College ParkMD United States HAMK University of Applied Sciences HAMK Tech Hämeenlinna Finland University of Helsinki Dept.of Computer Science Helsinki Finland University of Missouri Dept.of Computer Science and Electrical Engineering Kansas CityMO United States

ISBN: (纸本)9781728149226

This article presents a novel approach for simulating Spiking Neural Networks (SNNs) that is based on timed dataflow graphs. Whereas conventional SNN simulators compute changes in spiking neuron variables at each time step, the proposed simulation approach focuses on evaluating spike timings. This focus on evaluating when a dataflow actor (spiking neuron) reaches a new spike contributes to making spike evaluation an event-driven computation. The resulting event-driven simulation approach avoids unnecessary computations at time steps that lie between spiking events. This optimization is achieved while avoiding the large overheads associated with lookup tables that are incurred in existing event-driven approaches. Our results show identical spiking behavior compared to simulation using a conventional (time-based) simulator while providing significant improvement in execution time. © 2020 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

The Frontier of Geospatial AI Deep Learning Applications in Data Mining and Spatial Analysis

The Frontier of Geospatial AI Deep Learning Applications in ...

引用

Intelligent Systems and Advanced Applications (ICISAA), International Conference on

作者： Ajit Kumar Mishra Vikash Verma R. Manivannan N. Krishna Kumar Mudunuru Srividya Sanskriti Sharma Department of Electrical & Electronics Engineering IES College of Technology Bhopal M.P India Dept of Artificial Intelligence & Machine Learning GGITS Jabalpur M.P India School of Computing Computer Science & Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai TN India Dept.of CSE Guru Nanak Institutions Technical Campus Ibrahimpatam Hyderabad Telangana India Dept. of CSE MLR Institute of Technology Hyderabad Telangana India Dept of Computer Science & Business System GGITS Jabalpur M.P India

ISBN: (数字)9798331539948

ISBN: (纸本)9798331539955

Modern artificial intelligence uses geographical data mining and regional analysis to analyze large datasets. Deep learning is a new geographic AI method. Example: Geographic Deep Mining Network (GDMN). The Spatial Feature Extractor (SFE), Temporal Geospatial Attention Mechanism (TGAM), and Geospatial Data Fusion Module (GDFM) comprise this technique. We examined six popular approaches and found GDMN performed best. It worked successfully for several reasons. GDMN always outperforms its competitors in memory, F1 score, IoU, training time, and inference time. This is always true. These findings suggest that GDMN might boost geospatial AI’s data mining and location analysis abilities. After all the effort, we have developed a solid basis for location intelligence, making it useful in various subject areas. Because it’s versatile, mapping specialists may use GDMN for better environmental monitoring or city development. Deep learning helps GDMN make better space choices and uncover insights in large, challenging data sets that no one knew about. GDMN’s cutting-edge approaches make space and time research and prediction simpler. This wide perspective offers a more full and all-encompassing picture of today’s challenges than previous techniques. This makes it impossible to overstate how significant this work is to location intelligence. Its unmatched research and insights usher in a new era.

关键词： Deep learning Training Urban areas Transforms Feature extraction Solids Spatial databases Geospatial analysis Data mining Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

A Multistep Ahead Predictive Analysis of Crude Oil

A Multistep Ahead Predictive Analysis of Crude Oil

引用

Blockchain and Distributed Systems Security (ICBDS), IEEE International Conference on

作者： Srikanta Kumar Mohapatra Kamakhya Narayan Singh Prakash Kumar Sarangi Premananda Sahu Jayashree Mohanty Chitkara University Institute of Engineering and Technology Chitkara University Punjab India School Of Computer Application KIIT Deemed University Odisha India Department Of CSE(AI&ML) Vardhaman College of Engineering and Technology Hyderabad India School of Computer science and Engineering Lovely professional University Punjab India Dept.of AIT-CSE Chandigarh University Mohali Chandigarh Punjab India

The population is increasing in a rapid manner and the number of vehicles is increasing in the same ratio. Also, crude oils are very useful towards the energy needs in the industries. As a result, a day will come when we face the issue of feeling the vehicles with the petrol to run the vehicle and to run the industries. So, the solution is to find out the period up to which we can use the crude oil which is currently present in the world. To get a conclusion the most populated countries India and China is taken as reference. For simulation purpose time series based Artificial Neural Network application along with Facebook Prophet is used. Facebook Prophet is used to predict future situations in time series data related to oil production and consumption in two top countries by population, China, and India, over a period of 32 years. NeuralProphet is used for modelling time-series based on neural networks forecasting the near-term oil crisis. The dataset used in this study contains three characteristics, namely population, oil production, and consumption, and is obtained from different government sources. The best part of this model is that it can predict multi step ahead of given current data as required. The method based on NeuralProphet is best suit for the time series prediction for short period or long period. It can be used in multistep ahead prediction methods. It is predicted that by 2050 the scarcity of the petroleum is most. So, the solution is either to reduce the uses of vehicles, control the population or simply go for an alternate fuel like hydrogen could be considered a suitable substitute for oil. This prediction highlights the need for sustainable energy sources to meet the energy demand in the future. In conclusion, this paper presents NeuralProphet approach for forecasting future oil consumption and production trends combining the Facebook Prophet and NeuralProphet method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Algorithm to Segregate Suspicious node in FzMAI 2

A Novel Algorithm to Segregate Suspicious node in FzMAI

引用

2nd IEEE International Conference on Advances in Computing, Communication Control and Networking, ICACCCN 2020

作者： Singh, Neha Virmani, Deepali University School of Information Communication and Technology GGSIPU Delhi India BPIT Dept.of Computer Science and Engineering Delhi India

ISBN: (纸本)9781728183374

Intrusion prevention systems form a lacuna in wireless sensor networks(WSN). This paper widens the scope of fuzzified methodology to avert intrusion method (FzMAI). FzMAI defines an extra parameter for node classification other than normal and malicious: Suspicious. The paper proposes an algorithm for segregating a suspicious node into either a normal node or malignant node. The algorithm is inspired by Locard's Exchange Principle used in forensic science. The proposed algorithm is tested on a modified WSN-DS dataset and obtains an accuracy of 87%. © 2020 IEEE.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Educational Matlab Tool for Evaluating Liver Tumors Using Ultrasound 16

Educational Matlab Tool for Evaluating Liver Tumors Using Ul...

引用

16th International Symposium on Electronics and Telecommunications, ISETC 2024

作者： Veres, Denisa Alexandra Bonciog, Dumitru Daniel Olei, Damian Cirnatu, Daniela Goje, Daniel Iacob Comaniciu, David Iovan, Liliana Matiu Lascu, Mihaela Ruxandra Ordodi, Valentin Laurentiu University Politehnica Timişoara Dept. of Computer and Information Technology Timişoara Romania University Politehnica Timişoara Dept. of Measurements and Optical Electronics Timişoara Romania National Institute of Public Health Timisoara Regional Centre Timişoara Romania 'Victor Babes' University of Medicine and Phanmacy Timişoara Dept.of Internal medicine I. Timişoara Romania University of Medicine and Phanmacy Timişoara Dept. of Biochemistry.'Victor Babes' Timişoara Romania University Politehnica Timişoara Engineering of Organic and Natural Compounds Dept. of Applied Chemistry Timisoara Romania 'Victor Babes' University of Medicine and Phanmacy Timişoara Dept. of Functional Science Timisoara Romania

ISBN: (纸本)9798350390865

This paper aims to develop a Matlab application for computer-assisted learning in the evaluation of liver tumors using ultrasound. Diagnosing liver tumors detected during standard ultrasound exams is challenging for doctors, often requiring detailed investigations for accurate diagnosis and effective treatment. computerized analysis of ultrasound images can significantly aid doctors in interpreting these images and formulating accurate diagnoses. The Matlab programming environment provides various tools for processing biomedical images. In this study, Histogram and Entropy functions were utilized to accurately differentiate between malignant and benign liver tumors. Additionally, Matlab App Designer was used to create a user-friendly interface for doctors. This application is also beneficial for students, offering a valuable tool for self-testing and skill development in clinical ultrasound courses and practical sessions. The proposed Matlab application employs classic image processing tools and serves as useful software for students learning liver ultrasound techniques. © 2024 IEEE.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Real-Time Medical IoT for Continuous Glucose Monitoring

Real-Time Medical IoT for Continuous Glucose Monitoring

引用

Intelligent Systems and Advanced Applications (ICISAA), International Conference on

作者： Akanksha Goel Poi Tamrakar Mily Lal Manisha Bhende Minal Wani Saurabh Saoji Dr.D.Y. Patil School of Science & Technology Dr.D.Y. Patil Vidyapeeth Pimpri Pune India Dr.D.Y. Patil Vidyapeeth Pimpri Dr.D.Y. Patil Biotechnology and bioinformatics Institute Pune India Dept.of Computer Engineering Nutan Maharashtra Institute of Engineering and Technology Pune

ISBN: (数字)9798331539948

ISBN: (纸本)9798331539955

This research is about Continuous Glucose Monitoring (CGM) technology and its pivotal role in revolutionizing diabetes care. Leveraging data obtained from a comprehensive study focused on evaluating CGM’s efficacy in diabetes management, this study investigates the impact and potential benefits of CGM usage on patients’ health after collecting the real secondary data through online forms. It encompasses a diverse array of patient-centric variables, including medical history, medication intake, physiological parameters, and CGM-derived glucose *** integrating machine learning techniques and statistical analysis, this study aims to derive valuable insights into the interplay between CGM data patterns and real-time activities, patients’ physiological profiles, and diabetes management outcomes. The extracted features and processed data serve as a foundation for subsequent predictive modeling, classification, and regression analysis. This research aims to contribute to the expansion of knowledge regarding the effectiveness of CGM technology in diabetes treatment. By exploring correlations between CGM data, patient attributes, and clinical outcomes, this study endeavors to pave the way for personalized and optimized diabetes management strategies.

关键词： Continuous glucose monitoring Wireless sensor networks Reviews Medical services Machine learning Quality of service Feature extraction Real-time systems Diabetes Internet of Things

来源：评论

学校读者我要写书评

暂无评论

IoT-Based Diagnosis and Recommendation System for Chronic Diseases Using Patient Health Records

IoT-Based Diagnosis and Recommendation System for Chronic Di...

引用

Advance Computing and Innovative Technologies in engineering (ICACITE), International Conference on

作者： S. K. UmaMaheswaran Durgaprasad Gangodkar V. Samatha I. S. Chakrapani Dharamvir Dharam Buddhi Department of Mathematics Sri Sai Ram Engineering College Chennai Tamil Nadu India Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun Uttarakhand India Computer Applications DKW Govt. College for Women (A) Nellore AP India Dept.of Zoology PRR&VS Govt College AP Dept. of MCA The Oxford College of Engineering Bangalore Uttaranchal Institute of Technology Uttaranchal University

The proliferation of IoT applications, notably in the sphere of health care, has led to discussion of patient health records utilising data gathered from IoT-connected devices. Biological data from patients' medical records is mined for health analysis and diagnosis. Certain types of illness, known as chronic illnesses, are completely quiet yet devastating if left untreated. Recent years have seen an uptick in interest from academics in the utilization of patient health information data for the pre-emptive identification of chronic diseases. On the other side, healthcare and medical assistance have benefited enormously from the implementation of recommender systems that use machine learning techniques. Using an Internet of Things device, this research implemented a medical recommendation system to aid in the early diagnosis and management of chronic conditions. The current technique made use of the dataset of digitised patient health records that is housed in the Physio Net data repository. The current dataset contains patient health records that have been documented in accordance with the diseases that have been identified and the doctor's diagnosis. The recommended technique uses K-nearest neighbour classification to identify the kind of ailment before using collaborative filtering to select the optimal course of treatment for patients. The outcomes of using the suggested methodology show that this technique, which is based on using patient symptom similarity, produces better results than previous methods and has a high precision in diagnosing and forecasting chronic illnesses. After determining the kind of disease using the closest neighbour classification method, the collaborative filtering strategy is utilised to select the optimal course of therapy for patients. The outcomes of using the suggested methodology show that this technique, which is based on using patient symptom similarity, produces better results than previous methods and achieves better accuracy

关键词：

来源：评论

学校读者我要写书评

暂无评论

Recognition of fabricated online reviews using semi-supervised learning

引用

AIP Conference Proceedings 2023年第1期2794卷

作者： B. Satyanarayana Dinesh Chandra Pancharia Dept.of Computer Science & Engineering AVANTHI Institute of Engineering & Technology Vizianagaram A.P India

In the World Online reviews have major impact on daily business and e-commerce. Purchase of products in online mostly depends on reviews given by the users, reviews are the major parameter of decision making. Thus, opportunistic individuals or groups attempt to use product reviews to advance their own interests. We propose some semi-supervised text mining models to detect false online reviews in this paper.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Endoscopic Image Processing: Evaluating the Robustness of Deep Neural Networks

Endoscopic Image Processing: Evaluating the Robustness of De...

引用

Smart Electronics and Communication (ICOSEC), International Conference on

作者： C N Gireesh Babu Kaparapu Satish Babu Sajja Suneel K.Srinivasa Rao Divya Muralitharan R Aarthi Dept.of CSE/ISE BMS Institute of Technology and Management Bengaluru Karnataka Department of Electronics and Communication Engineering Geetanjali College of Engineering and Technology Hyderabad Telangana India Department of CSE(Data Science) Institute of Aeronautical Engineering Dundigal Hyderabad Telangana India Department of AI&ML K.S.R.M. College of Engineering Kadapa Andhra Pradesh Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Department of ECE R.M.D Engineering College R. S. M Nagar Gummidipoondi

ISBN: (数字)9798331504403

ISBN: (纸本)9798331504410

The Hybrid CNN-Transformer Model (HCNNT) is a novel model which exploits Convolutional Neural Networks (CNN) for spatial feature extraction and Transformers for capturing contextual and long range dependencies in order to carry complex image classification. In order to evaluate the algorithm proposed, a new model has been introduced and trained on a data set of gastrointestinal (GI) image classification, which is derived from a balanced data set with 226 images available on Kaggle. Although the cascaded CNN part is to learn elaborate visual characteristics, the improved understanding of complex patterns and relationships is achieved by the Transformer component to process these features. When both are integrated, we gain a powerful system that has high accuracy in distinguishing GI bleeding condition from normal condition. Extensive training and optimization of the hybrid model using binary cross-entropy loss and Adam optimizer has achieved state-of-the-art performance. Through the experiments evaluated on the HCNNT model, it is evident that an accuracy of 97.34% proves to be significantly beneficial, its practicality in terms of reliability for medical image classification that essentially improves the accuracy of diagnosis in gastrointestinal healthcare.

关键词： Training Visualization Accuracy Transformers Feature extraction Gastrointestinal tract Robustness Convolutional neural networks Image classification Context modeling

来源：评论

学校读者我要写书评

暂无评论

Using human-guided causal knowledge for more generalized robot task planning

arXiv

引用

arXiv 2021年

作者： Tatlidil, Semir Liu, Yanqi Sheetz, Emily Bahar, R. Iris Sloman, Steven Dept.of Cognitive Linguistics and Psychological Sciences Brown University ProvidenceRI02912 United States Dept.of Computer Science Brown University ProvidenceRI02912 United States Dept.of Electrical Engineering and Computer Science Robotics Institute Univ. of Michigan Ann ArborMI48109 United States

A major challenge in research involving artificial intelligence (AI) is the development of algorithms that can find solutions to problems that can generalize to different environments and tasks. Unlike AI, humans are adept at finding solutions that can transfer. We hypothesize this is because their solutions are informed by causal models. We propose to use humanguided causal knowledge to help robots find solutions that can generalize to a new environment. We develop and test the feasibility of a language interface that naïve participants can use to communicate these causal models to a planner. We find preliminary evidence that participants are able to use our interface and generate causal models that achieve neargeneralization. We outline an experiment aimed at testing far-generalization using our interface and describe our longer terms goals for these causal models. © 2021, CC BY.

关键词： Robot programming

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：