检索结果-内蒙古大学图书馆

5th International Conference on Smart Electronics and Communication, ICOSEC 2024

作者： Rao, M. Nagabhushana Reddy, L. Venkateswara Ganesh, D. Reddy, Lakkireddy Udanth Mohana, R Madana Marri Laxman reddy institute of Technology & Management Cse Hyderabad India Joginapally B. R. Engineering College Department of Cse RR Dist Yenkepally Telangana Hyderabad501504 India Cse Andhra Pradesh Tirupati India VIT-AP University Dept. of Ece Amaravath India Artificial Intelligence & Data Science Chaitanya Bharathi Institute of Technology Telangana Hyderabad500075 India

ISBN: (纸本)9798331504403

Breast cancer accounts for an extremely high annual death rate. Many tools have been created to facilitate earlier diagnosis of breast cancer, which is the most common cancer among females. According to the research, cancer of the breast is also regarded as the second most deadly form of the disease. It is the most prominent kind of the disease and the top reason for death among females worldwide. Any progress made in the early detection and identification of cancer is crucial to maintaining good health. Therefore, it is essential to improve both the therapeutic aspect and the survival standard of patients by utilizing high precision in cancer prognosis. A reliable, effective, and speedy reaction from medical professionals is provided by an automatic disease identification system, which also reduces the danger of death. Recently, breast cancer screening methods that utilise deep learning have shown promising results, allowing for earlier identification and thereby enhancing patients' chances of survival thanks to the introduction of artificial intelligence (AI). Deep learning reduces the need for manual intervention while extracting features, in comparison to traditional machine learning methods. We provide a brief overview of deep learning techniques, data availability, and the many breast cancer screening options, such as mammography, thermography, ultrasound, and MRI. Using demographic, laboratory, & mammographic data, this investigation sought to forecast breast cancer using various Deep learning algorithms. Ultimately, we apply artificial intelligence to breast cancer clinical trials and compare the proposed approach to current algorithms. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

FogMedX-Transform: A Transformer-Based Task Interoperability Framework for Energy-Efficient Fog-Enabled IoMT

FogMedX-Transform: A Transformer-Based Task Interoperability...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： R Jayakarthik Sajja Suneel Jayendra Gopal Thatipudi V. Jaganraja Minesh Vohra Gopinath D Dept of Computer science Saveetha College of Liberal Arts and Sciences SIMATS Department of CSE(Data Science) Institute of Aeronautical Engineering Dundigal Hyderabad Telangana India Dept. of Computer Science University of North Texas Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Chennai India School of Mechanical Engineering Lovely Professional University Phagwara Department of Computer Science Kristu Jayanti College (Autonomous) Bengaluru Karnataka India

ISBN: (数字)9798331512248

ISBN: (纸本)9798331512255

The increasing speed of Internet of Medical Things (IoMT) development requires framework approaches that secure, efficient, and scalable for healthcare data management. The study presents FogMedX-Transform as a Transformer-based task interoperability framework purposebuilt for energy-efficient fog-enabled IoMT systems. A customized Transformer design utilizing multi-head selfattention allows the framework to deliver timely critical healthcare data processing alongside optimized energy usage. This model demonstrated a 98.7% task interoperability success rate coupled with a 97.5% anomaly detection accuracy that exceeded results from conventional models based in fog environments and the cloud. The framework improved performance through latency reduction between 50% and 70% and energy consumption minimization reached between 25% to 40% thus proving its effectiveness in resource administration. The scalability tests proved steady system functionality when dealing with different device quantities and built-in security features blocked data breaches and had a false positive rate of 2.3% during testing. FogMedX-Transform demonstrates the capability for healthcare transformation through its union of fog computing and deep learning technology integration according to test results.

关键词： Deep learning Performance evaluation Internet of Medical Things data breach Transformers data processing Energy efficiency Real-time systems Interoperability Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

MEIL-NeRF: Memory-Efficient Incremental Learning of Neural Radiance Fields

arXiv

引用

arXiv 2022年

作者： Chung, Jaeyoung Lee, Kanggeon Baik, Sungyong Lee, Kyoung Mu Dept. of Electrical and Computer Engineering ASRI Seoul National University Seoul Korea Republic of Dept. of Data Science Hanyang University Seoul Korea Republic of

Hinged on the representation power of neural networks, neural radiance fields (NeRF) have recently emerged as one of the promising and widely applicable methods for 3D object and scene representation. However, NeRF faces challenges in practical applications, such as large-scale scenes and edge devices with a limited amount of memory, where data needs to be processed sequentially. Under such incremental learning scenarios, neural networks are known to suffer catastrophic forgetting: easily forgetting previously seen data after training with new data. We observe that previous incremental learning algorithms are limited by either low performance or memory scalability issues. As such, we develop a Memory-Efficient Incremental Learning algorithm for NeRF (MEIL-NeRF). MEIL-NeRF takes inspiration from NeRF itself in that a neural network can serve as a memory that provides the pixel RGB values, given rays as queries. Upon the motivation, our framework learns which rays to query NeRF to extract previous pixel values. The extracted pixel values are then used to train NeRF in a self-distillation manner to prevent catastrophic forgetting. As a result, MEIL-NeRF demonstrates constant memory consumption and competitive performance. © 2022, CC BY.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Learning Superconductivity from Ordered and Disordered Material Structures 38

Learning Superconductivity from Ordered and Disordered Mater...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Chen, Pin Peng, Luoxuan Jiao, Rui Mo, Qing Wang, Zhen Huang, Wenbing Liu, Yang Lu, Yutong National Supercomputer Center in Guangzhou School of Computer Science and Engineering Sun Yat-sen University China Dept. of Comp. Sci. & Tech. Institute for AI BNRist Center Tsinghua University China Institute for AIR Tsinghua University China Gaoling School of Artificial Intelligence Renmin University of China China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China

Superconductivity is a fascinating phenomenon observed in certain materials under certain conditions. However, some critical aspects of it, such as the relationship between superconductivity and materials' chemical/structural features, still need to be understood. Recent successes of data-driven approaches in material science strongly inspire researchers to study this relationship with them, but a corresponding dataset is still lacking. Hence, we present a new dataset for data-driven approaches, namely SuperCon3D, containing both 3D crystal structures and experimental superconducting transition temperature (Tc) for the first time. Based on SuperCon3D, we propose two deep learning methods for designing high Tc superconductors. The first is SODNet, a novel equivariant graph attention model for screening known structures, which differs from existing models in incorporating both ordered and disordered geometric content. The second is a diffusion generative model DiffCSP-SC for creating new structures, which enables high Tc-targeted generation. Extensive experiments demonstrate that both our proposed dataset and models are advantageous for designing new high Tc superconducting candidates. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Space-Frequency Diversity based MAC protocol for IEEE 802.11 ah networks 15

Space-Frequency Diversity based MAC protocol for IEEE 802.11...

引用

15th International Conference on Advanced Technologies for Communications, ATC 2022

作者： Minh Dang, Duc Ngoc Tran, Van Thau Nguyen, Hoang Lam Pham, Nhat Truong Tran, Anh Khoa Dang, Ngoc-Hanh Fpt University Dept. of Computing Fundamental Ho Chi Minh City Viet Nam Ton Duc Thang University Dept. of Electrical and Electronics Eng. Ho Chi Minh City Viet Nam Institute for Computational Science Ton Duc Thang University Ho Chi Minh City Viet Nam Ho Chi Minh City University of Technology Dept. of Telecommunications Engineering Ho Chi Minh City Viet Nam

ISBN: (数字)9781665451888

ISBN: (纸本)9781665451888

IEEE 802.11ah is a sub-GHz communication technology to offer longer range and low power connectivity for the Internet of Things (IoT) applications. A Restricted Access Window (RAW) is specified to decrease the collision probability. Stations are divided into groups and stations from each group attempt to access the channel by employing the Distributed Coordination Function during their assigned RAW slots. However, the network throughput is limited by a single channel MAC protocol. In this paper, Space-Frequency Diversity-based MAC protocol for the IEEE 802.11ah network (SF-MAC protocol) is proposed to allow stations of different sectors to transmit packets on different channels with the help of Forwarders. The proposed SF-MAC protocol improves the packet delivery ratio and aggregate throughput of the network. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

dataset Preprocessing Leveraging Vision Language Models: Storytelling for Accident Detection and Description

Dataset Preprocessing Leveraging Vision Language Models: Sto...

引用

Electrical engineering (ICEENG), International Conference on

作者： Mohamed Yossri Elwaly Amgad Abdo Aly Ahmed Sewelam Sarah Elshamy Asmaa Zayed Mohamed Elsayed Mohamed Abdou Mohamed Saleh Faculty of Computers and Data Science Alexandria University Alexandria Egypt Dept. of Electrical Engineering Phaors Uniersity in Alexndria Alexandria Egypt Faculty of Computer Science and Engineering Alamein International University (AIU) Alamein Egypt Informatics Research Institute City of Scientific Research and Technological Applications (SRTA-City) Alexandria Egypt

ISBN: (数字)9798331519018

ISBN: (纸本)9798331519025

In recent years, the Vision-Language Models (VLMs) have significantly advanced the field of storytelling applications. Visual storytelling involves the use of Generative AI models to transform a sequence of video frames into a semantics-preserving story-like text. A critical aspect of developing these models lies in the preparation of datasets, which directly impacts their efficacy and robustness. This paper explores a comprehensive methodology for dataset preparation tailored to the detection and description of car accidents in video surveillance footage. This research explains the necessity of data collection, annotation, and preprocessing to transform a sequence of frames in a video into a semantics-preserving story-like text. We describe the steps, tools and challenges of this task.

关键词： Electrical engineering Generative AI Visual analytics Scalability Semantics Transforms Video surveillance Robustness Automobiles Accidents

来源：评论

学校读者我要写书评

暂无评论

ANFIS Model for Cost Analysis in a Dual Source Multi-Destination System

引用

Procedia Computer science 2023年 217卷 1266-1279页

作者： M.O. Okwu L.K. Tartibu E.O. Ojo S. Adume J.O. Gidiagba J. Fadeyi Department of Mechanical and Industrial Engineering Tech. University of Johannesburg South Africa Department of Mechanical Engineering Federal University of Petroleum Resources Effurun Nigeria Mathematics and Data Science Dept. Computing Science and Mathematics Division Faculty of Natural Science University of Stirling UK Faculty of Engineering and Applied Sc. Memorial University Newfoundland Canada Department of Industrial and Systems Engineering University of Buffalo USA

Managers face uncertainties while making allocation decisions, especially in dual or multi-source multi-destination inventory systems. Regrettably, many studies focus on classical methods as a technique for product distribution, which has never guaranteed a satisfactory solution. Real-life problems are non-deterministic polynomial-time hard (NP-hard), and solving such problems is relatively challenging. Such complicated problems need an efficient and robust computational hybrid algorithm. This study emphasises the need for a hybrid intelligent technique for effective product distribution. Soft computing hybrid algorithm, ANFIS was applied to product distribution in a double source multi-destination system. Rules were developed from available input datasets. Distributing products from dual manufacturing plants to fifteen available depots using the creative algorithm resulted in an overall 13.5% decrease in cost compared to the existing method adopted by the company. The result showed that the proposed method is relatively satisfactory and adequate for cost modelling. In addition, it is easy to use and outperforms the classical approach.

关键词： Adaptive Neuro-Fuzzy Inference System Dual Source Multi-Echelon Multi-Destinations

来源：评论

学校读者我要写书评

暂无评论

Collaborative Filtering ML Technique for Recommendation in E-Commerce Energy System 5

Collaborative Filtering ML Technique for Recommendation in E...

引用

5th IEEE International Conference on Electro-Computing Technologies for Humanity, NIGERCON 2024

作者： Yen, Hew Sok Ajibade, Samuel-Soma M. Hoong, Angela Lee Siew Culpable, Rex V. Quirante, Celestino A. Dayupay, Johnry P. Adetunla, Adedotun O. Oyebode, Oluwadare Joshua Sunway University School of Engineering and Technology Department of Data Science and Artificial Intelligence Selangor Malaysia Selangor Malaysia Cebu Technological University College of Technology Moalboal Cebu Philippines Cebu Technological University Moalboal Cebu Philippines Afe Babalola University Dept. of Mechanical and Mechatronics Engineering Ekiti Ado Nigeria University of Johannesburg Dept. of Mechanical Engineering Science Johannesburg South Africa Afe Babalola University Civil and Environmental Engineering Department Ekiti Ado Nigeria

ISBN: (纸本)9798331542559

The growing integration of e-commerce into daily life has highlighted the essential need for recommender systems to enhance user experience and drive business success. This study examines machine learning techniques for developing effective recommender systems, with a particular focus on collaborative filtering (CF) and content-based filtering (CBF) methods. This study employs exploratory data analysis (EDA) to analyze e-commerce statistics, identifying trends in consumer behavior, product ratings, and user engagement, culminating in the development of a hybrid recommender system. The hybrid method amalgamates the benefits of Continuous Feedback (CF) with Context-Based Feedback (CBF) to deliver customized recommendations, hence improving accuracy and relevance for users. The application of hybrid models yields a notable improvement in predictive performance, evidenced by reduced mistake rates and heightened customer satisfaction. This research offers distinctive insights on user-product interactions, thereby advancing the comprehension of how machine learning could transform e-commerce personalization. © 2024 IEEE.

关键词： Marketplaces

来源：评论

学校读者我要写书评

暂无评论

Advancing Wearable Electronics via Shoe-Integrated Piezoelectric Energy Harvesting

Advancing Wearable Electronics via Shoe-Integrated Piezoelec...

引用

IEEE International Conference on Signal Processing, Information, Communication & Systems (SPICSCON)

作者： Akib Jayed Islam Sultanus Salehin Shreya Paul Prithwi Chowdhury Sayem UI Alam Prithy Paul Computational Colour and Spectral Imaging Norwegian University of Science and Technology Gjovik Norway Dept. of ECE The University of Alabama Tuscaloosa USA Electrical & Electronics Engineering National Institute of Technology Trichy Tamil Nadu India Electrical & Electronic Engineering Ahsanullah University of Science & Technology Dhaka Bangladesh Electrical and Computer Engineering The University of Alabama Tuscaloosa USA Computer Science and Engineering East Delta University Chattogram Bangladesh

ISBN: (数字)9798331510213

ISBN: (纸本)9798331510220

This research explores the viability of utilizing human locomotion as a renewable energy source through piezo- electric energy harvesting. By embedding piezoelectric transducers within footwear, mechanical energy generated during movement can be effectively converted into electrical energy. A comprehensive power management circuit, including a battery, rectifier, and DC-DC converter, is proposed to optimize energy capture and storage. Experimental results demonstrate significant improvements in energy harvesting efficiency through strategic placement and sizing of the piezoelectric transducer within the shoe soles. These findings underscore the potential of this method for powering wearable electronics, advancing the development of sustainable, self-powered devices. Moreover, this approach extends the application of piezoelectric energy harvesting beyond traditional power sources, facilitating the creation of self-sustaining wearable sensors and devices, with potential applications in fields such as rehabilitation and sports science.

关键词： Electric potential Power system management Piezoelectric transducers Rectifiers Footwear Medical services Energy harvesting Piezoelectric devices Wearable devices Sports

来源：评论

学校读者我要写书评

暂无评论

Long Short-Term Memory-Based Next Keyword Prediction

Long Short-Term Memory-Based Next Keyword Prediction

引用

Emerging Smart Computing and Informatics (ESCI), Conference on

作者： Rajkumar. K Karthikeyan. S U. Hariharan Dept. of Data Science and Business Systems College of Engineering and Technology SRM Institute of Science & Technology Kattankulathur Tamilnadu India Department of CSE FET Jain (Deemed-to-be University) Bangalore Department of CSE Apex Institute of Technology Chandigarh University Punjab India

This paper focuses on a method that uses an LSTM model to predict the next word of a sentence. Based on Katz's Backoff model, it has been designed to improve and further succeed in our previous work. The main intention here is to show how effective the LSTM model is when compared to Katz's backoff model in terms of the number of n-grams required to predict the next word, and it also helps you predict more accurately. Here LSTM is used for processing, prediction and classification. Since the LSTM model is efficient and has been modified to the task at hand, the model offers very highly accurate predictions even though have used only a tiny portion of the entire corpus. When comparing the existing model, the proposed model predicts the word with accuracy of 90%.

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：