检索结果-内蒙古大学图书馆

1st International Conference on Computing, sciences and Communications, ICCSC 2024

作者： Sinha, Niraj Kumar Pundir, Meena Dhiman, Tanu Chandigarh University Dept. of Computer Science & Engineering Gharuan Punjab Mohali India

ISBN: (纸本)9798350353648

Diabetes is a chronic disease posing a significant global health challenge, with the number of affected individuals projected to nearly double by 2045. This disease, which is characterized by high blood sugar, can cause severe complications such as kidney failure, blindness, and heart problems. To address this pressing concern this study target to enhanced machine learning technology-based system for the early understanding of diabetes with high accuracy. The suggested method makes use of the output of different technique, such as Decision Tree, Random Forest, K-Nearest Neighbor and Naive Bayes, to maximize their benefits and enhance overall prediction performance. The study evaluates the accuracy of each algorithm individually and selects the techniques with the best result as the final predictive system. The results of this study support ongoing initiatives to apply innovative data science methods for diabetes early diagnosis and treatment, ultimately assisting in the avoidance of the disease's severe consequences and enhancing patient outcomes. Based on the Random Forest classifier model, this model generated an accuracy of 96.83%. © 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

Genetic Algorithms and Computational Biology in Crop Improvement

Genetic Algorithms and Computational Biology in Crop Improve...

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Anand, Pushpam Raj, Shreyansh Pradhan, Soumya Ranjan Shah, Syed Sajid Hussain Verma, Shreyash Kumar, Vinod Chandigarh University Bachelor of Engineering Dept. of Computer Science Punjab 140413 India

ISBN: (纸本)9798331543617

Genetic algorithms (GAs) are a subset of machine learning and can potentially solve complex biological challenges in agriculture, including crop improvement. These algorithms help simulate the process of nature selection using techniques such as Mutation, Crossover, and Selection. Integrating genetic algorithms with computational biology can help improve the agriculture field's outcomes such as crop yield, resistance to crop diseases, and crop quality, and crops are more adaptable in the environment. The role of genetic algorithms in agriculture focuses on improving breeding strategies, optimizing agricultural outputs, sustainable farming, and enhancing global food security. © 2024 IEEE.

关键词： Livestock

来源：评论

学校读者我要写书评

暂无评论

Graph-based Named Entity Information Retrieval from News Articles using Neo4j 18

Graph-based Named Entity Information Retrieval from News Art...

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Chaudhary, Shikha Vyas, Hirenkumar Arora, Naveen D'Mello, Sejal Vidyavardhini's College of Engineering and Technology Dept. of Artificial Intelligence and Data Science Mumbai India

ISBN: (纸本)9789380544519

The internet, social media, and other cutting-edge technologies are all contributing to the exponential growth of digital information. This makes interpreting and applying this enormous amount of data both possible and challenging. Our research proposes a smart system that can convert unprocessed text into a knowledge graph in order to address this. This system makes use of the graph database Neo4j. Although there are currently available tools for linking entities and models to extract relationships, such as Spacy, NLTK, and Flair, their combined use is inefficient. Our suggested method seeks to efficiently blend entity linkage and relation extraction, allowing us to convert raw data into a knowledge graph. There are many real-world uses for this strategy, particularly in data analysis and decision-making. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Cypher Queries Graph database Information Retrieval Named Entity Recognition Neo4j News Articles Relation extraction

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Aided Privacy Preserving Framework for Federated Learning 2

Blockchain-Aided Privacy Preserving Framework for Federated ...

引用

2nd IEEE International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, ICIITCEE 2024

作者： Jain, Chitresha Chaudhari, Payal Pandit Deendayal Enerygy University Dept. of Computer Science and Engineering Gandhinagar India

ISBN: (纸本)9798350306415

Blockchain has shown tremendous growth in the past few years because of its decentralized and immutable architecture, which makes transactions transparent, making it a feasible choice for authentication and security purposes. Federated learning is a collaborative model training method that can benefit from Blockchain Technology. It is vulnerable to a single point of failure while performing aggregation in a centralized server architecture. Blockchain-aided Federated Learning can be proposed for enhancing the security and privacy of user data together with removing a single aggregator. It also supports a mechanism of giving rewards to users in the form of cryptocurrency to encourage users to follow the protocol. This paper introduces a framework named Blockchain-Aided privacy preserving framework for Federated Learning (BPPF) that helps in model training on the user side with added security and privacy. © 2024 IEEE.

关键词： Blockchain Differential Privacy Federated Learning Security

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Low Power Circuits Based on 5nm Double Gate MOSFET Technology Using Different Materials 3

Design and Implementation of Low Power Circuits Based on 5nm...

引用

3rd IEEE International Conference of Electron Devices Society Kolkata Chapter, EDKCON 2024

作者： Kundu, Shrabanti Mandal, Jyotsna Kumar. University of Kalyani Dept. of Computer Science and Engineering WB Kalyani Nadia India

ISBN: (纸本)9798350374643

This paper presents a comprehensive investigation of 5nm double gate MOSFETs (DG MOSFETs) circuits using different substrate semiconductor materials for low-power devices. A comparative analysis of characteristics of SiGe, InGaAs and GaN as substrate materials is performed. The study reveals that InGaAs offers superior performance due to its higher electron mobility, lower threshold voltage and thermal stability than other materials studied here for low-power applications. The electrical properties of DG MOSFETs on these substrates have been investigated by calculating key parameters such as threshold voltages (Vth), Ion and Ioff currents. The results show that InGaAs-based DG MOSFETs exhibit superior performance with threshold voltage, improved leakage current and Ion/Ioff ratio compared to other substrate materials. Additionally, a lower threshold voltage has been observed for InGaAs-based devices, indicating reduced power consumption. These findings demonstrate the potential of InGaAs as a preferred substrate material for low-power, high-performance DG MOSFET devices. Double gate MOSFET circuits are designed using InGaAs and power dissipation is calculated. The results show a significant reduction in power consumption and improved circuit performance compared to traditional Si-based devices. This research demonstrates the potential of InGaAs-based DG MOSFETs for low-power electronic devices, enabling the development of energy-efficient circuits for various applications. © 2024 IEEE.

关键词： III-V semiconductors

来源：评论

学校读者我要写书评

暂无评论

MSCE-LT: Multi-Label Supervised Contrastive Enhancement for Long-Tailed Retinal Diseases Recognition

MSCE-LT: Multi-Label Supervised Contrastive Enhancement for ...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Li, Tingyao Sheng, Bin Shanghai Jiao Tong University Dept. Computer Science and Engineering Shanghai China

ISBN: (纸本)9798350386226

Retinal diseases are leading causes of blindness globally. In real-world clinical practice, a patient may suffer from multiple retinal diseases, and these diseases are often under a long-tailed distribution, which poses significant challenges for accurate diagnosis. In this work, we propose a novel contrastive learning(CL)-based framework for multi-label retinal disease recognition. It consists of two parallel branches, a multi-label supervised contrastive learning branch and a classifier branch. The positive sets are created by the extent of proportional label overlap between samples and the anchor in calculating contrastive loss. For minority information enhancement, we design a hybrid-proxy model to generate class-dependent proxies, which are updated alongside the network. We capture rich relations samples, proxies, and labels by introducing the hybrid sample-proxy contrastive loss. Taking both label co-occurrence and data imbalance into consideration, we further utilize Distribution Balanced (DB) binary cross-entropy loss to guide the classifier branch learning. Experimental results on four public retinal disease datasets have demonstrated the superiority and effectiveness of our method. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Compressed Sensing for Real-Time Electrocardiogram Acquisition on Low-Power Medical Devices

Efficient Compressed Sensing for Real-Time Electrocardiogram...

引用

2024 IEEE-EMBS International Conference on Biomedical and Health Informatics, BHI 2024

作者： Terrell, Mitchell Weissman, Jon University of Minnesota Dept. of Computer Science and Engineering MinneapolisMN United States

ISBN: (纸本)9798350351552

Low cost wearable and implantable cardiac monitoring devices (WCM & ICM), combined with increasingly accurate disease and arrhythmia detection algorithms have proven effective to help slow the impact of cardiovascular disease, the worlds leading cause of death in 2022 [1]. Improvements to server-side detection algorithms along with hardware limitations of these devices such as slow processor speeds and minimal battery life has led to a desire to offload data from the devices for later analysis. Paired with limited storage capacity, this has led to a push to decrease the necessary storage for electrocardiogram (EKG) signals without sacrificing disease detection accuracy and device longevity. A promising recent innovation in EKG compression has come from Compressed Sensing (CS), which exposes inherent sparseness in the signal to selectively sample for eventual server-side reconstruction. Many CS approaches have been implemented on WCM devices which demonstrate a high compression ratio (CR) and accurate signal reconstruction, but quickly become impractical for the stricter hardware constraints of ICM devices due to the increased computation on the device and slow reconstruction time. In this paper we propose a CS approach known as Tailored Sensing (TS) which combines on-device prior knowledge, a custom transform basis, and optimal sense location selection to achieve improved CR and reconstruction accuracy while eliminating on-device computational burden and slow reconstruction time. Our approach offers equivalent or better signal reconstruction at previously unfathomable CRs due to our novel signal segmentation scheme. Additionally, our approach boasts a zero overhead on-device sensing strategy and a 93 % reduction in signal reconstruction time. © 2024 IEEE.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Quora Question Sincerity Detection Using BERT-Based Framework 14

Quora Question Sincerity Detection Using BERT-Based Framewor...

引用

14th International Conference on Cloud Computing, data science and engineering, Confluence 2024

作者： Arora, Drishti Aggarwal, Garima Asif, Farhan Amity University Dept. of Computer Science and Engineering Uttar Pradesh Noida India

ISBN: (纸本)9798350344837

In the dynamic landscape of online knowledge exchange, platforms such as Quora have become vital arenas for diverse discussions and information dissemination. However, distinguishing sincere from insincere questions poses a challenge, impacting user experience and content credibility. The research seeks to utilize BERT-based frameworks to classify Quora questions, with a specific focus on discerning between sincere and insincere inquiries. The study underscores the significance of automated insincere content identification in fostering a trustworthy and constructive online environment on Quora, thereby contributing to the improvement of online interaction quality. The research delves into a comprehensive methodology, including data preprocessing, model training, fine-tuning, and performance evaluation. Extensive experimentation demonstrates that the proposed BERT-based approach achieves an impressive F1-score of 96.1%, outperforming existing methods. The contribution of the study lies in its potential to enhance online interactions by automating the identification of insincere content, fostering a conducive environment for meaningful conversations. © 2024 IEEE.

关键词： Information dissemination

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Electric Kickboard Helmet Detection under Night Driving Conditions

引用

Transactions of the Korean Institute of Electrical Engineers 2022年第10期71卷 1411-1419页

作者： Kim, Daun Jeong, Jin-Woo Dept. of Data Science Seoul National University of Science and Technology Korea Republic of Dept. of Industrial Engineering Seoul National University of Science and Technology Korea Republic of

As the use of electric kickboards has increased recently, the frequency of safety accidents is also increasing. Even though the government amended the road traffic law to make it compulsory to wear a helmet, the helmet-wearing rate is still remarkably low. In this work, we propose a novel method to monitor and detect whether a user of an electric kickboard is wearing a helmet through a deep learning-based object detection network, thereby increasing the helmet-wearing rate. For continuous driver monitoring, the proposed method captures the user's face in a front view using the user's mobile phone attached to the kickboard. In addition, to handle both day and night driving conditions, various image conversion, enhancement, and augmentation techniques were considered and evaluated. The experimental results showed the feasibility of the proposed method. © 2022 Korean Institute of Electrical Engineers. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Automatic Detection of Hypernasality in Cleft Palate Speech Using Phase Feature 14

Automatic Detection of Hypernasality in Cleft Palate Speech ...

引用

14th International Conference on Cloud Computing, data science and engineering, Confluence 2024

作者： Hashreta, Kanuri Naga Venkata Sai Lalitha, Duggaraju Sri Lahari, Maddula Lalitha Sri, Pittala Deepthi Dubey, Akhilesh Kumar Koneru Lakshmaiah Education Foundation Dept. of Computer Science and Engineering Guntur India

ISBN: (纸本)9798350344837

The detection of hypernasality, a speech disorder common in children with cleft palate, typically involves analyzing vowels within speech stimuli. An essential acoustic cue for hypernasality detection is the presence of a nasal peak near the first formant (F1). Traditionally, a two-step process is employed, where vowel selection from stimuli is initially performed through manual annotation, followed by automatic feature extraction and classification. This work introduces a novel method for hypernasality detection, automating the entire process, including vowel region selection, feature extraction, and classification. The method leverages vowel onset points for the automatic identification of the vowel region. Subsequently, a modified group delay cepstral coefficient feature is extracted from this automatically selected vowel region. The feature is extracted from modified group delay spectrum, offering enhanced resolution to distinguish closely spaced nasal peaks and the F1, thus improving the capture of nasality evidence. The proposed method demonstrates promising results when applied to hypernasality detection using a support vector machine classifier with the accuracy of 83.50% for /a/ vowel and 93.21% for /i/ vowel. © 2024 IEEE.

关键词： Support vector machines

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：