检索结果-内蒙古大学图书馆

2023 International Conference on Integrated Intelligence and Communication systems, ICIICS 2023

作者： Ghantasala, G. S. Pradeep Kunchala, Anjaneyulu Sathiyaraj, R. Venkateswarulu Naik, B. Raparthi, Yaswanth Vidyullatha, P. Alliance University Faculty of Science & Technology Alliance College of Engineering and Design Bengaluru India Gitam University Gitam School of Technology Department of Computer Science and Engineering Karnataka Bangalore India Computer Science Engineering Narasimha Reddy Engineering College Hyderabad India Computer Science Engineering Vellore Institute of Technology TN Vellore India Computer Science Engineering Koneru Lakshmaiah Education Foundation A.P Guntur India

ISBN: (纸本)9798350315455

Subclass of Artificial Intelligence, machine learning integrates several optimizations, probabilistic, and statistical methodologies to help computers learn from prior occurrences and find it challenging to spot patterns in intricate datasets, noised and large datasets. As a result, machine learning in cancer diagnosis and detection has increased. In women, breast cancer is the utmost common malignancy. The study aims to predict breast cancer by comparing widely used machine learning algorithms and methodologies, neural networks, Random Forest, and Boosting, upon Wisconsin Diagnosis Breast Cancer data set to inspect the performance of critical characteristics such as precision and accuracy. This study's accurate, competitive results can be used for detection and treatment. © 2023 IEEE.

关键词： Artificial intelligence Boosting Cancer prediction Neural network Random Forest

来源：评论

学校读者我要写书评

暂无评论

The Health Impact of Consuming Smoked Fish and Roasted Plantain on Albino Rats by Serum Enzyme Assay

引用

Proceedings of the National Academy of sciences India Section B - Biological sciences 2023年第1期93卷 181-188页

作者： Amaihe, Ugochukwu Ikechukwu Onyeze, Godfrey Osuagwu, Obinna Ikechukwu Enyoh, Christian Ebere Akakuru, Ozioma Udochukwu Department of Natural Sciences National Institute for Nigerian Languages Aba Nigeria Department of Biochemistry Faculty of Science Federal University of Technology Imo State Owerri Nigeria Power System Engineering Unit Department of Electrical and Electronics Engineering Federal University of Technology Imo State Owerri Nigeria Graduate School of Science and Engineering Saitama University Saitama Japan Department of Chemical and Petroleum Engineering Schulich School of Engineering University of Calgary AB Canada

Over the years, grilling and smoking as food preparation techniques have been found to introduce polycyclic aromatic hydrocarbons (PAHs) to the food products. Such food products when ultimately consumed by human could pose sever health challenges. Here, the effects of consumption of smoked fish and roasted plantain on the serum enzymes of Wistar albino rats were investigated as a method of determining the potential effect of such food consumption on humans. To achieve this, twenty-eight (28) Wistar male albino rats were fed with different concentrations (5, 10, and 20%) of smoked fish and/or roasted plantain for 21 days and killed after 28 days to collect serum for investigating the activities of aspartate aminotransferase (AST), alanine aminotransferase (ALT), and alkaline phosphatase (ALP). Results obtained for AST and ALT in the serum of rats fed with different concentrations of smoked fish and/or roasted plantain were significantly (p < 0.05) different from those obtained for control rats. However, the activity of ALP was substantially lower in the rats fed with different concentrations of smoked fish and roasted plantain when compared to that of the control. Thus, exposure of the albino rats to smoked or roasted foods which inherently contain PAHs induced changes in the activities of AST, ALT, and ALP, which are an indication of the effect on health. This study therefore promotes the awareness on potential human health implications of consuming smoked fish and roasted plantain, which could guide public health policies and decisions. © 2022, The Author(s), under exclusive licence to The National Academy of sciences, India.

关键词： Alanine aminotransferase Albino rats Alkaline phosphatase Aspartate amino transferase Plantain Smoked fish

来源：评论

学校读者我要写书评

暂无评论

Pre-trained Self-Attention Framework: An Efficient Mechanism for Source Separation 13th

Pre-trained Self-Attention Framework: An Efficient Mechanism...

引用

13th International Conference on Information technology and its Applications, CITA 2024

作者： Minh Tan, Ha Fhadli, Muhammad Kim Quoc, Nguyen Vu, Duc-Quang Faculty of Information Technology Nguyen Tat Thanh University Ho Chi Minh City Viet Nam Department of Informatics Faculty of Engineering Khairun University Ternate City Indonesia Department of Computer Science and Information System Thai Nguyen University of Education Thai Nguyen Viet Nam

ISBN: (纸本)9783031741265

In this work, the pre-trained model of the self-attention framework is proposed for single-channel speech separation. Firstly, all layers in the pre-trained self-attention framework are frozen. The model is then retrained through three stages using the scheduling mechanism for learning rates and the layers of the framework are unlocked following the schedule. This way, the model is relearned, enhanced, and updated from previous knowledge. This is an effective way to improve the advanced model performance while significantly reducing the time and cost of a training model. This method is beneficial in applying existing models to perform a similar task or enhancing model performance. In this strategy, the pre-trained system outperforms the non-pre-trained system since the following phases of the model’s training repurpose characteristics extracted through the previously trained early phases. The suggested method is tested and assessed on a conventional dataset. The findings from experiments suggest that the methodology has higher performance than the baseline framework and outperforms current methods for the monaural speech separation task. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： fine-tuning framework pre-trained model self-attention mechanism speech separation time masking framework Transformer

来源：评论

学校读者我要写书评

暂无评论

Neutronic and Thermal-Hydraulic Analyses for an Additive Manufacturing Reactor Core With SiC Matrix and TRISO Particle Fuel 29

Neutronic and Thermal-Hydraulic Analyses for an Additive Man...

引用

2022 29th International Conference on Nuclear engineering, ICONE 2022

作者： Han, Wenbin Deng, Jian Lu, Qi Chen, Chong Xu, Youyou Zhang, Tao Huang, Shanfang Department of Engineering Physics Tsinghua University Beijing China Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of China Chengdu China

ISBN: (纸本)9780791886502

Additive manufacturing (AM) is a transformational digital manufacturing technology featured with rapidity, customizability, precision, and economy, which is fundamentally altering the way components are designed and manufactured. AM enables the freedom of design, and makes full use of complexity of geometry which comes for free . Applying AM technology to nuclear industry can yield advanced reactor designs with function and structure matched for the best thermal, hydraulic and mechanical performance. In this work, an AM-informed reactor core design with silicon carbide (SiC) matrix and tri-structural isotropic (TRISO) particle fuel is proposed and analyzed. The core is an integrated 3D-printing SiC bulk with helical cruciform coolant channels, and the UO2-bearing TRISO fuel particles are dispersed in the bulk. A multi-physics analysis framework for irregular geometry is developed to analyze and further optimize the reactor design. The TRISO particle positions are generated with discrete element method (DEM). The Reactor Monte Carlo code (RMC) and the commercial CFD software STAR-CCM+ are used for the neutronic and thermal-hydraulic analyses, respectively. RMC simulates the neutron transport to predict the effective multiplication factor and power distribution. STAR-CCM+ calculates the flow and heat transfer in coolant channels and heat conduction in solid matrix with the power distribution as the heat source. Preliminary results show that the power peaking factor FQ decreases below 1.65, the heat transfer area increases by 30.3% and the fuel peaking temperature decreases by 25 K. The optimized AM-informed design enjoys better neutronic and thermal-hydraulic performance than those with regular geometry. © 2022 by ASME.

关键词： 3D printers

来源：评论

学校读者我要写书评

暂无评论

TEG-Self-Powered system for Wireless Sensing Node Operating in Aqua-Greenhouse

引用

IEEJ Transactions on Sensors and Micromachines 2024年第10期144卷 332-337页

作者： Quan, Nguyen Hoang Van An, Nguyen Huy, Ho Thanh Tuoi, Truong Thi Kim Ono, Takahito Nguyet, Nguyen Phan Minh Cuong, Mai Thanh Tan Nhan, Nguyen Chi Van Toan, Nguyen Van Hieu, Nguyen BiSAE lab Department of Physics and Electronic Engineering Faculty of Physics- Engineering Physic University of Science 227 Nguyen Van Cu Str. Dist. 5 Ho Chi Minh city Viet Nam Department of Mechanical System Engineering Graduate School of Engineering Tohoku University 6-6-01 Aramaki-Aza-Aoba Aoba-ku Sendai980-8579 Japan Department of Science and Technology Vietnam National University Ho Chi Minh City Linh Trung ward Thu Duc Ho Chi Minh city Viet Nam

This research focuses on harnessing excess heat energy in Aquaponic greenhouses-a system combining vegetable and fish cultivation with water circulation, where a perpetual temperature difference exists between the greenhouse air and the water in hydroponic vegetable tubes. Our objective is to convert this temperature difference into electric power for using in wireless IoT sensing systems. Nineteen thermoelectric generators (TEG-12708) were evaluated in a laboratory environment to determine their internal resistance and corresponding load resistance for experimental energy surveys in greenhouses. The maximum output power reached 699.38 µW when the temperature difference across the TEG was 3°C. Furthermore, we successfully demonstrated a sensing system driven by the realistic ambient temperature environment by integrating the TEG with other electronic components, including a DC-DC converter, power management circuit, supercapacitor, and sensors. Under aqua-greenhouse conditions, the harvested temperature difference across the TEG was 3.5°C, corresponding to the TEG’s output power of 0.55 mW. The output of the DC-DC converter could reach over 8 V. This work opens up new opportunities for TEGs to harness ambient aqua-greenhouse energy and convert it into usable electricity for wireless IoT sensing systems. © 2024 The Institute of Electrical Engineers of Japan.

关键词： Signal receivers

来源：评论

学校读者我要写书评

暂无评论

Smart Assistive system for Paralysis Patients using Finger Flex Sensors, Eye Movement Detection, and Vital Sign Monitoring 8

Smart Assistive System for Paralysis Patients using Finger F...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Kokila, N. Anandaraju, M.B. Dankan Gowda, V. Manoj Kumar, S.B. Naveen, K.B. Shobha, B.N. Adichunchanagiri University Vlsi Design & Embedded System Bgs Institute of Technology Karnataka B G Nagara571448 India Adhichunchangiri University Bgsit Department of Ece BG Nagara India Bms Institute of Technology and Management Department of Electronics and Communication Engineering Karnataka Bangalore India Adichunchanagiri University Faculty of Engineering Management & Technology Bgsit Dept. of Ece Karnataka B G Nagara571448 India Adichunchanagiri University Faculty of Engineering Management and Technology Bgsit B G Nagara571448 India

ISBN: (纸本)9798350376425

This research presents a novel assistive system designed to address communication and health monitoring challenges faced by paralysis patients. By integrating finger flex sensors, eye movement recognition, and vital sign measurement, the system offers a holistic solution for patient care. The proposed system utilizes a microcontroller and Bluetooth module to transfer sensor data to a mobile application, enabling effective communication between patients and caregivers. Performance analysis demonstrates the system's high accuracy in finger flex detection, eye blink recognition, and health monitoring. User feedback highlights the system's ease of use and its ability to facilitate communication and improve the quality of life for paralysis patients. The study emphasizes the system's extensibility, allowing for future integration of advanced sensor technologies and data analytics systems to enhance its capabilities and versatility. This assistive system represents a significant step towards improving the lives of paralysis patients by providing a reliable and effective communication and health monitoring solution. © 2024 IEEE.

关键词： Assistive technology

来源：评论

学校读者我要写书评

暂无评论

A novel K-nearest neighbor classifier for lung cancer disease diagnosis

引用

Neural Computing and Applications 2024年第35期36卷 22403-22416页

作者： Sachdeva, Ravi Kumar Bathla, Priyanka Rani, Pooja Lamba, Rohit Ghantasala, G. S. Pradeep Nassar, Ibrahim F. Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura India Chandigarh University Punjab Gharuan Mohali India Haryana Mullana Ambala India Haryana Mullana Ambala India Department of Computer Science and Engineering Alliance College of Engineering and Design Alliance University Bengaluru India Faculty of Specific Education Ain Shams University 365 Ramsis Street Abassia Cairo Egypt

One of the world's deadliest diseases is lung cancer. Based on a few features, machine learning techniques can help in the diagnosis of lung cancer. The performance of several classifiers: support vector machine (SVM), logistic regression (LR), Naïve Bayes (NB), random forest (RF), and K-nearest neighbor (KNN), was evaluated by the authors using the dataset available on Kaggle to create a systematic approach for the diagnosis of lung cancer disease based on readily observable signs and historical medical data without the requirement of CT scan images. The authors have proposed a novel approach for classification called Pearson correlation weighted KNN (PCWKNN), which is a modified version of KNN and uses Pearson correlation coefficient values to determine weights in a weighted KNN. The performance of the classifiers was evaluated using the hold-out validation method. SVM, LR, and RF were 96.77% accurate. NB obtained 95.16% accuracy. KNN achieved 91.93% accuracy. PCWKNN outperformed the employed classifiers and obtained an accuracy of 98.39%. Addressing the imperative for improved model generalization, the researchers utilized PCWKNN on an alternative, more extensive lung cancer dataset and subsequently broadened its application to diverse diseases, including the brain stroke dataset. The encouraging outcomes underscore PCWKNN's resilience and adaptability, suggesting its viability for real-world implementation. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Performance Comparison of Object Detection Neural Network Models Based on Accuracy and Latency 2

Performance Comparison of Object Detection Neural Network Mo...

引用

2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Gomathy, B. Sengottaiyan, N. Aarthi, K. Thirumoorthy, P. Tamizharasu, K. Kalyanasundaram, P. Dr.NGP Institute of Technology Dept of Computer Science and Business Systems Tamilnadu Coimbatore India Alliance College of Engineering and Design Alliance University Faculty of Science and Technology Karnataka Anekal562106 India Kongu Engineering College Department of ECE Erode Tamilnadu Perundurai638 060 India Nandha Engineering College Department of CSE Erode Perundurai638 052 India KSR Institute for Engineering and Technology Tiruchengode Department of CSE 637215 India

ISBN: (纸本)9798350327533

Aim: The purpose of this study is to compare the object detection performance of You Only Look Once V4 (YOLOv4) and Single Shot Multibox Detector (SSD) algorithms with respect to metrics like accuracy and latency. Materials and method: Twenty sample photos in all, from different classifications and labels, were gathered. These samples were divided into training dataset (60 %) and test dataset (40 %). To measure the performance, values for accuracy and latency were computed for YOLOv4 and SSD with G power 0.8. Result: The accuracy in prediction of the object in the image was higher in the YOLOv4 algorithm (97 %) compared to the SSD algorithm (84 %). After running a t-test on an independent sample of the two groups under consideration. It is observed that YOLOv4 reported greater preference than the SSD algorithm having p value 0.166 (p>0.05). It was proven that the YOLOv4 reported greater preference than SSD in terms of accuracy. © 2024 IEEE.

关键词： Convolutional neural networks Machine Learning Novel Custom Dataset Object Detection Single Shot Multibox Detector You Only Look Once V4

来源：评论

学校读者我要写书评

暂无评论

Distributed MQTT Brokers Infrastructure with Network Transparent Hardware Broker 11

Distributed MQTT Brokers Infrastructure with Network Transpa...

引用

11th International Symposium on Computing and Networking, CANDAR 2023

作者： Toyohara, Tokimasa Nishi, Hiroaki Keio University Graduate School of Science and Technology 3-14-1 Hiyoshi Kohoku Yokohama Kanagawa223-8522 Japan Keio University Department of System Design Faculty of Science and Technology 3-14-1 Hiyoshi Kohoku Yokohama Kanagawa223-8522 Japan

ISBN: (纸本)9798350306705

In recent years, the number of IoT devices has been rapidly increasing. Therefore, MQ Telemetry Transport (MQTT) has attracted attention as a lightweight protocol for IoT devices. MQTT employs a publish/subscribe model of communication via a broker, and since the performance of the MQTT broker directly affects the quality of service, various studies have been conducted to improve its performance. Among them, the hardware implementation of MQTT broker has higher performance than software implementations in terms of publish throughput and processing delay. However, there are some problems such as inflexibility and resource limitations. Therefore, we propose a distributed MQTT brokers infrastructure using the hardware broker. In this architecture, the software broker on the cloud and the hardware broker at the edge region work in cooperation to achieve low latency processing at the edge region and software flexibility. The hardware broker operates network transparently, so that end devices communicate with the software broker in the cloud and do not need to be aware of the presence of the hardware broker at the edge region. This enables resource and processing load distribution without affecting end devices. We implemented the network transparent hardware broker in a field-programmable gate array (FPGA) and evaluated it. © 2023 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

A Review on Implementation of Wearable Devices in Healthcare

A Review on Implementation of Wearable Devices in Healthcare

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： Saurabh Suman Vishal Kumar Choudhary Utkarsha Pacharaney Abhishek Kumar Dhiraj Kumar Rahul Raushan Department of Computer Science and Design Faculty of Engineering and Technology Wardha Maharashtra India Department of Computer Science and Medical Engineering Faculty of Engineering and Technology Wardha Maharashtra India Department of Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Wardha Maharashtra India

ISBN: (数字)9798350359299

ISBN: (纸本)9798350359305

The capacity to get additional patient data, including clinical, behavioral, and self-monitored data, has enhanced by the expanding usage of wearable technology. Large volumes of previously unobtainable data are now available, providing a chance to create new instruments with sophisticated analysis and decision support systems for application in clinical settings. Additionally, it gives patients additional options by arming them with personalized decision-support resources and information, enabling them to take charge of their own health care while maintaining their sense of autonomy. Especially well-suited for miniaturization and integration into microfluidic devices are biosensors with electrochemical sensors. Applications cover activities in the domains of diagnostics, food and environmental control, and the identification of complete cells, the parts of cells, proteins, and tiny compounds. Microfluidic technologies can be as basic as sample transport tubes or as sophisticated as platforms with extra components for sample preparation and sensing electrode integration. The kind of detection, application, and sample material all influence the microfluidics design. The next issue for the healthcare industry will be how to use newly acquired information in a way that benefits patients, healthcare organizations, and professionals all while reducing costs and workloads. Given the current limitations, the challenge for wearable technology designers is to provide solutions that healthcare practitioners can readily integrate and use.

关键词： Proteins Industries Reviews Instruments Medical services Organizations Sensors

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：