检索结果-内蒙古大学图书馆

Applied Computational Intelligence in Information Systems (ACIIS), International Conference on

作者： Wafiq Zariful Najeebah Az-Zahra Tashim Tiong Hoo Lim Aida Maryam Basri Suriayati Chuprat Seno Adi Putra Pengcheng Liu Hanif Fakhrurroja Electrical and Electronic Engineering Universiti Teknologi Brunei Bandar Seri Begawan Brunei School of Applied Sciences and Mathematics Universiti Teknologi Brunei Bandar Seri Begawan Brunei Razak Faculty of Technology and Informatics Universiti Teknologi Malaysia Johor Bahru Malaysia School of Industrial and System Engineering Telkom Universiti Bandung Indonesia Department of Computer Science University of York York United Kingdom Research Center for Smart Mechatronics National Research and Innovation Agency Telkom University Bandung Indonesia

Deep Learning plays a vital role in various domains, spanning surveillance, agriculture, and healthcare. However, the current landscape lacks comprehensive comparative studies, underscoring the needs to explore various convolutional neural networks (CNNs) for aquaculture industries. This study conducts a comprehensive comparative analysis on state-of-the-art object detection models to identify the most suitable approach for detecting freshwater prawns, specifically in challenging turbid and murky water conditions as there is a lack of comparison studies for underwater images of freshwater prawns. The evaluated models, including YOLOv8, Faster R-CNN (FRCNN), Single Shot Detector (SSD), and EfficientDet, are assessed based on the following metrics namely inference time, accuracy, image cropping size, and model memory footprint. Using a dataset comprising 2976 manually collected images of freshwater prawns, augmented to a total of 7148 images, our results demonstrate that YOLOv8 outperforms its counterparts, achieving an impressive mean Average Precision (mAP) accuracy of 83.71% with an inference time of 32.9 milliseconds. This positions YOLOv8 as a dependable choice for real-time object detection in challenging underwater environments and contributes to addressing the limited research comparing YOLOv8 with other popular object detection algorithms, thereby aiding model selection for similar object detection applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Feedback seeding scheme for wide frequency band with low seeding power 20

Feedback seeding scheme for wide frequency band with low see...

引用

6th International Conference on engineering and MIS, ICEMIS 2020

作者： Shaltami, Farhat M. Alfaitori, Khalid Ateea Alfergani, Asma Ab-Rahman, Mohammed Syuhaimi Electronics and Communiticaon Technology Department College of Electrical and Electronics Technology - Benghazi Benghazi Libya Department of Computer Networks and Communications University of Benghazi Faculty of Information Technology Benghazi Libya Electrical and Electronics Engineering Department University of Benghazi Benghazi Libya Electrical and Electronic Engineering Department Universiti Kebangsaan Malaysia Bangi Selangor Malaysia

ISBN: (纸本)9781450377362

In this paper, We use Feedback seeding scheme FBS to increase the scalability of colorless passive optical networks. FBS is compared with remote seeding scheme. In the Feedback seeding scheme, the OSNR is higher in FBS scheme than in remote seeding scheme between 1525 nm and 1585 nm. The results show the improvement in the BER performance when the feedback seeding scheme is implemented at the wavelengths 1525 nm, 1530 nm, 1580 nm and 1585 nm Remote seeding scheme provides sufficient sensitivity at wavelengths around the center of C band, while FBS works sufficiently at the whole band. These results show that the proposed FBS scheme provides additional 25 nm in the frequency band to be used for upstream channels using the same SOA. © 2020 ACM.

关键词： Passive optical networks

来源：评论

学校读者我要写书评

暂无评论

Towards Lightweight and Efficient Distributed Intrusion Detection Framework

Towards Lightweight and Efficient Distributed Intrusion Dete...

引用

2021 IEEE Global Communications Conference (GLOBECOM)

作者： Shuai Yuan Hongwei Li Rui Zhang Meng Hao Yiran Li Rongxing Lu School of Computer Science and Engineering University of Electronic Science and Technology of China China Chinese Academy of Sciences Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent Technology Chongqing China Faculty of Computer Science University of New Brunswick Canada

ISBN: (纸本)9781728181059

Federated learning (FL), as a promising distributed learning paradigm, has put many efforts into distributed intrusion detection systems (IDS), for defending against various malicious attacks, such as SQL injection and DDoS attacks. Compared with traditional IDS based on centralized deep learning (DL), FL-based solutions require not to share users' raw data while yielding better detection performance. However, state-of-the-art FL-based methods still suffer from two key limitations: 1) insufficient detection performance on non-independent and identically distributed (non-IID) data, and 2) high communication and computational overheads due to the utilization of large-scale neural network models. In this paper, we propose a lightweight collaborative intrusion detection framework, called CoLGBM, the first of its kind in the regime of decentralized IDS, where decision tree and light gradient boosting machine (LGBM) are combined for constructing the detection scheme. The main insight is that through combining user-trained decision trees (each user's decision tree is derived from its own data with unique distribution), our framework can perform effectively on non-IID data while working efficiently for handling enormous samples. Compared with the current FL-based methods, our CoLGBM achieves higher accuracy and lower overhead on both IID and non-IID data. Extensive experiment results demonstrate our scheme with high-level performance.

关键词： Deep learning Distance learning Neural networks Intrusion detection Distributed databases SQL injection Boosting

来源：评论

学校读者我要写书评

暂无评论

Risk Factors of Cervical Cancer using Classification in Data Mining 2

Risk Factors of Cervical Cancer using Classification in Data...

引用

2nd Joint International Conference on Emerging Computing technology and Sports, JICETS 2019

作者： Razali, Nazim Mostafa, Salama A. Mustapha, Aida Wahab, Mohd Helmy Abd Ibrahim, Nurul Atieqah Faculty of Computer Science and Information Technology Universiti Tun Hussein Onn Malaysia Parit Raja Batu Pahat Johor86400 Malaysia Faculty Electrical and Electronic Engineering Universiti Tun Hussein Onn Malaysia Parit Raja Batu Pahat Johor86400 Malaysia

According to World Health Organization, cervical cancer is the fourth most frequent cancer that have high mortality rate which affected women all around the world especially in low and middle-income countries. As the computer science and information technology field growth, researches on analysing medical datasets such as diabetes, cervical cancer and liver disease and etc also growth. This paper is set to studies classification techniques in data mining on risk factor of cervical cancer datasets. The clssification techniques such as Naive Bayes (NB), C4.5 Decision Tree (C4.5), k-Nearest Neighbors (kNN), Sequential Minimal Optimization (SMO), Random Forest Decision Tree (RF), Multilayer Perceptron (MLP) Neural Network and Simple Logistic Regression (SLR) have been used to classify the dataset whether healthy or cancer result for cervical cancer diagnostic. The dataset is needed to be undergoing intense data pre-processing phase due to imbalance and have a lot of missing value. The performance of classification were evaluated using 10-folds cross validation where accuracy, precision and recall as evaluation metric were measured using confusion matrix to determine the performance power for all classification techniques. © 2020 IOP Publishing Ltd. All rights reserved.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

A Data Mining Approach to Prediction of Liver Diseases 2

A Data Mining Approach to Prediction of Liver Diseases

引用

2nd Joint International Conference on Emerging Computing technology and Sports, JICETS 2019

作者： Razali, Nazim Mustapha, Aida Wahab, Mohd Helmy Abd Mostafa, Salama A Rostam, Siti Khadijah Faculty of Computer Science and Information Technology Universiti Tun Hussein Onn Malaysia Parit Raja 86400 Batu Pahat Johor Malaysia Faculty Electrical and Electronic Engineering Universiti Tun Hussein Onn Malaysia Parit Raja 86400 Batu Pahat Johor Malaysia Faculty of Computer Science and Information Technology Universiti Tun Hussein Onn Malaysia Parit Raja 86400 Batu Pahat Johor Malaysia

One of the major diseases in the world is liver disease. The liver is an important part of the large organs in the human body and is also considered a gland. This is because it creates and bites bile. Liver disease is a liver problem that causes the disease. The objective of this study is to propose a rule-based classification model with basic decision making techniques to predict various types of heart disease. To get better results the experiment was done using a different data mining algorithm compared with previous liver disease predictions. All experiments have been implemented at Azure Machine Learning tool. This paper is about to study the prediction of liver disease to produce better performance accuracy by comparing various mining data classification algorithms. © Published under licence by IOP Publishing Ltd.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Cognitive Inspired Sound-Based Automobile Problem Detection: A Step Toward Xai

SSRN

引用

SSRN 2024年

作者： Hamad, Abdulsattar Abdullah Nasim, Muhammad Fawad Jaffar, Arfan Khalaf, Osamah Ibrahim Ouahada, Khmaies Hamam, Habib Akram, Sheeraz Siddique, Abubakar Faculty of Computer Science and Information Technology The Superior University Lahore54000 Pakistan Lahore55150 Pakistan University of Samarra College of Education Department of physics Iraq Lahore 54000 Lahore55150 Pakistan Department of Solar Al-Nahrain Research Center for Renewable Energy Al-Nahrain University Baghdad Jadriya Iraq School of Electrical Engineering Dept. of Electrical and Electronic Eng. Science University of Johannesburg Johannesburg2006 South Africa Faculty of Engineering Uni de Moncton NBE1A3E9 Canada Hodmas University College Somalia Bridges for Academic Excellence Taleh Area Mogadishu Centre-Ville Tunis Tunisia School of Electrical Engineering University of Johannesburg South Africa Riyadh12571 Saudi Arabia Wellington Institute of Technology Te Pukenga Wellington6022 New Zealand

The automobile has become an essential part of modern human life, and one of the critical factors that determine a vehicle’s value is its reliability. Engine breakdowns are not only hazardous but also financially burdensome. Early detection of engine failure can help save costs and improve the average lifespan of a car. Traditionally, manual inspection of engine sounds by expert mechanics has been used as an effective approach for the early detection of engine problems. There have been recent attempts to develop sound detection-based methods for the automatic diagnosis of engine problems. However, the majority of these techniques are neither robust nor explainable. These systems act like black boxes, making their decision-making process difficult to *** Learning Classifier System, also known as LCS, is a machine learning technique that operates on a set of rules. It has shown promise in producing robust, explainable, and generalizable solutions for many problem domains. The objective of this work is to develop a novel LCS-based system for the automatic detection of engine problems. The developed system’s decision-making process is interpretable, which is a step toward eXplainable artificial intelligence. Using time domain, frequency domain, and time-frequency domain features, the innovative system’s generalizability is assessed. While the developed system’s robustness is evaluated using noisy sound data collected under various normal and abnormal conditions, The experimental results indicate that the novel approach outperformed conventional state-ofthe-art techniques by 2.6% − 6.0% and achieved the highest performance accuracy of 98.6%. © 2024, The Authors. All rights reserved.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Efficient Water Evaporation Using Black Silicon

ACS Sustainable Resource Management

引用

ACS Sustainable Resource Management 2025年第2期2卷 316-321页

作者： Yoshiaki Nishijima Hiroyoshi Nishijima Makoto Ohashi Tomas Katkus Saulius Juodkazis Department of Electrical and Computer Engineering Graduate School of Engineering Yokohama National University 79-5 Tokiwadai Hodogaya-ku Yokohama 240-8501 Japan；Precursory Research for Embryonic Science and Technology (PRESTO) Japan Science and Technology Agency (JST) 7 Gobancho Chiyoda-ku Tokyo 102-0076 Japan；Institute of Advanced Sciences Yokohama National University 79-5 Tokiwadai Hodogaya-ku Yokohama 240-8501 Japan；Institute for Multidisciplinary Sciences Yokohama National University 79-5 Tokiwadai Hodogaya-ku Yokohama 240-8501 Japan；Research Institute for Electronic Science (RIES) Hokkaido University North 20 West 10 Kita-ku Sapporo Hokkaido 001-0020 Japan Hokkaido Obihiro South Commercial High School 36-1 West 21 South 5 Obihiroshi Hokkaido 080-2471 Japan Department of Electrical and Computer Engineering Graduate School of Engineering Yokohama National University 79-5 Tokiwadai Hodogaya-ku Yokohama 240-8501 Japan Optical Sciences Centre and ARC Training Centre in Surface Engineering for Advanced Materials School of Science Swinburne University of Technology Hawthorn Victoria 3122 Australia Institute of Advanced Sciences Yokohama National University 79-5 Tokiwadai Hodogaya-ku Yokohama 240-8501 Japan；Optical Sciences Centre Swinburne University of Technology Hawthorn Victoria 3122 Australia；Tokyo Tech World Research Hub Initiative School of Materials and Chemical Technology Tokyo Institute of Technology 2-12-1 Ookayama Meguro-ku Tokyo 152-8550 Japan；Laser Research Center Physics Faculty Vilnius University Vilnius 01513 Lithuania

The black silicon (b-Si)─plasma-etched nanostructured surface of crystalline Si─was used as a light absorber due to its extremely low reflectivity (<1%) at the visible-to-near-IR spectral range. Flat Fresnel lenses of 1.47 and 0.36 m2were used to focus light onto b-Si, which was a photothermal absorber. Experiments to distill water were carried out from October 2021 to April 2022 in Obihiro (42°55′N 143°12′E), Hokkaido, Northern Japan. The same b-Si has biocidal properties (antibactericidal, antiviral, and antifungal) due to mechanical nanoscale needles, which complement the water purification when gray water sources are used in applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Synergistic Enhancement with Mesoporous Silica Colloidal Electrolyte for Lithium-Oxygen Batteries

SSRN

引用

SSRN 2022年

作者： Mu, Hailiang Zhuge, Xiangqun Liu, Tong Ding, Zhengping Ren, Guogang Liu, Terence Xiaoteng Xu, Ben Bin Luo, Zhihong Luo, Kun Changzhou Key Laboratory of Intelligent Manufacturing and Advanced Technology for Power Battery Changzhou University Changzhou213164 China Guangxi Key Laboratory of Optical and Electronic Materials and Devices Guilin University of Technology Guilin541004 China Department of Mechanical and Construction Engineering Faculty of Engineering and Environment Northumbria University Newcastle upon TyneNE1 8ST United Kingdom Department of Engineering and Technology School of Physics Engineering and Computer Science University of Hertfordshire Hatfield Hertfordshire AL10 9AB United Kingdom

Protecting lithium anode and accelerating cathode reaction kinetics are indispensable to developing reliable lithium-oxygen batteries (LOBs). Herein, we demonstrate a mesoporous silica (mSiO 2 ) colloidal electrolyte that synergistically enhances both the anode and cathode processes in LOBs. The cycle life was significantly elongated for 6 ~7 times at different rates of 1 A g -1 , 3 A g -1 and 5 A g -1 , respectively, and the full discharge capacity was also enlarged for 10 times with addition of mSiO 2 in the aprotic electrolyte. Morphological and electrochemical analyses indicate that the large surface area and mesoporous structure of mSiO 2 serve to provide uniform Li + flux at the anode, absorb the superoxide intermediates by oxygen reduction reaction in the electrolyte, and improve the mass transfer in the decomposition of discharge product at the cathode, which resulted in the apparent protection of lithium metal and electrolyte, as well as the improved cyclability of the LOBs. The design principle can be expanded to other porous materials at low cost, and offers a new route toward the development of applicable lithium-air batteries. © 2022, The Authors. All rights reserved.

关键词： Electrolytes

来源：评论

学校读者我要写书评

暂无评论

Dual Functional Mesoporous Silica Colloidal Electrolyte for Lithium-Oxygen Batteries

SSRN

引用

SSRN 2022年

作者： Mu, Hailiang Zhuge, Xiangqun Ren, Guogang Luo, Kun Ding, Zhengping Ren, Yurong Luo, Zhihong Bayati, Maryam Xu, Ben Bin Liu, Xiaoteng Changzhou Key Laboratory of Intelligent Manufacturing and Advanced Technology for Power Battery School of Materials Science ＆ Engineering Changzhou University Changzhou213164 China Department of Engineering and Technology School of Physics Engineering and Computer Science University of Hertfordshire Hertfordshire HatfieldAL10 9AB United Kingdom Guangxi Key Laboratory of Optical and Electronic Materials and Devices Guilin University of Technology Guilin541004 China Department of Mechanical and Construction Engineering Faculty of Engineering and Environment Northumbria University Newcastle upon TyneNE1 8ST United Kingdom

Dual functional mesoporous silica (mSiO2) colloidal electrolytes are designed for lithium-oxygen batteries (LOBs) for the purpose of protecting lithium anode and accelerating cathode reaction kinetics. It suppresses the side reactions of Li stripping/plating and enhances the cycling life performance of the LOB by relieving the attack of superoxide intermediates. The co-deposition of mesoporous mSiO2 and Li2O2 also effectively accelerated the decomposition of the discharge product by promoting the mass transfer at the cathode. Testing results show that the battery life of LOB using mSiO2 with a concentration of 80 mg L-1 in the colloidal electrolyte has been extended from 55 to 328 cycles compared with the one using conventional LiClO4/DMSO electrolyte. The rate performance and full-discharge capacity are also significantly enhanced. We discovered that the as-synthesized mSiO2 has a special well-ordered hexagonal mesoporous structure, with a high specific surface area of 1016.30 m2 g-1, which can form a stable colloid after mixing with 1.0 M LiClO4/DMSO. This is a meaningful investigation of suppressing side reactions using non-aqueous electrolytes, and the design principle also impacts research on other types of lithium metal batteries. © 2022, The Authors. All rights reserved.

关键词： Electrolytes

来源：评论

学校读者我要写书评

暂无评论

Extended Cantor Arrays with Hole-Free Fourth-Order Difference Co-Arrays

Extended Cantor Arrays with Hole-Free Fourth-Order Differenc...

引用

IEEE International Symposium on Circuits and Systems

作者： Zixiang Yang Qing Shen Wei Liu Yonina C. Eldar Wei Cui School of Information and Electronics Beijing Institute of Technology Beijing China Department of Electronic and Electrical Engineering University of Sheffield Sheffield United Kingdom Faculty of Mathematics and Computer Science Weizmann Institute of Science Israel

We present extended Cantor arrays based on fourth-order difference co-arrays (E-FO-Cantor). These arrays result from extending the recently proposed fractal arrays to fourth-order difference co-arrays, and lead to fourth-order difference co-arrays that are hole-free. The set of sensor positions of the E-FO-Cantor is expressed in a simple and recursive form. The proposed Cantor arrays lead to O(N~2 log~(2 3)) ≈ O(N~(3.17)) degrees of freedom compared to O(N~2) that can be achieved by existing sparse arrays with the hole-free property. Compared with other sparse arrays with the hole-free property in their fourth-order co-arrays, the proposed Cantor arrays provide a longer uniform linear array with more virtual sensors, leading to better DOA estimation performance.

关键词： Direction-of-arrival estimation Circuits and systems Estimation Parallel processing Fractals Sensor arrays

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：