检索结果-内蒙古大学图书馆

Automation, Computing and Renewable Systems (ICACRS), International Conference on

作者： Ezekiel Alaric Majaw G. Naveen Sundar D. Narmadha Senthil Kumar Thangavel Venkatesan Adeyemi Abel Ajibesin Department of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore India Department of Computer Science and Engineering Amrita School of Computing Coimbatore India Department of Information Technology Faculty of Informatics and Design Cape Peninsula University of Technology South Africa

ISBN: (数字)9798331532420

ISBN: (纸本)9798331532437

The most common cause of blindness among diabetics is diabetic retinopathy. This disease must be detected in its early stages as delaying treatment can result in permanent blindness. In today’s modern world with the development of technologies, automated techniques have improved the accuracy and efficiency of detecting and classifying this disease. This study suggests a deep learning model utilizing EfficientNetB0 that focuses on designing a neural network structure that requires fewer parameters and computations compared to traditional architectures. Further to help in increasing the accuracy, the image is being processed with methods like CLAHE which is an image processing algorithm that helps in enhancing the contrast while keeping the noise of the images as low as possible. Also, augmentation is being done on the images and SMOTE is applied to handle class imbalance. We collected the APTOS Blindness Detection dataset consisting of retinal fundus images. The accuracy that is being obtained from the proposed methodology is 98.78% indicating the model's effectiveness in detection and classifying between the various stages of diabetic retinopathy.

关键词： Diabetic retinopathy Renewable energy sources Accuracy Computational modeling Blindness computer architecture Transformers Retina Real-time systems Diseases

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of YOLO-Based Deep Learning Models for Real-Time Armour Unit Detection with Image Pre-processing Method

Performance Evaluation of YOLO-Based Deep Learning Models fo...

引用

International Electronics Symposium (IES)

作者： Firmansyah Putra Pratama Alfan Rizaldy Pratama Dewi Mutiara Sari Bayu Sandi Marta R. Haryo Dwito Armono Department of Informatics and Computer Engineering Politeknik Elektronika Negeri Surabaya Surabaya Indonesia Data Science Department Faculty of Computer Science Universitas Pembangunan Nasional Veteran Jawa Timur Surabaya Indonesia Department of Ocean Engineering Faculty of Marine Technology Institut Teknologi Sepuluh Nopember Surabaya Surabaya Indonesia

ISBN: (数字)9798350391992

ISBN: (纸本)9798350392005

Breakwater construction in Indonesia still relies on divers to direct the placement of rock armour units, which is risky and time-constrained. This research aims to replace the diver's task with a deep learning-based vision system using YOLO-based deep learning models. The system utilizes image pre-processing technology by applying histogram equalization (HE) techniques to improve image quality before the detection process. This research evaluates the performance of the YOLO-based deep learning models in detecting armour units in real-time with a focus on various environmental conditions, which are clear and murky water. The analysis reveals clear water consistently supports higher average frame rates (FPS) compared to murky water, maintaining efficient frame processing across all models. In murky water, histogram equalization significantly enhances detection accuracy from 60% to 80% for YOLOv4-tiny and YOLOv7-tiny, demonstrating its effectiveness in challenging conditions. Notably, accuracy remains at 100% for all models in clear water, underscoring their robust performance under optimal visibility conditions.

关键词： Deep learning Performance evaluation Image quality Histograms Analytical models Accuracy Machine vision

来源：评论

学校读者我要写书评

暂无评论

An E-Business Event Stream Mechanism for Improving User Tracing Processes

引用

computers, Materials & Continua 2021年第10期69卷 767-784页

作者： Ayman Mohamed Mostafa Saleh N.Almuayqil Wael Said College of Computers and Information Sciences Jouf UniversitySakaka72314Saudi Arabia Faculty of Computers and Informatics Zagazig UniversityZagazig44519Egypt College of Computer Science and Engineering Taibah UniversityMedina42353Saudi Arabia

With the rapid development in business transactions,especially in recent years,it has become necessary to develop different mechanisms to trace business user records in web server log in an efficient *** business transactions have increased,especially when the user or customer cannot obtain the required *** example,with the spread of the epidemic Coronavirus(COVID-19)throughout the world,there is a dire need to rely more on online business *** order to improve the efficiency and performance of E-business structure,a web server log must be well utilized to have the ability to trace and record infinite user *** paper proposes an event stream mechanism based on formula patterns to enhance business processes and record all user activities in a structured log *** user activity is recorded with a set of tracing parameters that can predict the behavior of the user in business *** experimental results are conducted by applying clustering-based classification algorithms on two different datasets;namely,Online Shoppers Purchasing Intention and Instacart Market Basket *** clustering process is used to group related objects into the same cluster,then the classification process measures the predicted classes of clustered *** experimental results record provable accuracy in predicting user preferences on both datasets.

关键词： Business transactions event stream log file tracing parameters clustering-based classification

来源：评论

学校读者我要写书评

暂无评论

Prediction of Heat Energy Release Rate for Ammonia Combustion in a Constant Volume Combustion Chamber: A Machine Learning Approach 15

Prediction of Heat Energy Release Rate for Ammonia Combustio...

引用

15th International Conference on Electronics, computers and Artificial Intelligence, ECAI 2023

作者： Fang, Lijia Singh, Hardeep Ichiyanagi, Mitsuhisa Suzuki, Takashi Raboaca, Maria Simona Filote, Constantin Verma, Chaman Sophia University Department of Engineering and Applied Sciences Tokyo Japan University of Windsor Turbulence and Energy Laboratory Windsor Canada Institute for Cryogenics and Isotopic Technologies Icsi Energy Department National Research and Development Ramnicu Valcea Romania Stefan Cel Mare University of Suceava Faculty of Electrical Engineering and Computer Science Suceava Romania Eötvös Loránd University Faculty of Informatics Budapest Hungary

ISBN: (纸本)9798350321388

Addressing global warming requires immediate and concerted action. Transitioning to non-conventional energy sources, such as solar and Aeolian power, reducing emissions from transportation and industry, and implementing sustainable land-use practices are crucial steps. Therefore, Ammonia attracts researchers when used as a fuel, and offers several potential benefits such as higher energy density. However, due to poor combustion speed of Ammonia offers slower energy release. To enhance the average flame velocity of Ammonia, the current investigation employed the exhaust gas expelled from the secondary chamber to compress the mixture within the primary chamber and facilitate its HCCI combustion. The main goal of research is the optimization on air-fuel ER to contribute to the development of more efficient and sustainable constant volume combustion. However, the time required for constructing physical prototypes and conducting experiments can be considerable, thus, to mitigate these challenges, the authors turned to machine learning tools as an alternative approach. In the proposed research, results were evaluated through Support Vector Regression. However, due to poor prediction accuracy, authors tried KNeighborsRegressor model for predicting and validating the results. Finally, it is revealed from the KNN model that data sets are highly accurate. © 2023 IEEE.

关键词： Ammonia

来源：评论

学校读者我要写书评

暂无评论

Decision Support System in Determining the Achievement of Widyaiswara Value Using WASPAS and TOPSIS Algorithm 1

Decision Support System in Determining the Achievement of Wi...

引用

1st International Conference on Technology Innovation and Its Applications, ICTIIA 2022

作者： Pratama, Yudhistira Adhitya Iswara, Bagus Ajie Nababan, Adli Abdillah Information System Studies Program Pelita Harapan University Medan Campus Faculty Of Computer Science Medan Indonesia Master's Study Program Informatics Engineering Universitas Sumatera Utara Faculty Of Computer Science And Information Technology Medan Indonesia Digital Business Study Program Stmik Pelita Nusantara Medan Indonesia

ISBN: (数字)9781665488266

ISBN: (纸本)9781665488266

Widyaiswara is required to show the best performance to fulfill his duties and obligations. Therefore, it is very important to measure the performance of the Widyaiswara, so that it can be used as evaluation material by the BPSDM PROVSU. However, the assessment process that occurs is still not precise and time-consuming. Therefore, to minimize this, a decision support system is needed that can minimize time errors and data processing in decision-making so that the assessment runs well and accurately. This system was built by applying the WASPAS method and the TOPSIS method. Based on the results of tests carried out five times, the results of the WASPAS method processing time resulted in an average processing time of 0.00029791 ms and an average memory usage value of 2.836.44 kb, while the results of the TOPSIS method processing time test resulted in an average processing time - an average of 0.000296428 ms and an average memory usage value of 2.862.34 kb. © 2022 IEEE.

关键词： Decision support systems

来源：评论

学校读者我要写书评

暂无评论

Implementation Analysis of KEBI Application on Non-Standard Words Detection in Student Essay Tasks on Language Variety 7

Implementation Analysis of KEBI Application on Non-Standard ...

引用

7th IEEE Information Technology International Seminar, ITIS 2021

作者： Sa'diyah, Ilmatus Fahrudin, Tresna Maulana Latinah Illah, Ibnu Zahy Atha Lima, Cagiva Chaedar Bey Acarya, Burhan Syarif Universitas Pembangunan Nasional 'Veteran' Jawa Timur Faculty of Computer Science Department of Data Science Surabaya Indonesia Universitas Narotama Faculty of Computer Science Department of Informatics Engineering Surabaya Indonesia

ISBN: (纸本)9781665408073

Non-standard word errors in writing sometimes escape the attention of writers or editors due to several factors, including unintentional or limited time in editing. Non-standard word is one of the Indonesian spelling error. Therefore, the application for detecting non-standard words in writing, KEBI, was created to minimize the height of non-standard words in writing. In this study, KEBI was analyzed in terms of application implementation to five various language essay documents as student assignments for Indonesian language courses. There are three things that are analyzed, namely the interface page, processing time, and the level of accuracy of detection and correction using the precision and recall method (confusion matrix). The overall research method includes literature study, data collection, testing, measurement of display, time, and accuracy. Based on the results of the analysis, the interface page display shows good quality. The processing time required by KEBI to detect non-standard words is in the range of 0.02-0.06 seconds. Meanwhile, KEBI's non-standard word detection accuracy rate is 86%, while KEBI's non-standard word correction accuracy rate is 90%. © 2021 IEEE.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection System Model Based on Gated Recurrent Unit to Detect Anomaly Traffic 4

Intrusion Detection System Model Based on Gated Recurrent Un...

引用

4th International Conference on Information and Communications Technology, ICOIACT 2021

作者： Alsyaibani, Omar Muhammad Altoumi Utami, Ema Hartanto, Anggit Dwi Magister of Informatics Engineering Universitas Amikom Yogyakarta Yogyakarta Indonesia Faculty of Computer Science Universitas Amikom Yogyakarta Yogyakarta Indonesia

ISBN: (纸本)9781665433945

In this study, we proposed the Gated Recurrent Unit method to develop an Intrusion Detection System to detect traffic anomalies. This model was trained in several scenarios to get the best model. Scenario variations were carried out on the learning rate, the activation function and the optimization function. We used the CIC IDS 2017 dataset because it has the latest types of attacks. The dataset was divided into 3 parts, namely training, validation and a test with a ratio of 60%, 20% and 20% respectively. The model was compiled with a binary cross-entropy loss function. Measurement of the results was done using metric accuracy and F1 Score. The experimental result shows that the model with the highest accuracy is obtained from a model that used a learning rate of 0.0001, the LRelu activation function and the Adam optimization function with accuracy and the F1 score reaching 97.7739% and 97.7979% respectively. These results exceed the accuracy of previous studies on the same dataset and the same case classification. On the other hand, it can be concluded also from the study results that the models compiled using the Adam optimized have higher accuracy than the models compiled using Stochastic Gradient Descent. Our studies have not been able to figure out what types of attacks that the model detects. Therefore, we suggest conducting a further study of the multiclass classification case. In addition, further studies are also needed to increase the speed of the model in studying data so that it can be applied in real time to a production environment. © 2021 IEEE

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Recommender System Algorithm's Quality Through the Utilization of Affinity Analysis

Enhancing the Recommender System Algorithm's Quality Through...

引用

International Conference on Actual Problems of Electronic Instrument engineering (APEIE)

作者： Igor M. Stubarev Olga K. Alsova Alexander A. Yakimenko Faculty of Automation and Computer Engineering FB Consult Novosibirsk State Technical University Novosibirsk Russia Faculty of Automation and Computer Engineering Novosibirsk State Technical University Novosibirsk Russia Faculty of Automation and Computer Engineering Institute of Computational Mathematics and Mathematical Geophysics SB RAS Laboratory of Geophysical Informatics Novosibirsk State Technical University Novosibirsk Russia

The demand for auxiliary systems that utilize methods and technologies of intellectual data analysis and machine learning is increasing in the CRM system development field. These systems are capable of generating valuable insights from vast amounts of data collected in CRM. The article shows the results of the development and study of the CRM system using the methods of affinity analysis. Earlier, the authors developed and implemented the base version of the recommender algorithm based on the use of cluster data analysis and collaborative filtration [1],[2]. The new version of the algorithm additionally uses affinity analysis methods to form recommendations for the selection of products, which made it possible to increase the accuracy of the recommendation system (service) by metrics F2 on average from 67.98% to 81.24% with an increase in the time for issuing recommendations (On average by 2.47 ms). The study and comparison of the basic and modified versions of the algorithm were executed using data sourced from insurance companies, furnished by "FB Consult".

关键词：

来源：评论

学校读者我要写书评

暂无评论

IPFS: An Off-Chain Storage Solution for Blockchain 5th

IPFS: An Off-Chain Storage Solution for Blockchain

引用

5th International Conference on Recent Innovations in Computing, ICRIC 2022

作者： Kaur, Manpreet Gupta, Shikha Kumar, Deepak Raboaca, Maria Simona Goyal, S.B. Verma, Chaman Department of Computer Science and Engineering Chandigarh University Mohali India Department of Computer Science and Engineering Guru Nanak Dev Engineering College Ludhiana India Apex Institute of Technology Chandigarh University Mohali India National Research and Development Institute for Cryogenic and Isotopic Technologies-ICSI Râmnicu Vâlcea Romania Faculty of Information Technology City University London Malaysia Department of Media and Educational Informatics Eötvös Loránd University Budapest Hungary

ISBN: (纸本)9789811998751

Due to intrinsic properties such as transparency, immutability, decentralization, and cryptographic security, blockchain has emerged as a revolutionary technology. Despite its widespread application, blockchain is not used to store huge data due to the restricted storage capacity offered by each block. Furthermore, because the data contained in a block must be duplicated on many other nodes on the network, storage space is wasted. Off-chain storage is therefore required to store significant volumes of data while preserving the efficiency and performance of the network. Additionally, off-chain solutions such as Inter-Planetary File System (IPFS) would reduce the cost requirements of blockchain nodes as data stored and processed by these nodes would be reduced. Hence, strong decentralized storage is provided by IPFS that is a P2P-based content-addressed file sharing system that uses cryptographic hashes to store data. As a result, by combining blockchain with IPFS, an efficient file sharing system would be created. This paper presents a comprehensive IPFS architecture, a simplified version of this integrated approach, and potential applications that might assist to maximize the worth of both systems. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Adaptation of AI-Accelerated CFD Simulations to the IPU Platform 1

引用

14th International Conference on Parallel Processing and Applied Mathematics, PPAM 2022

作者： Rościszewski, Pawel Krzywaniak, Adam Iserte, Sergio Rojek, Krzysztof Gepner, Pawel Graphcore Gdańsk Poland Department of Construction and Mechanical Engineering Universitat Jaume I Castellón de la Plana Spain Barcelona Supercomputing Center Barcelona Spain Institute of Computer and Information Sciences Czȩstochowa University of Technology Czȩstochowa Poland Faculty of Mechanical and Industrial Engineering Warsaw University of Technology Warszawa Poland Department of Computer Architecture Faculty of Electronics Telecommunications and Informatics Gdańsk University of Technology Narutowicza 11/12 Gdańsk80-233 Poland

ISBN: (数字)9783031304453

ISBN: (纸本)9783031304446

Intelligence Processing Units (IPU) have proven useful for many AI applications. In this paper, we evaluate them within the emerging field of AI for simulation, where traditional numerical simulations are supported by artificial intelligence approaches. We focus specifically on a program for training machine learning models supporting a computational fluid dynamics application. We use custom TensorFlow provided by the Poplar SDK to adapt the program for the IPU-POD16 platform and investigate its ease of use and performance scalability. Training a model on data from OpenFOAM simulations allows us to get accurate simulation state predictions in test time. We show how to utilize the popdist library to overcome a performance bottleneck in feeding training data to the IPU on the host side, achieving up to 34% speedup. Due to communication overheads, using data parallelism to utilize two IPUs instead of one does not improve the throughput. However, once the intra-IPU costs have been paid, the hardware capabilities for inter-IPU communication allow for good scalability. Increasing the number of IPUs from 2 to 16 improves the throughput from 560.8 to 2805.8 samples/s. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Machine learning

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：