检索结果-内蒙古大学图书馆

Regression based prediction of higher heating value for refuse-derived fuel using convolutional neural networks predicted elemental data and spectrographic measurements

引用

Waste Disposal and Sustainable Energy 2024年第3期6卷 429-437页

作者： Baki Osman Bekgoz Zerrin Günkaya Kemal Ozkan Metin Ozkan Aysun Ozkan Müfide Banar Department of Computer Engineering Meselik CampusEskisehir Osmangazi University26480EskisehirTürkiye Department of Environmental Engineering Iki Eylul CampusEskisehir Technical University26555EskisehirTürkiye Center of Intelligent Systems Applications Research Meselik CampusEskisehir Osmangazi University26480EskisehirTürkiye

Higher heating value(HHV)is the key parameter for replacing Refuse-Derived Fuel(RDF)with fossil fuels in the cement *** can be measured with a bomb calorimeter or predicted from direct elemental data by using regression *** methods require the continuous use of special laboratory equipment and are time *** overcome these limitations,this study aims to predict the HHV value of RDF from predicted elemental data by using regression ***,once the predicted elemental data are generated,there will be no need to have continuous elemental data to predict *** elemental data were generated from direct elemental data and Near Infrared(NIR)camera-based spectrometric data by using a deep learning model.A convolutional neural networks(CNN)model was used for deep learning and was trained with 10,500 NIR image samples,each of which was 28×28×*** regression models(Linear,Tree,Support-Vector Machine,Ensemble and Gaussian process)were applied for HHV *** to these results,higher R2 values(>0.85)were obtained with Gaussian process models(except for the Rational Quadratic model)for the predicted elemental *** the Gaussian models,the highest R2(0.95)but the lowest Root Mean Square Error(RMSE)(0.0563),Mean Squared Error(MSE)(0.0317)and Mean Absolute Error(MAE)(0.0431)were obtained with the Mattern 5/2 *** results of predictions from predicted elemental data were compared to predictions from direct elemental *** results show that the regression from predicted elemental data has an adequate prediction(R2=0.95)compared to the prediction from the direct elemental data(R^(2)=0.99).

关键词： Deep learning Higher heating value Refuse-derived fuel Regression Spectrographic measurement

来源：评论

学校读者我要写书评

暂无评论

Development of a Mobile Monitoring Application for a Message Queuing Telemetry Transport (MQTT)-Based Struvite Fertilizer Production System 10

Development of a Mobile Monitoring Application for a Message...

引用

10th International HCI and UX Conference in Indonesia, CHIuXiD 2024

作者： Maulana, Ilham Fitria, Maya Faizah, Cut Nurul Adharani, Daffa Hirta Jinan, Sarah Nada Dawood, Rahmad Universitas Syiah Kuala Department of Electrical and Computer Engineering Banda Aceh23111 Indonesia Universitas Syiah Kuala Interactive Intelligent Systems Reseach Group Department of Electrical and Computer Engineering Banda Aceh23111 Indonesia

ISBN: (纸本)9798350380439

Struvite fertilizer, characterized by its slow-release qualities, is comprised of magnesium, ammonium, and phosphate and is vital for plant growth. The Integrated Laboratory Unit of Universitas Syiah Kuala (USK) has developed a prototype for struvite fertilizer production equipment, but the production process requires manual monitoring. This project seeks to create an MQTT (Message Queuing Telemetry Transport)-based mobile application for the real-time monitoring and control of struvite fertilizer production equipment. The application employs the MQTT communication protocol, known for its quick data transmission and minimal bandwidth requirements. This application incorporates sensors on the production machine, which includes a reactor, filter, and dryer, and employs an Amazon Web Service's (AWS) IoT Core as the MQTT broker. Findings from the application's evaluation indicate that the mobile application can efficiently monitor and control several machine components. Data transmission to MQTT topics was successful, facilitating seamless communication. Functional and integration testing demonstrated that the system operates effectively. Usability testing outcomes yielded an average score of 77.75 with a system usability scale (SUS) approach, signifying that the application possesses a satisfactory degree of usability classified within the 'Grade B' category. © 2024 IEEE.

关键词： Telemetering systems

来源：评论

学校读者我要写书评

暂无评论

Explainability Spectrum Analysis of Weather Sequences in Short-Term Load Forecasting 14th

Explainability Spectrum Analysis of Weather Sequences in Sho...

引用

14th International Conference on Information, Intelligence, systems, and Applications, IISA 2023

作者： Kontogiannis, Dimitrios Bargiotas, Dimitrios Daskalopulu, Aspassia Tsoukalas, Lefteri H. Department of Electrical and Computer Engineering University of Thessaly Volos Greece Center for Intelligent Energy Systems Purdue University West Lafayette United States

ISBN: (纸本)9783031674259

Short-term load forecasting tasks utilize a plethora of weather sequences in order to study meaningful features that describe complex relationships between environmental parameters and the variable of load, as well as the occurrence of impactful events, thus reinforcing the predictive power of estimators. It is evident that the inclusion of those additional features increases the input dimensions and decreases the overall explainability of forecasting models, since not all of the extracted features are equally compatible with the assumptions of the regressors, resulting in models where the justification of predictive potency, the connection between the variance of the target variable and the variance of predictors, as well as the explanation of the computational flow become increasingly difficult due to ambiguity. Therefore, this analysis investigates the representativeness of weather variables and examines the explainability of interpretable short-term load forecasting structures that utilize environmental sequences towards the selection of important feature subsets that maximize the explained variance of load time series as well as the seasonal, trend and residual load components during training. This methodology considers linear regression and prominent tree-based estimators coupled with model-dependent feature importance frameworks utilizing game theoretic, permutative and impurity-based approaches for the derivation of optimal feature sets and feature set combinations in terms of explained variance scores. Additionally, two structural approaches of explainable feature set generation from the joint feature importance scores through the utilization of hierarchical and majority inclusion are compared, their execution behavior towards explainability maximization is examined, and the main observations from each stage of this analysis are discussed. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Weather forecasting

来源：评论

学校读者我要写书评

暂无评论

Fractal Measurement of Images Human Brain from MRI

Fractal Measurement of Images Human Brain from MRI

引用

2024 Cognitive Models and Artificial Intelligence Conference, AICCONF 2024

作者： Anarova, Shahzoda Jabbarov, Jamoliddin Uralova, Iroda Tashkent University of Information Technologies Department of Convergence of digital technologies Computer Engineering Faculty Tashkent Uzbekistan Department of Computer science and technology Intelligent systems and computer technologies Faculty Samarkand State University Samarkand Uzbekistan

ISBN: (纸本)9798400716928

This article is devoted to the determination of the fractal size of the damaged part of the human brain on the basis of images obtained from MRI (magnetic resonance imaging). There are various mathematical methods for determining the size of fractal structures, this article uses two variants of the cell counting method and describes the analysis of errors in determining the fractal size of the damaged part of the human brain. The article shows that the damaged part of the human brain has a fractal structure and that it has a fractal dimension. Fractal measurement has also been used to determine the size of the damaged part of the human brain, unlike common methods. In determining the fractal scale, cases of changes in human body organs were not taken into account. In the article, the determination of the size of the damaged part of the human brain is studied on the basis of mathematical formulas. Two different variants of the special cell counting method were used to calculate the fractal measurements, as well as the corresponding number of experimental results. In addition, these measurements were used to assess the extent to which patients suffered brain damage and to provide information on the practical application of these fractal measurements. © 2024 ACM.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

EEG Signal-Based Autism Spectrum Disorder Detection Through Normalized Mutual Information and Convolutional Neural Network 2nd

EEG Signal-Based Autism Spectrum Disorder Detection Through ...

引用

2nd International Conference on Big Data, IoT and Machine Learning, BIM 2023

作者： Peya, Zahrul Jannat Maria, Mahfuza Akter Akhand, M.A.H. Siddique, Nazmul Department of Computer Science and Engineering Khulna University of Engineering and Technology Khulna9203 Bangladesh School of Computing Engineering and Intelligent Systems Ulster University Northern Ireland Londonderry United Kingdom

ISBN: (纸本)9789819989362

Autism Spectrum Disorder (ASD) is a diverse neurological problem with several contributing factors involving both genetic and environmental variables. The diagnosis of ASD based on neural activity analysis of various signals from the brain, especially electroencephalography (EEG), has drawn attention. A technique for capturing an electrogram of the brain's spontaneous electrical activity is called EEG which is simple to use and non-intrusive. The aim of this study is to classify people with ASD and controls using the most efficient band by examining different sub-bands (such as alpha, beta, and gamma) of the EEG data. Normalized Mutual Information (NMI) is used to create Connectivity Feature Maps (CFMs). Classification is performed through Convolutional Neural Network (CNN). Gamma band is found effective for ASD detection with an accuracy of 96%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Directed Machine Learning Approaches for Determining Alzheimer Disease 3

Directed Machine Learning Approaches for Determining Alzheim...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Vashist, Ansh Jain, Tarun Sharma, Vijay Shankar Manipal University Jaipur Department of Computer Science and Engineering India Manipal University Jaipur Department of Iot & Intelligent Systems India

ISBN: (纸本)9798350319125

Alzheimer's is a neurogenic disease which progress into neurological disorder that primarily affects cognitive function and memory. It's a Neurodegenerative (ND) disease, characterized by the gradual deterioration of cognitive function, memory, thinking, and behaviour. There are two most common diseases among neurodegenerative diseases: (a) Alzheimer's Disease and (b) Parkinson's Disease. We used 12 classifiers on the given dataset on UC Irvine Machine Learning Repository. The machine learning algorithms were engaged to identify Alzheimer Disease. Our research results showed that the XGB Model is the one that shows the best accuracy, of 100%, of all the 12 classifiers. © 2023 IEEE.

关键词： AdaBoost Model Alzheimer's ANN Model Binary Decision Tree Model Classification Complement Naive Baye Model Disease Detection Ensemble Voting Model Gaussian Naive Baye Model Logistic Regression Machine Learning Multinomial Naive Baye Model Random Forest SGD Model XG Boost Model

来源：评论

学校读者我要写书评

暂无评论

Analysis of Life Expectancy Rate Post Lung Surgery Using Machine Learning 3

Analysis of Life Expectancy Rate Post Lung Surgery Using Mac...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Shreya Jain, Tarun Sharma, Vijay Shankar Manipal University Jaipur Department of Computer Science and Engineering India Manipal University Jaipur Department of Iot & Intelligent Systems India

ISBN: (纸本)9798350319125

It has become really important for patients to know the precise results that can happen post the treatment of lung cancer or that if they have any underlying health problem which can be the cause of death post lung cancer surgery. Doctors also need to know the full detailed report of patients' health with the risk factors that can affect their survival rate for better treatment of their patients. As such results are crucial, we need to implement such techniques which can generate the most accurate results. For such accurate analysis, we use machine learning techniques to generate better results. Several machine learning and deep learning approaches are being used to estimate the survival rate of lung cancer patients post the surgery. Examination of various health factors is used for prediction, as health factors could be significant predictors. Seven machine learning techniques that are linear regression, XGBooster, random forests, Decision Tree, KNN, SVM, voting classifier and two deep learning techniques that are ANN and BILSTM are used for analyzing performance. Analysis of accuracy has been done using F1 score, precision, and recall as measuring factors. For the analysis of outcome prediction, we have taken accuracy. © 2023 IEEE.

关键词： ANN Decision Tree Machine learning Random Forest Thoracic Surgery

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Mesothelioma: Early Detection and Treatment 3

Machine Learning for Mesothelioma: Early Detection and Treat...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Garg, Bhavika Jain, Tarun Sharma, Vijay Shankar Manipal University Jaipur Department of Computer Science and Engineering India Manipal University Jaipur Department of Iot & Intelligent Systems India

ISBN: (纸本)9798350319125

Mesothelioma is an extremely severe cancer that can easily transform into lung cancer. Mesothelioma diagnosis takes several months and treatment, including surgery, is expensive. Given the risk, early detection of Mesothelioma is essential for patient health, as it is connected to asbestos exposure. Various machine learning algorithms has been used in this research paper to compare with accurate results for mesothelioma detection. Support Vector Machine (SVM), Random Forest (RF), Decision Tree (DT), k Nearest Neighbourhood (k-NN), and Linear Regression (LR) are some of the machine learning methods being used. For this research paper, dataset is available on UCI, called the University of California Irvine [1]. The test dataset contains 264 instances, 35 characteristics and 8 performance measures, which is used to evaluate the classifiers accuracy. The average accuracy of XGB, RF, DT, SGD, LR and Voting Classifier are 100% each. Combing all the classifiers, helps us to break through the Mesothelioma data and the creation of data driven insights to improve patient care. © 2023 IEEE.

关键词： Asbestos Exposure DT Machine Learning Machine Learning Algorithms-SVM Mesothelioma

来源：评论

学校读者我要写书评

暂无评论

Ovarian Cancer Prediction using Machine Learning 3

Ovarian Cancer Prediction using Machine Learning

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Agnihotri, Yashika Jain, Tarun Sharma, Vijay Shankar Manipal University Jaipur Department of Computer Science and Engineering India Manipal University Jaipur Department of Iot & Intelligent Systems India

ISBN: (纸本)9798350319125

Ovarian cancer is the type of cancer that has the highest recurrence rate in women and poses a serious threat to women. Due to the lack of observable signs, this quiet invader often goes undetected in the beginning, leaving women susceptible to its sneaky development. Once it has advanced and its symptoms are obvious, it becomes arduous to treat. Machine learning is emerging as a ray of hope in the healthcare scene in the current era of rapid technological innovation. Machine learning provides a promising path for the early diagnosis and prediction of ovarian cancer by harnessing the power of algorithms and data analytics, perhaps turning the tide against this tough enemy. The dataset [17] comprises of 349 instances and 49 features. The goal here is to derive a model that helps in classification of instances into two classes: Benign Ovarian Tumors (BOT) and Ovarian Cancer (OC). Therefore, methodical machine learning algorithms are employed to detect ovarian cancer. Our research findings revealed that out of all the classifiers, the Random Forest Model has the highest accuracy (91.43 %). This approach is capable of accurately classifying BOT and OC and could have immense effect on diagnosis of patients, leading to better treatments and higher survival rate. © 2023 IEEE.

关键词： Classification Decision Tree Model KNN Logistic Regression Model Random Forest Model SGD Model and Voting Classifier Model SVM Model Used - Machine Learning XGB Model

来源：评论

学校读者我要写书评

暂无评论

Modeling and Simulating more efficient and reliable fuel cell vehicles through enhancing the integration of the 6kW PEM fuel cell stack with DC/DC boost converter and BLDC motor 33

Modeling and Simulating more efficient and reliable fuel cel...

引用

33rd Southern African Universities Power engineering Conference, SAUPEC 2025

作者： Mtumka, Olona Krishnamurthy, Senthil Cape Peninsula University of Technology Bellville Center for Intelligent Systems and Emerging Technologies Department of Electrical Electronic and Computer Engineering Cape Town7530 South Africa

ISBN: (纸本)9798331535162

This study focuses on enhancing the integration of the PEM fuel cell, DC/DC boost converter, and BLDC motor, which help to develop more efficient and dependable fuel cell vehicles. The development of renewable energy sources for power generation has received much attention due to the depletion of fossil fuel supplies worldwide and economic difficulties. Fuel cells are one of the most efficient and cleanest power generation methods. Polymer electrolyte membrane (PEM) fuel cell is the preferred type of fuel cell for vehicles because of its high energy density, fast start-up, and lack of pollution. This paper aims to model and simulate a PEM fuel cell stack to power a Brushless DC (BLDC) motor for a fuel cell vehicle to reduce emissions in the transportation sectors. A boost converter is implemented to boost the output voltage of the PEM fuel cell stack to 100 V. The paper utilizes the trapezoidal commutation of the BLDC motor to drive the inverter. The trapezoidal commutation uses the six-switching technique to control the inverter's phase currents. The variation of fuel flow rate and drive cycle are included to observe the effect on the operation of the fuel cell stack. The paper presents the modeling and simulation of the PEM Fuel cell stack to improve power conversion, energy management, and vehicle control, helping to make fuel cell vehicles more viable for widespread adoption in the future. © 2025 IEEE.

关键词： Brushless DC motors

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：