The paper introduces briefly some of the key structures of the computer games system in *** it mainly provides a further optimization for the current existing computer games system in *** machine learning algorithm ca...
详细信息
ISBN:
(纸本)9781467397155
The paper introduces briefly some of the key structures of the computer games system in *** it mainly provides a further optimization for the current existing computer games system in *** machine learning algorithm can increase the adaptive width adjustment in the MTD（f） algorithm and the self-learning method by TDP algorithm in the evaluation function which could strengthen the "thinking" ability on the computer games system in *** advanced and modified algorithm is proved to be practical and applicative by experimentations and tests of computer games system in connect6 provided in this paper.
Building height information is essential for determining urban morphology, urban planning studies, and manage sustainable growth. This study aims to use machine learning algorithms to estimate building heights from ai...
详细信息
Building height information is essential for determining urban morphology, urban planning studies, and manage sustainable growth. This study aims to use machine learning algorithms to estimate building heights from airborne LiDAR and spaceborne ICESat-2/ATLAS data. The performance of different machine learning algorithms was investigated when analyzing ICESat-2/ATLAS and airborne LiDAR data. The accuracy of building height information was compared with field measurements. machine learning algorithms such as K-Nearest Neighbors (K-NN), Random Forest (RF), Support Vector machines (SVM), Artificial Neural Networks (ANNs), and Random Sample and Consensus (RANSAC) were used to classify spaceborne and airborne LiDAR data. Among all the algorithms applied to ICESat-2/ATLAS, the RF algorithm provided the best results for the strong and weak beams with 0.9683 and 0.9614, respectively. The K-NN yielded the best result for the airborne LiDAR dataset with 0.9999. Statistical analyzes were applied to both LiDAR datasets. The results of statistical analyzes for the pair of field measurement and ICESat-2 were R2 = 0.9894, RMSE = 0.4131, MSE = 0.1706, MAE = 0.3184, and ME = 0.0003;for the pair of field measurement and airborne LiDAR: R2 = 0.8368, RMSE = 1.9646, MSE = 3.8597, MAE = 1.0586, and ME = -0.3450;and for the pair of airborne LiDAR and ICESat-2: R2 = 0.8275, RMSE = 1.6664, MSE = 2.7770, MAE = 0.9040, and ME = 0.4598. As a result of the analysis, it was seen that the data obtained from the ICESat-2 system was successful in estimating building height and provided reliable data.
In this modern world, data mining technology holds an essential position in all the major Engineering fields. Handling of Unstructured Big Data is an essential task of this era. At present, making the maximum advantag...
详细信息
ISBN:
(纸本)9781479970759
In this modern world, data mining technology holds an essential position in all the major Engineering fields. Handling of Unstructured Big Data is an essential task of this era. At present, making the maximum advantage of parallel processing know-hows and the task of rapid examination of huge data steadily and continuously transmitted or received from various sources is becoming popular or conventional. The big data analytics job is fragmented into smaller jobs and ran over tens, hundreds or thousands of product servers by the parallel processing architecture. This helps in maintaining the data center cost efficient and facilitates easy handling of the enormous work in an efficient way. In this paper, proposed solution takes online consumer purchase. The online system has unrivalled bank of data on online consumer purchasing behavior that can be mined from its 100 million customers accounts. They use customer click -stream data and historical purchase data of all those 100 million customers and each user is shown personalized results on customized web pages. For improving Big Data performance the machinelearning Method i.e. K -Nearest Neighbour algorithm used to support to take good analysis. Hadoop simulator is used to solve this kind of task.
Mortar is subjected to high temperatures during fire attacks or when it is near heat-radiating equipment like furnaces and reactors. The physical and microstructure of mortar were considerably altered by high temperat...
详细信息
Mortar is subjected to high temperatures during fire attacks or when it is near heat-radiating equipment like furnaces and reactors. The physical and microstructure of mortar were considerably altered by high temperatures. In this investigation, the effects of elevated temperatures on the flexural and compressive strengths of wood ash (WA) cement mortar modified with green-synthesised Nano titanium oxide (NT) were examined. In order to produce mortar samples, the cement was replaced with 10% WA, and 1-3% NT by weight of binder were added at constant water-binder ratio. The specimens were heated to 105, 200, 400, 600, and 800? with an incremental rate of 10 ? per min in the electric furnace for a sustained period of 2 h to measure their strengths. The machine learning algorithm of artificial neural networks with Levenberg-Marquardt backpropagation training techniques of different network architectures was engaged to predict the compressive strength of WAcement-NT-based mortar produced. The findings showed that higher temperatures reduced compressive strength after 400 ? and flexural strength after 200 ?. The mortar specimen with a 3% NT addition showed the highest residual compressive strength increase, ranging from 18.75 to 27.38%. Compared to compressive strength, flexural strength is more severely affected by high temperatures. The backpropagation training algorithm revealed that each hidden layer displayed its unique strong prediction. However, Levenberg-Marquardt backpropagation training technique of 7-10-10-1 network structures yielded the best performance metrics for training, validation, and testing compared to 7-10-10-10 and 7-10-1 network architectures.
With the rapid development of modern logistics industry, traditional monitoring methods are limited by environmental factors and equipment costs, thermal radiation image monitoring can provide more accurate and realti...
详细信息
With the rapid development of modern logistics industry, traditional monitoring methods are limited by environmental factors and equipment costs, thermal radiation image monitoring can provide more accurate and realtime monitoring data, the advantages are more obvious. A set of thermal radiation image monitoring system based on machine learning algorithm is developed to simulate the real-time monitoring and management of logistics economy services. In this paper, the real-time image data in the logistics process is collected by thermal radiation imaging equipment, and the collected thermal radiation images are preprocessed. The key features in the thermal radiation images are extracted by machine learning algorithm, and the classifier and detector models are constructed and trained. The trained model is integrated into a monitoring system, and a complete thermal radiation image monitoring solution is developed. The performance of the monitoring system is tested in a simulated logistics environment, and its effect in practical applications is evaluated. The results show that the system can accurately identify and track the key events in the logistics process, and meet the needs of real-time logistics monitoring. This technology can not only provide high-precision real-time monitoring data, but also effectively reduce the operating costs of logistics enterprises and improve logistics efficiency.
machine learning algorithm and web-based application systems have played a major role in improving the healthcare organisation in terms of continuous tele-monitoring therapy and maintaining telemedicine management sys...
详细信息
ISBN:
(纸本)9781509018611
machine learning algorithm and web-based application systems have played a major role in improving the healthcare organisation in terms of continuous tele-monitoring therapy and maintaining telemedicine management systems. Currently, no intelligent system has been used in terms of managing sickle cell disease. However, this paper presents a system that facilitates a shift from manual methods to automated approach that can offer fast data collection with a reduced error rate. The system will be able to examine patient data and provide a suitable amount of Hydroxycarbamide drugs/liquid for each patient. By using a web-based system, we tend to improve patient welfare and mitigate patient illness before it gets worse over time, particularly with elderly people. The system will forward any critical concerns from the patient;it generates an automatic message to the medical doctors based on web-based platform in order to assist them with optimal decision-making. The initial case study that has been addressed in this project is how to make predictions for sickle cell disease for the amount of dose based on different architectures of machinelearning in order to obtain high accuracy and performance. The most significant key for making predictions of the amount of medication is to enable healthcare organisation to provide accurate therapy recommendations based on previous data. The results using ANN showed that the proposed network produces significant improvements using the different evaluation methods. In our experiments, The MLP algorithm produced the best result in terms of the lowest error rates compare with other techniques. The Mean Square Error, Root Mean Square Error, Mean Absolute Error, and Mean Absolute Percentage Error achieved 17887.55, 133.74, 90.20 and 0.1345, respectively.
Floods are common natural disasters that cause severe devastation of any country. They are commonly caused by precipitation and runoff of rivers, particularly during periods of excessively high rainy season. Due to gl...
详细信息
ISBN:
(纸本)9781467383530
Floods are common natural disasters that cause severe devastation of any country. They are commonly caused by precipitation and runoff of rivers, particularly during periods of excessively high rainy season. Due to global warming issues and extreme environmental effects, flood has become a serious problem to the extent of bringing about negative impact to the mankind and infrastructure. To date, sensor network technology has been used in many areas including water level fluctuation. However, efficient flood monitoring and real time notification system still a crucial part because Information Technology enabled applications have not been employed in this sector in a broad way. This research presents a description of an alert generating system for flood detection with a focus on determining the current water level using sensors technology. The system then provides notification message about water level sensitivity via Global Communication and Mobile System modem to particular authorise person. Besides the Short Message Service, the system instantaneously uploads and broadcast information through web base public network. machine-learningalgorithms were conducted to perform the classification process. Four experiments were carried out to classify flood data from normal and at risk condition in which 99.5% classification accuracy was achieved using Random Forest algorithm. Classification using Bagging, Decision Tree and HyperPipes algorithms achieved accuracy of 97.7 %, 94.6% and 89.8 %, respectively.
Background Kidney disease progression rates vary among patients. Rapid and accurate prediction of kidney disease outcomes is crucial for disease management. In recent years, various prediction models using machine Lea...
详细信息
Background Kidney disease progression rates vary among patients. Rapid and accurate prediction of kidney disease outcomes is crucial for disease management. In recent years, various prediction models using machinelearning (ML) algorithms have been established in nephrology. However, their accuracy have been inconsistent. Therefore, we conducted a systematic review and meta-analysis to investigate the diagnostic accuracy of ML algorithms for kidney disease progression. Methods We searched PubMed, EMBASE, Cochrane Central Register of Controlled Trials, the Chinese Biomedicine Literature Database, Chinese National Knowledge Infrastructure, Wanfang Database, and the VIP Database for diagnostic studies on ML algorithms' accuracy in predicting kidney disease prognosis, from the establishment of these databases until October 2020. Two investigators independently evaluate study quality by QUADAS-2 tool and extracted data from single ML algorithm for data synthesis using the bivariate model and the hierarchical summary receiver operating characteristic (HSROC) model. Results Fifteen studies were left after screening, only 6 studies were eligible for data synthesis. The sample size of these 6 studies was 12,534, and the kidney disease types could be divided into chronic kidney disease (CKD) and Immunoglobulin A Nephropathy, with 5 articles using end-stage renal diseases occurrence as the primary outcome. The main results indicated that the area under curve (AUC) of the HSROC was 0.87 (0.84-0.90) and ML algorithm exhibited a strong specificity, 95% confidence interval and heterogeneity (I-2) of (0.87, 0.84-0.90, [I-2 99.0%]) and a weak sensitivity of (0.68, 0.58-0.77, [I-2 99.7%]) in predicting kidney disease deterioration. And the the results of subgroup analysis indicated that ML algorithm's AUC for predicting CKD prognosis was 0.82 (0.79-0.85), with the pool sensitivity of (0.64, 0.49-0.77, [I-2 99.20%]) and pool specificity of (0.84, 0.74-0.91, [I-2 99.84%]). The ML algor
In the mineral production industry, the separation of valuable from waste minerals is generally conducted through the froth flotation process. Flotation is a multivariate and complex process that cannot be modeled usi...
详细信息
In the mineral production industry, the separation of valuable from waste minerals is generally conducted through the froth flotation process. Flotation is a multivariate and complex process that cannot be modeled using traditional mathematical procedures. Therefore, machine learning algorithms must be applied to experimental databases for the identification of the flotation system. The grade and recovery of concentrate serve as key metallurgical parameters in the flotation process, reflecting the quality and quantity of the final product. These parameters are directly linked to the manipulated variables of the process, such as gas velocity, frother type/dosage, and slurry solids concentration. In this study, the metallurgical parameters (i.e. copper recovery and concentrate grade) of an industrial flotation column were modeled using various machine learning algorithms. The final results indicate that optimised Gaussian Process Regression (GPR) outperforms the other learningalgorithms in the data-based modeling of the flotation system. Dans l'industrie de la production min & eacute;rale, la s & eacute;paration des min & eacute;raux pr & eacute;cieux des d & eacute;chets est r & eacute;alis & eacute;e g & eacute;n & eacute;ralement par le proc & eacute;d & eacute;de flottation par moussage. La flottation est un proc & eacute;d & eacute;complexe & agrave;plusieurs variables qu'on ne peut pas mod & eacute;liser en utilisant des proc & eacute;dures math & eacute;matiques traditionnelles. Par cons & eacute;quent, on doit appliquer des algorithmes d'apprentissage automatique aux bases de donn & eacute;es exp & eacute;rimentales pour l'identification du syst & egrave;me de flottation. La qualit & eacute;et la r & eacute;cup & eacute;ration du concentr & eacute;servent de param & egrave;tres m & eacute;tallurgiques cl & eacute;s dans le proc & eacute;d & eacute;de flottation, refl & eacute;tant la qualit & eacute;et la quantit & eacute;du produit final. Ces param & egrave;
This study applies three different artificial intelligence algorithms (Multi-layer Perceptron (MLP), Extreme Gradient Boosting (XGBoost), and Support Vector machine (SVM)) to estimate CO2 emissions in Turkiye's tr...
详细信息
This study applies three different artificial intelligence algorithms (Multi-layer Perceptron (MLP), Extreme Gradient Boosting (XGBoost), and Support Vector machine (SVM)) to estimate CO2 emissions in Turkiye's transportation sector. The input parameters considered are Energy consumption (ENERGY), Vehicle Kilometers (VK), POPulation (POP), Year (Y), and Gross Domestic Product Per Capita (GDP). Strong correlations are observed, with ENERGY having the highest correlation followed by VK, POP, Y, and GDP. Four scenarios are designed based on the correlation effect: scenario 1 (ENERGY/VK/POP/Y/GDP), scenario 2 (ENERGY/VK/POP/Y), scenario 3 (ENERGY/VK/POP), and scenario 4 (ENERGY/VK). Experiments compare their effects on CO2 emissions using statistical indicators (R-2, RMSE, MSE, and MAE). Across all scenarios and algorithms, R-2 values range from 0.8969 to 0.9886, and RMSE values range from 0.0333 to 0.1007. The XGBoost algorithm performs best in scenario 4. Artificial intelligence algorithms prove successful in estimating CO2 emissions. This study has significant implications for policymakers and stakeholders. It highlights the need to review energy investments in transportation and implement regulations, restrictions, legislation, and obligations to reduce emissions. Artificial intelligence algorithms offer the potential for developing effective strategies. Policymakers can use these insights to prioritize sustainable energy investments. In conclusion, this study provides insights into the relationship between input parameters and CO2 emissions in the transportation sector. It emphasizes the importance of proactive measures and policies to address the sector's environmental impact. It also contributes to the understanding of AI-assisted CO2 emissions forecasting in the transport sector, potentially informing future policy decisions aimed at emission reduction and sustainable transport development.
暂无评论