Dermatological diseases are the most prevalent diseases worldwide. Despite being common, its diagnosis is extremely difficult and requires extensive experience in the domain. In this research paper, we provide an appr...
详细信息
ISBN:
(纸本)9781467391870
Dermatological diseases are the most prevalent diseases worldwide. Despite being common, its diagnosis is extremely difficult and requires extensive experience in the domain. In this research paper, we provide an approach to detect various kinds of these diseases. We use a dual stage approach which effectively combines Computer Vision and machinelearning on clinically evaluated histopathological attributes to accurately identify the disease. In the first stage, the image of the skin disease is subject to various kinds of pre-processing techniques followed by feature extraction. The second stage involves the use of machinelearning algorithms to identify diseases based on the histopathological attributes observed on analysing of the skin. Upon training and testing for the six diseases, the system produced an accuracy of up to 95 percent.
Although AI was proposed by *** back in 1956, 60 years later, we are beginning to witness a surge of interest in the practical applications of AI in many sectors. However, the actual adoption rate of AI in businesses ...
详细信息
ISBN:
(纸本)9781890843373
Although AI was proposed by *** back in 1956, 60 years later, we are beginning to witness a surge of interest in the practical applications of AI in many sectors. However, the actual adoption rate of AI in businesses has been quite low. The current 3rd AI boom follows the 2nd AI boom in the 1980s which focused mainly on expert systems. In this paper, an attempt is made to analyze the technological accumulation process from the 2nd to the 3rd AI boom and to identify forthcoming key application areas. The methodology is based on a 3 step approach. In the first step, a bibliometric analyses of Artificial Intelligence was carried out to analyze the technological accumulation during the 2nd and the 3rd AI boom. Having done the desk work and interviewed several experts in AI, we decided that 2013 was the year which marked the boundary between the two AI booms. A bibliometric analyses based on countries and institutions over the 2 periods was followed by co-occurrence analyses of the author keywords in the 2 periods, before and after 2013. In the third stage, interviews were carried out with some corporate members to do a qualitative analysis on the possible application areas of AI and issues to be solved for adopting AI were identified. The results showed that in the 3rd AI boom, machinelearning, deep learning, genetic algorithm have been identified as the key technologies. Furthermore, prediction, forecasting, datamining, fault diagnosis, patternrecognition were identified as important areas in the 3rd AI boom. It was also revealed that firms' R&D has been changing to focus more on AI applications.
Nowadays, the researches in datamining area have been continuous increasing. Appling datamining to agriculture;for example, the prediction of rice produce for farmers is still challenging. The objective of the resea...
详细信息
ISBN:
(纸本)9781538649916
Nowadays, the researches in datamining area have been continuous increasing. Appling datamining to agriculture;for example, the prediction of rice produce for farmers is still challenging. The objective of the research is to propose a model using machinelearning Techniques comparing between Decision Tree Technique and Neural Network Technique (ANN) for the prediction of rice produce for farmers. Farmers can predict volume of rice produce and selling price. It is helpful for farmers to increase their income. The process of the research follows Cross-industry standard process for datamining (CRISP-DM) process. The model pattern is classified by machinelearning techniques experiment with a dataset of farmer records. Performance measure of model pattern uses four options such as Test Options, Cross-Validation Folds 10, Split 80-20, and Use Training Set. After that, four options will be averaged for accuracy. The experimental result shows that the best technique which has highest accuracy can be helpful for farmers in real world.
Driving behavior recognition is an active research topic as it has many potential applications, such as fleet management, vehicle anti-theft, and planning of car insurance policies. Nowadays, the most successful appro...
详细信息
ISBN:
(纸本)9781728107882
Driving behavior recognition is an active research topic as it has many potential applications, such as fleet management, vehicle anti-theft, and planning of car insurance policies. Nowadays, the most successful approaches to driving behavior recognition are based on machinelearning algorithms. Each machinelearning algorithm has its pros and cons, and no single algorithm fits all problems. Therefore, how to determine an appropriate algorithm suitable for discovering driving patterns is a critical step in driving behavior recognition. This paper aims to conduct an empirical study for driving behavior recognition and evaluate the recognition performance of popular machine-learning algorithms. The experimental results showed that many sensor values gathered from the CAN bus are either highly correlated with one another or less important attributed to driving behavior identification. Among traditional machinelearning approaches, ensemble tree-based algorithms, such as Random Forests and Decision Trees have better performance when compared with other approaches.
Planning has achieved significant progress in recent years. Among the various approaches to scale up plan synthesis, the use of macro-actions has been widely explored. As a first stage towards the development of a sol...
详细信息
ISBN:
(纸本)9781467391870
Planning has achieved significant progress in recent years. Among the various approaches to scale up plan synthesis, the use of macro-actions has been widely explored. As a first stage towards the development of a solution to learn on-line macro-actions, we propose an algorithm to identify useful macroactions based on datamining techniques. The integration in the planning search of these learned macro-actions shows significant improvements over six classical planning benchmarks.
In recent years, the need for real-time patternrecognition applications has sharply increased. Along with deep and probabilistic neural networks, hybrid architectures such as neo-fuzzy networks and networks based on ...
详细信息
Our work is focused on determining whether any correlation exists between preparatory classes taken by Electrical Engineering (EE) students at Eastern Washington University (EWU) early in their academic careers (e.g. ...
详细信息
ISBN:
(纸本)9781728107882
Our work is focused on determining whether any correlation exists between preparatory classes taken by Electrical Engineering (EE) students at Eastern Washington University (EWU) early in their academic careers (e.g. Calculus and Physics sequences) and their departmental GPAs upon graduation. Using academic data from prior EE graduates, a machinelearning algorithm was trained to predict with 85% certainty whether a student's GPA will fall above/below one standard deviation from the mean. This prediction can be used to channel university resources to support those students who need it the most. However, there is a significant prediction overlap for average students, i.e. those who fall within approximately one standard deviation around the mean. It is our conjecture that incorporating more major-specific data (e.g. grades in a set of core introductory level departmental courses) or a customized general aptitude test administered at the end of the sophomore year could improve the prediction accuracy for the average group.
In this paper the fusion of artificial neural networks, granular computing and learning automata theory is proposed and we present as a final result ANLAGIS, an adaptive neuron-like network based on learning automata ...
详细信息
ISBN:
(纸本)9783642022630
In this paper the fusion of artificial neural networks, granular computing and learning automata theory is proposed and we present as a final result ANLAGIS, an adaptive neuron-like network based on learning automata and granular inference systems. ANLAGIS can be applied to both patternrecognition and learning control problems. Another interesting contribution of this paper is the distinction between pre-synaptic and post-synaptic learning in artificial neural networks. To illustrate the capabilities of ANLAGIS some experiments on knowledge discovery in datamining and machinelearning are presented. Previous work of Jang et al. [1] on adaptive network-based fuzzy inference systems, or simply ANFIS, can be considered a precursor of ANLAGIS. The main, novel contribution of ANLAGIS is the incorporation of learning Automata Theory within its structure.
The Locally Linear Embedding (LLE) is one of the efficient nonlinear dimensionality reduction techniques. But for some high dimensional data, it is not taking the class information of the data into account and Euclide...
详细信息
ISBN:
(纸本)9781479928606
The Locally Linear Embedding (LLE) is one of the efficient nonlinear dimensionality reduction techniques. But for some high dimensional data, it is not taking the class information of the data into account and Euclidean distance can not accurately reflect the similarity among samples. The paper proposes an improved Supervised LLE which combines class labeled data and Mahalanobis Distance (MSP-LLE). First, the approach learns a Mahalanobis Distance from the existing data. Then the Mahalanobis Distance and label information are combined to choose neighborhoods. Finally, ELM is using to map the unlabeled data to the feature space, which easily implement fault patternrecognition. The experiment result shows its good performance on reduction and recognition for high-dimensional and similar data.
datamining is the science of finding unexpected, valuable, or interesting structures in large data sets. It is an interdisciplinary activity, taking ideas and methods from statistics, machinelearning, database techn...
详细信息
datamining is the science of finding unexpected, valuable, or interesting structures in large data sets. It is an interdisciplinary activity, taking ideas and methods from statistics, machinelearning, database technology, and other areas. It poses novel challenges, in part arising from the sheer size of modem data sets. Although there is no doubt that it addresses important questions, there are deep issues to be resolved relating to data quality and the nature of inference. Statisticians have an important role to play in resolving these issues.
暂无评论