cloud extraction and classification from satellite imagery is important for many applications in remote sensing. Satellite images are segmented based on distance, intensity and texture of the images. The popular segme...
详细信息
cloud extraction and classification from satellite imagery is important for many applications in remote sensing. Satellite images are segmented based on distance, intensity and texture of the images. The popular segmentation algorithms, k-means (KM) and fuzzyc-means (FcM) clusteringalgorithms, face some problems such as unknown number of groups, unknown initialization and dead centers. In this paper, an unsupervised pixel classification by the KM and FcM algorithms is improved and the selection of centroids is made automatic. The proposed improved k-means (IKM) and improved fuzzyc-means (IFcM) clusteringalgorithms segment the INSAT-3D satellite's thermal infrared image into low-level, middle-level, high-level clouds and non-cloudy region. As human beings can easily find the clouds in the satellite images, visible image is used to differentiate the clouds from the background. A threshold is found from the histogram of the visible image to separate the cloudy and non-cloudy pixels. The other three thresholds to divide the clouds into three types are found from the thermal infrared image's histogram. The segmentation results of IKM and IFcM algorithms are compared with the existing segmentation algorithms. The comparison shows that IFcM algorithm matches well with original image followed by IKM algorithm as compared with existing algorithms.
University course timetabling problem is one of the hard problems and it must be done for each term frequently which is an exhausting and time consuming task. The main technique in the presented approach is focused on...
详细信息
ISBN:
(纸本)9781509035861
University course timetabling problem is one of the hard problems and it must be done for each term frequently which is an exhausting and time consuming task. The main technique in the presented approach is focused on developing and making the process of timetabling common lecturers among different departments of a university scalable. The aim of this paper is to improve the satisfaction of common lecturers among departments and then minimize the loss of resources within departments. In this method, at first all departments perform their scheduling process locally;then two clustering and traversing agents are used where the former is to cluster common lecturers among departments and the latter is to find extra resources among departments. After performing the clustering and traversing processes, the mapping operation in done based on principles of common lecturers constraint in redundant resources in order to gain the objectives of the problem. The problem's evaluation metric is evaluated via using fuzzyc-meansclustering algorithm on common lecturer constraints. An applied dataset is based on meeting the requirements of scheduling in real world among various departments of Islamic Azad University, Ahar Branch, Ahar, Iran.
University course timetabling problem is one of the hard problems and it must be done for each term frequently which is an exhausting and time consuming task. The main technique in the presented approach is focused on...
详细信息
ISBN:
(纸本)9781509035878
University course timetabling problem is one of the hard problems and it must be done for each term frequently which is an exhausting and time consuming task. The main technique in the presented approach is focused on developing and making the process of timetabling common lecturers among different departments of a university scalable. The aim of this paper is to improve the satisfaction of common lecturers among departments and then minimize the loss of resources within departments. In this method, at first all departments perform their scheduling process locally; then two clustering and traversing agents are used where the former is to cluster common lecturers among departments and the latter is to find extra resources among departments. After performing the clustering and traversing processes, the mapping operation in done based on principles of common lecturers constraint in redundant resources in order to gain the objectives of the problem. The problem's evaluation metric is evaluated via using fuzzyc-meansclustering algorithm on common lecturer constraints. An applied dataset is based on meeting the requirements of scheduling in real world among various departments of Islamic Azad University, Ahar Branch, Ahar, Iran.
暂无评论