Deep convolutional networks often encounter information bottlenecks when extracting land object features, resulting in critical geometric information loss, which impedes semantic segmentation capabilities in complex g...
详细信息
Deep convolutional networks often encounter information bottlenecks when extracting land object features, resulting in critical geometric information loss, which impedes semantic segmentation capabilities in complex geospatial backgrounds. We developed LULC-SegNet, a semantic segmentation network for land use and land cover (LULC), which integrates features from the denoising diffusion probabilistic model (DDPM). This network enhances the clarity of the edge segmentation, detail resolution, and the visualization and accuracy of the contours by delving into the spatial details of the remote sensing images. The LULC-SegNet incorporates DDPM decoder features into the LULC segmentation task, utilizing machine learning clusteringalgorithms and spatial attention to extract continuous DDPM semantic features. The network addresses the potential loss of spatial details during feature extraction in convolutional neural network (CNN), and the integration of the DDPM features with the CNN feature extraction network improves the accuracy of the segmentation boundaries of the geographical features. Ablation and comparison experiments conducted on the Circum-Tarim Basin Region LULC Dataset demonstrate that the LULC-SegNet improved the LULC semantic segmentation. The LULC-SegNet excels in multiple key performance indicators compared to existing advanced semantic segmentation methods. Specifically, the network achieved remarkable scores of 80.25% in the mean intersection over union (MIOU) and 93.92% in the F1 score, surpassing current technologies. The LULC-SegNet demonstrated an IOU score of 73.67%, particularly in segmenting the small-sample river class. Our method adapts to the complex geophysical characteristics of remote sensing datasets, enhancing the performance of automatic semantic segmentation tasks for land use and land cover changes and making critical advancements.
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 fuzzy c-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 fuzzy c-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.
Due to the constant fluctuation on global currency rates, it is challenging to make predictions on trading in foreign exchange (Forex) currency market without an intensive analysis;hence, traders struggle to make a pr...
详细信息
ISBN:
(纸本)9781728130033
Due to the constant fluctuation on global currency rates, it is challenging to make predictions on trading in foreign exchange (Forex) currency market without an intensive analysis;hence, traders struggle to make a profit. This study aims to analyze the relationship between the trade open time and profit in the Forex currency market to help traders to increase the chance of winning trades and make a profit. We developed a technique to observe the most suitable time duration to trade and the profit. This technique assists traders to enhance the chance of winning trades and make a profit by identifying whether it is more likely to make a profit when they keep the trade opened for a longer time or a shorter time. A Forex dataset (N=1,000,000 trades) from a third-party broker database based in Australia has been used. The collected data were filtered according to the popularity of currency pairs. Five currency pairs (as EUR vs USD, GBP vs JPY, USD vs JPY, GBP vs USD and EUR vs JPY) were further analyzed using Support Vector Machine (SVM) with the Radial Basis Function (RBF) kernel and k-means clustering algorithms. It showed that EUR vs USD and USD vs JPY have sensitive movements of profit with the trading time. The highest profit was observed trading time in between 5 to 15 minutes. Our analysis illustrates that shorter time traders are making more profits than the longer time traders. Hence, this study demonstrates that Forex traders make a profit when the market has a unique volatile situation. This study should be useful as a reference for researches in Forex market analyses and Forex Industry to utilize profit-making strategies.
This paper discusses the effect of under-sampling to determine outliers in terms of the amount of effort, which is the number of people hours needed to complete a task, in embedded software development projects. Estim...
详细信息
ISBN:
(纸本)9781728125534
This paper discusses the effect of under-sampling to determine outliers in terms of the amount of effort, which is the number of people hours needed to complete a task, in embedded software development projects. Estimating the amount of effort for new software projects is especially important. As outliers are harmful to the estimation, they are excluded from many estimation models. However, such outliers can be identified in practice once the projects are completed, and so they should not be excluded during the creation of models and when estimating the amount of effort. We have also attempted to detect outliers in the amount of effort by using an ANN and an SVM. However, the accuracy of the classifications was insufficient due to a small number of outliers. This problem is called data imbalance, and occurs in most of machine learning methods. In order to avoid this problem, we explores rebalancing methods with k-means cluster-based under-sampling. The purpose of the methods are to improve the proportion of outliers that are correctly identified, while keeping the other classification criteria high. Evaluation experiments are carried out to compare the prediction accuracy of the methods with k-means under-sampling, with random under-sampling and without under-sampling using 10-fold cross-validation. The results show that the methods with under-sampling have higher sensitivity and lower precision than these of the methods without under-sampling. The results show that the proposed methods can improve the accuracy to determine outliers;however they pick up excess samples as outliers.
The abstract There has been much research on efficient energy utilisation to prolong the life-span of wireless sensor networks and other tiny devices, with various techniques deployed to address energy consumption iss...
详细信息
ISBN:
(纸本)9781538667125
The abstract There has been much research on efficient energy utilisation to prolong the life-span of wireless sensor networks and other tiny devices, with various techniques deployed to address energy consumption issues. The aim of this paper is to build on previous research and further investigate the use of a mobile sink for data collection in wireless sensor networks. We aim to find an optimal path for a mobile sink to collect a single packet from each sensor via a single hop and return back to the starting point such that, subject to the length constraint L, total energy wastage is minimised. We have previously referred to this problem as the minimum energy cost mobile sink restricted tour problem and showed that this is NP-hard. We were inspired by the concept of the k-meansclustering algorithm and propose a restricted k-meansclustering algorithm. In this approach, we first divide the sensing field into a set of k clusters such that the radius of each cluster is R, where R is the maximum transmission range of the sensor. We iteratively increase the value of k until all the sensors are covered under the length constraint. Simplicity, efficiency, and flexibility are the most important and distinctive features of this algorithm. The technique is implemented to evaluate the algorithm and compare it to our previous algorithm. Our simulation results outperformed the previous technique.
In this paper, a novel clustering algorithm dubbed as Visual k-means (VkM) is proposed. The proposed algorithm deals with the uniform effect which is very much visible in k-means algorithm for skewed distributed data ...
详细信息
ISBN:
(纸本)9788132225263;9788132225256
In this paper, a novel clustering algorithm dubbed as Visual k-means (VkM) is proposed. The proposed algorithm deals with the uniform effect which is very much visible in k-means algorithm for skewed distributed data sources. The evaluation of the proposed algorithm is conducted with 10 imbalanced dataset against five benchmarkalgorithms on six evaluation metrics. The observations from the simulation results project that the proposed algorithm is one of the best alternatives to handle the imbalanced datasets effectively.
The effectiveness of clustering analysis relies not only on the assumption of cluster number but also on the class distribution of the data employed. This paper represents another step in overcoming a drawback of k-me...
详细信息
ISBN:
(纸本)9783319137315;9783319137308
The effectiveness of clustering analysis relies not only on the assumption of cluster number but also on the class distribution of the data employed. This paper represents another step in overcoming a drawback of k-means, its lack of defense against imbalance data distribution. k-means is a partitional clustering technique that is well-known and widely used for its low computational cost. However, the performance of k-means algorithm tends to be affected by skewed data distributions, i.e., imbalanced data. They often produce clusters of relatively uniform sizes, even if input data have varied cluster size, which is called the "uniform effect." In this paper, we analyze the causes of this effect and illustrate that it probably occurs more in the k-meansclustering process. As the minority class decreases in size, the "uniform effect" becomes evident. To prevent the effect of the "uniform effect", we revisit the well-known k-means algorithm and provide a general method to properly cluster imbalance distributed data. The proposed algorithm consists of a novel under random subset generation technique implemented by defining number of subsets depending upon the unique properties of the dataset. We conduct experiments using ten UCI datasets from various application domains using five algorithms for comparison on eight evaluation metrics. Experiment results show that our proposed approach has several distinctive advantages over the original k-means and other clustering methods.
k-means is a partitional clustering technique that is well known and widely used for its low computational cost. However, the performance of k-means algorithm tends to be affected by skewed data distributions, i.e., i...
详细信息
k-means is a partitional clustering technique that is well known and widely used for its low computational cost. However, the performance of k-means algorithm tends to be affected by skewed data distributions, i.e., imbalanced data. They often produce clusters of relatively uniform sizes, even if input data have varied cluster size, which is called the "uniform effect". In this paper, we analyze the causes of this effect and illustrate that it probably occurs more in the k-meansclustering process. As the minority class decreases in size, the "uniform effect" becomes evident. To prevent the effect of the "uniform effect", we revisit the well-known k-means algorithm and provide a general method to properly cluster imbalance distributed data. The proposed algorithm consists of a novel undersampling technique implemented by intelligently removing noisy and weak instances from majority class. We conduct experiments using twelve UCI datasets from various application domains using five algorithms for comparison on eight evaluation metrics. Experimental results show the effectiveness of the proposed clustering algorithm in clustering balanced and imbalanced data.
Taking thermal efficiency and LOI as outputs and 20 operating parameters as inputs of the combustion process of a 600 MWe cyclone boiler with 6 mills, 10 fuzzy rules are set up by k-meansclustering firstly according ...
详细信息
ISBN:
(纸本)9780769538198
Taking thermal efficiency and LOI as outputs and 20 operating parameters as inputs of the combustion process of a 600 MWe cyclone boiler with 6 mills, 10 fuzzy rules are set up by k-meansclustering firstly according to the data collected by DCS. Secondly, a T-S (Takagi-Sugeno) fuzzy neural network which consists of 11 BP sub-networks is developed to model the combustion process characteristics. As the LOI measuring device does not work well and thermal efficiency is a calculation value which is dependent on other primary parameters especially those of coal quality which are hard to be measured accurately and timely, the data collected are unavoidably spoiled by noise seriously. Normal neural networks such as BP and RBF are not capable of dealing with such a noise case. Validation tests demonstrate that the proposed T-S fuzzy neural network, which synthesizes well the advantages both of neural network and fuzzy reasoning, is much friendly to data noise and can be chose as an applied data mining tool.
暂无评论