Offline Handwritten Character & Numeral Recognition A Kernel Based Approach

Automatic Character Recognition for the handwritten Indic script has listed up as most the challenging area for research in the field of pattern recognition. Although a great amount of research work has been reported, but all the state-of-art methods are limited with optimal features. This article aims to suggest a well-defined recognition model which harnessed upon handwritten Odia characters and numerals by implementing a novel process of decomposition in terms of 3rd level Fast Discrete Curvelet Transform (FDCT) to get higher dimension feature vector. After that, Kernel-Principal Component Analysis (K-PCA) considered to obtained optimal features from FDCT feature. Finally, the classification is performed by using Probabilistic Neural Network (PNN) on handwritten Odia character and numeral dataset from both NIT Rourkela and IIT Bhubaneswar. The outcome of proposed scheme outperforms better as compared to existing model with optimized Gaussian kernel-based feature set.

Deep neural learning based protein function prediction

<abstract> <p>It is vital for the annotation of uncharacterized proteins by protein function prediction. At present, Deep Neural Network based protein function prediction is mainly carried out for dataset of small scale proteins or Gene Ontology, and usually explore the relationships between single protein feature and function tags. The practical methods for large-scale multi-features protein prediction still need to be studied in depth. This paper proposes a DNN based protein function prediction approach IGP-DNN. This method uses Grasshopper Optimization Algorithm (GOA) and Intuitionistic Fuzzy c-Means clustering (IFCM) based protein function modules extracting algorithm to extract the features of protein modules, utilizing Kernel Principal Component Analysis (KPCA) method to reduce the dimensionality of the protein attribute information, and integrating module features and attribute features. Inputting integrated data into DNN through multiple hidden layers to classify proteins and predict protein functions. In the experiments, the F-measure value of IGP-DNN on the DIP dataset reaches 0.4436, which shows better performance.</p> </abstract>

A saliency model-oriented convolution neural network for cloud detection in remote sensing images

Remote sensing is an indispensable technical way for monitoring earth resources and environmental changes. However, optical remote sensing images often contain a large number of cloud, especially in tropical rain forest areas, make it difficult to obtain completely cloud-free remote sensing images. Therefore, accurate cloud detection is of great research value for optical remote sensing applications. In this paper, we propose a saliency model-oriented convolution neural network for cloud detection in remote sensing images. Firstly, we adopt Kernel Principal Component Analysis (KCPA) to unsupervised pre-training the network. Secondly, small labeled samples are used to fine-tune the network structure. And, remote sensing images are performed with super-pixel approach before cloud detection to eliminate the irrelevant backgrounds and non-clouds object. Thirdly, the image blocks are input into the trained convolutional neural network (CNN) for cloud detection. Meanwhile, the segmented image will be recovered. Fourth, we fuse the detected result with the saliency map of raw image to further improve the accuracy of detection result. Experiments show that the proposed method can accurately detect cloud. Compared to other state-of-the-art cloud detection method, the new method has better robustness.

Short-Term Load Forecasting of Distributed Energy System Based on Kernel Principal Component Analysis and KELM Optimized by Fireworks Algorithm

Accurate and stable load forecasting has great significance to ensure the safe operation of distributed energy system. For the purpose of improving the accuracy and stability of distributed energy system load forecasting, a forecasting model in view of kernel principal component analysis (KPCA), kernel extreme learning machine (KELM) and fireworks algorithm (FWA) is proposed. First, KPCA modal is used to reduce the dimension of the feature, thus redundant input samples are merged. Next, FWA is employed to optimize the parameters C and σ of KELM. Lastly, the load forecasting modal of KPCA-FWA-KELM is established. The relevant data of a distributed energy system in Beijing, China, is selected for training test to verify the effectiveness of the proposed method. The results show that the new hybrid KPCA-FWA-KELM method has superior performance, robustness and versatility in load prediction of distributed energy systems.

Research on the rapid design technology of automotive inspection structure based on MBD model

In view of the specificity and low efficiency of the design of automobile inspection fixture, a deformation design method of inspection fixture based on BP neural network algorithm is proposed. BP neural network algorithm is used to realize the learning and classification of case knowledge, and FCM (fuzzy c-means) algorithm and kernel principal component analysis are used to optimize the information source to improve the retrieval efficiency and accuracy. Based on the analysis of the existing fixture design case structure, the case structure is skeletonized to increase the applicability of the case structure. At the same time, the case frame structure is associated with the size chain, the priority deformation rule is proposed, and the relationship of each size chain is established to realize the mutual adjustment of each size chain. From the similarity of retrieval cases, the paper proposes the design scheme of inspection tools to improve the design efficiency. Finally, taking the front bumper model as the experimental object, the deformation rules are compared, and the priority deformation rule is more accurate than the ordinary basic rule. Compared with the manual design, the design efficiency of this method is improved by 55.71%, which proves the feasibility of this method.

Sensitivity analysis of factors affecting motion reliability of manipulator and fault diagnosis based on kernel principal component analysis

As an important index to quantitatively measure the motion performance of a manipulator, motion reliability is affected by many factors, such as joint clearance. The present research utilized a UR10 manipulator as the research object. A factor mapping model for influencing the motion reliability was established. The link flexibility factor, joint flexibility factor, joint clearance factor, and Denavit–Hartenberg (DH) parameters were comprehensively considered in this model. The coupling relationship among the various factors was concisely expressed. Subsequently, the nonlinear response surface method was used to calculate the reliability and sensitivity of the manipulator, which provided an applicable reference for its trajectory planning and motion control. In addition, a data-driven fault diagnosis method based on the kernel principal component analysis (KPCA) was used to verify the motion accuracy and sensitivity of the manipulator, and joint rotation failure was considered as an example to verify the accuracy of the KPCA method. This study on the motion reliability of the manipulator is of great significance for the current motion performance, adjusting the control strategy and optimizing the completion effect of the motion task of a manipulator.

Clustering Algorithm for Vehicle’s Driving Data Feature based on Integrated Navigation

The clustering result of K-means clustering algorithm is affected by the initial clustering center and the clustering result is not always global optimal. Therefore, the clustering analysis of vehicle’s driving data feature based on integrated navigation is carried out based on global K-means clustering algorithm. The vehicle mathematical model based on GPS/DR integrated navigation is constructed and the vehicle’s driving data based on GPS/DR integrated navigation, such as vehicle acceleration, are collected. After extracting the vehicle’s driving data features, the feature parameters of vehicle’s driving data are dimensionally reduced based on kernel principal component analysis to reduce the redundancy of feature parameters. The global K-means clustering algorithm converts clustering problem into a series of sub-cluster clustering problems. At the end of each iteration, an incremental method is used to select the next cluster of optimal initial centers. After determining the optimal clustering number, the feature clustering of vehicle’s driving data is completed. The experimental results show that the global K-means clustering algorithm has a clustering error of only 1.37% for vehicle’s driving data features and achieves high precision clustering for vehicle’s driving data features.