A GRNN-based Approach towards Prediction from Small Datasets in Medical Application

Hyperspectral imaging with shallow convolutional neural networks (SCNN) predicts the early herbicide stress in wheat cultivars.

Hyperspectral imaging with shallow convolutional neural networks (SCNN) predicts the early herbicide stress in wheat cultivars

In high-field magnetic resonance imaging, water-fat separation in the presence of B0 field inhomogeneity is an important research. Various field map estimation techniques that use three-point multi-echo acquisitions have been developed for reliable water-fat separation. Among the numerous techniques, iterative decomposition of water and fat with echo asymmetry and least squares estimation (IDEAL) has gained considerable popularity as an iterative method for acquiring high-quality water and fat images. Some of the goals for the IDEAL are to obtain an initial estimate of the field map and to ensure that the algorithm arrives at the correct solution that is close to the true value. However, due to the worsened B0 inhomogeneity at high field, IDEAL cannot adjust for meaningful field map estimation, particularly for a large field of view. Previously, to improve the robustness of this estimation, a region-growing technique was developed to take advantage of the 2D linear extrapolation procedure through the seed point set by the median value in the target object. There are some limitations with this approach, for example, the dependence on the initial seed point such as its number, intensity, and position. In this paper, we introduce a robust method called the multiple region-growing scheme that does not need to consider parameters related to accuracy. As a result of the proposed method, we obtained a robust field map estimation that can be applied in high fields with an average accuracy of 91.9% higher than the existing method.

/pdf/effective-fat-quantification-using-multiple-region-growing-59i6074t6h.pdf

Effective Fat Quantification Using Multiple Region Growing Scheme at High-Field MRI

Automatic weed classification is necessary to enhance the productivity of crops in weed management system. Major issue in agriculture is the control of weeds growing among plantation crops. Various site-specific weed management techniques are developed to classify the weeds, but enhancing the production quality and yield poses a complex task in agriculture. An effective method is developed to classify the crop or weeds using the proposed Feedback Cat Swarm Optimization-based Deep Neuro-Fuzzy Network (FCSO-based DNFN). However, the proposed FCSO is derived by integrating the Feedback Artificial Tree (FAT) algorithm and Cat Swarm Optimization (CSO) algorithm. The process of weed classification is carried out with the MapReduce framework by employing the mapper and reducer functions. The cluster head (CH) selection is made, and the process of routing is carried out through CH to transfer the weed image from the sensor nodes to Base Station (BS) for weed classification. However, the classification process is done based on the fitness measure by considering the feature vector. Through the comparative analysis of the proposed system with the existing state-of-art techniques, the proposed FCSO-based DNFN obtained higher performance in terms ofthroughput, energy, delay, and accuracy with the values of 0.5018, 0.5014 J, 0.5174 s, and 0.9523, respectively. Besides, while increasing the node size, the accuracy of the classification improves, and hence the performance of the developed model also increases.

FCS-fuzzy net: cluster head selection and routing-based weed classification in IoT with mapreduce framework

In the automatic apple sorting task, it is necessary to automatically classify certain apple species A shallow convolutional neural network (CNN) architecture is proposed for this purpose After collecting a certain number of apple images and labelling them, training data is obtained through a series of data augmentation operations, and then training and parameter optimization are carried out through the Caffe framework The feasibility of the method is verified by experiments which are divided into two cases In the case of no occlusion, the classification accuracy of apple images reaches approximately 92% in our test set Besides, block voting is used to aid the proposed method and a good result can be achieved in our test set in the case of part occlusion caused by branches and leaves, rotten spots, and other kinds of apples The proposed shallow network is characterized by a small number of parameters and shows resistance to overfitting with a limited dataset Such a network presents an alternative for classification related tasks in smart visual Internet of Things and brings attention to reducing the complexity of deep neural networks while maintaining their strength

/pdf/a-shallow-convolutional-neural-network-for-apple-gta1jbyx0s.pdf

A Shallow Convolutional Neural Network for Apple Classification

Aiming at the problem that the robot de-palletizing task is difficult to accomplish under unstable ambient light, a two-step method is proposed to realize the localization of workpieces, which in this work are woven bags. To begin with, Region Growing method is used to extract the whole target region in the original image, and the relationship model between image intensity and the optimal Region Growing threshold is established. Then, Progressive Probabilistic Hough Transform(PPHT) is used to locate each woven bag. To improve the system performance, the optimal parameters of the PPHT function in different illumination intervals are determined. Finally, experiments are conducted to verify the effectiveness of the proposed method. Experiment results demonstrate this method is robust and feasible.

/pdf/a-workpiece-localization-method-for-robotic-de-palletizing-f6vzablidy.pdf

Jia Kang

Papers

A Shallow Convolutional Neural Network for Apple Classification

A Workpiece Localization Method for Robotic De-Palletizing Based on Region Growing and PPHT

Strongly Bonded Cfx@S Composite Assisting the Long-Cycle Stability of Li-S Battery

High-rate performance and super long-cycle stability of Na3V2(PO4)3 cathode material coated by diatomic doped carbon

Diatomic Doped Carbon Coating Boosting the High-Rate Performance and Super Long-Cycle Stability of Na3v2(Po4)3 Cathode Material