Feature extraction to predict quality of segregating sweet tamarind using image processing

<p>In this modern age, several new methods have been developed, especially in image processing for agriculture business, which consists of technologies derived from artificial intelligence (AI) capabilities called machine learning. Classify is a widely used method to analyze patterns, trends, as well as the body of knowledge from the data visualization. Image classification application improves discrimination and prediction efficiency. The objective of this research was to feature extraction of sweet tamarind and compare the algorithm for classification. This research used images from golden sweet tamarind species with the use of MATLAB and Python language. The steps of this research consisted of 1) preprocessing step for finding the distance to appropriate of the image quality, 2) feature extracting for finding the number of black pixels and the number of white pixels, perimeter, diameter, and centroid, and 3) classifying for algorithms' comparison. The results showed that the camera's distance to the image was 60 cm. The coefficient of determination was at 0.9956, and the Standard Error of Estimate was 7,424.736 pixels. The conclusion of classification found that the random forest had the highest accuracy at 92.00%, SD. = 8.06, precision = 90.12, recall = 92.86, and F1-score = 91.36.</p>

Characteristic of Neural Signal Feature for Spike Sorting and Detection

Neural spike plays an important role in understanding brain activities, and in neural spike sorting, the features of signal are of great importance. This paper aims to have a review on features used to discriminate different originated spikes. The features are divided into three categories: features in the time domain, features in the transformation domain, and features of dimensional reduction. For each kind of feature, the basic principle, advantages, and disadvantages are described and discussed. Results showed that features in the time domain are suitable for on-chip or real-time spike sorting, while features in the transformation domain can be used in offline spike sorting aiming at high performance. For features of dimensional reduction, it makes a large number of features available in spike sorting. In conclusion, researchers need to determine features by balancing the minimization of calculation complexity and maximizing sorting performance according to different occasions and demands. Expectations are also made for future directions of spike feature studies. The article may guide both the physiologists who want to determine features in neural spike sorting and researchers who want to work on feature extracting algorithms further to achieve better performance in experimental challenges.

Generating faces From the Sketch Using GAN

In most cases, sketch images simply show basic profile details and do not include facial detail. As a result, precisely generating facial features is difficult. Using the created adversarial network and attributes, we propose an image translation network. A feature extracting network and a down-sampling up-sampling network make up the generator network. There is a generator and a discriminator in GANs. The Generator creates fake data samples (images, audio, etc.) in intended to mislead the Discriminator. On the other hand, the Discriminator attempts to distinguish between the real and fake sample Keywords: Deep Learning, Generative Adversarial Networks, Image Translation, face generation, skip-connection.

iPReditor-CMG: Improving Predictive RNA Editor for Crop Mitochondrial Genomes Using Genomic Sequence Features and Optimal Support Vector Machine

Cytosine (C) to uracil (U) RNA editing is one of the most important post-transcriptional processes, however exploring C-to-U editing events efficiently within the crop mitochondrial genome remains a challenge. An improving predictive RNA editor for crop mitochondrial genomes, iPReditor-CMG, was proposed, which was based on SVM, three common crop mitochondrial genomes and self-sequenced tobacco mitochondrial ATPase. After multi-combination feature extracting, high-dimension feature screening and multi-test independent predicting, the results showed that the average accuracy of intraspecific prediction was 0.85, and the highest value even up to 0.91, which outperformed the previous reference models. While the prediction accuracies were 0.78 between dicotyledons and no more than 0.56 between dicotyledons and monocotyledons, implying a possible similarity in C-to-U editing mechanisms among close relatives. The best model was finally identified with an independent test accuracy of 0.91 and an area under the curve of 0.88, and further suggested that five unreported feature sequences TGACA, ACAAC, GTAGA, CCGTT and TAACA were closely associated with the editing phenomenon. Multiple evaluation findings supported that the iPReditor-CMG could be effectively applied to predict crop mitochondrial editing sites, which may contribute to insight into their recognition mechanisms and even other post-transcriptional events in crop mitochondria.

A Novel Two-Stage Refine Filtering Method for EEG-Based Motor Imagery Classification

Cerebral stroke is a common disease across the world, and it is a promising method to recognize the intention of stroke patients with the help of brain–computer interface (BCI). In the field of motor imagery (MI) classification, appropriate filtering is vital for feature extracting of electroencephalogram (EEG) signals and consequently influences the accuracy of MI classification. In this case, a novel two-stage refine filtering method was proposed, inspired by Gradient-weighted Class Activation Mapping (Grad-CAM), which uses the gradients of any target concept flowing into the final convolutional layer to highlight the important part of training data for predicting the concept. In the first stage, MI classification was carried out and then the frequency band to be filtered was calculated according to the Grad-CAM of the MI classification results. In the second stage, EEG was filtered and classified for a higher classification accuracy. To evaluate the filtering effect, this method was applied to the multi-branch neural network proposed in our previous work. Experiment results revealed that the proposed method reached state-of-the-art classification kappa value levels and acquired at least 3% higher kappa values than other methods This study also proposed some promising application scenarios with this filtering method.

AGTH-Net: Attention-Based Graph Convolution-Guided Third-Order Hourglass Network for Sports Video Classification

As a hot research topic, sports video classification research has a wide range of applications in switched TV, video on demand, smart TV, and other fields and is closely related to people’s lives. Under this background, sports video classification research has aroused great interest in people. However, the existing methods usually use manual video classification, which the workers themselves often influence. It is challenging to ensure the accuracy of the results, leading to the wrong classification. Due to these limitations, we introduce neural network technology to the automatic classification of sports. This paper proposed a novel attention-based graph convolution-guided third-order hourglass network (AGTH-Net) classification model. First, we designed a kind of figure convolution model based on the attention mechanism. The model is the key to introduce the attention mechanism for neighborhood node weights’ allocation. It reduces the impact of error nodes in the neighborhood while avoiding manual weight assignment. Second, according to the sports complex video image characteristics, we use the third-order hourglass network structure. It is used for the extraction and fusion of multiscale characteristics of sports. In addition, in the hourglass, internal network residual-intensive modules are introduced, realizing characteristics in different levels of network transfer and reuse. It is helpful for maximum details to feature extracting and enhancing the network expression ability. Comparison and ablation experiments are also carried out to prove the effectiveness and superiority of the proposed algorithm.

3D-CNN-Based Sky Image Feature Extraction for Short-Term Global Horizontal Irradiance Forecasting

The instability and variability of solar irradiance induces great challenges for the management of photovoltaic water pumping systems. Accurate global horizontal irradiance (GHI) forecasting is a promising technique to solve this problem. To improve short-term GHI forecasting accuracy, ground-based sky image is valuable due to its correlation with solar generation. In previous studies, great efforts have been made to extract numerical features from sky image for data-driven solar irradiance forecasting methods, e.g., based on pixel-value color information, and based on the cloud motion detection method. In this work, we propose a novel feature extracting method for GHI forecasting that a three-dimensional (3D) convolutional neural network (CNN) is developed to extract features from sky images with efficient training strategies. Popular machine learning algorithms are introduced as GHI forecasting models and corresponding forecasting accuracy is fully explored with different input features on a large dataset. The numerical experiment illustrates that the minimum average root mean square error (RMSE) of 62 W/m2 is achieved by the proposed method with 15.2% improvement in Skill score against baseline forecasting method.

Automatic ER and PR scoring in Immunohistochemistry H-DAB Breast Cancer images

Breast Cancer (BC) is the most frequently diagnosed cancer for women. This way, the Brazilian Unified Health System (SUS) focuses on studying the disease and improving all the steps involved in dealing with BC. The presence or absence of the Estrogen Receptor (ER) and the Progesterone Receptor (PR), which define invasive subtypes, is detected through Immunohistochemistry (IHC). One way to assist the manual assessment of pathologists and histopathologists is to develop automatic scoring systems. Fortunately, digital pathology is increasingly achieving higher agreement with the pathologist. Therefore we create an automatic scoring system composed of image preprocessing, feature extracting, and classification achieves a 69% f-score rate.

A connectivity-constrained computational account of topographic organization in high-level visual cortex

Inferotemporal cortex (IT) in humans and other primates is topographically organized, with multiple domain-selective areas and other general patterns of functional organization. What factors underlie this organization, and what can this neural arrangement tell us about the mechanisms of high level vision? Here, we present an account of topographic organization involving a computational model with two components: 1) a feature-extracting encoder model of early visual processes, followed by 2) a model of high-level hierarchical visual processing in IT subject to specific biological constraints. In particular, minimizing the wiring cost on spatially organized feedforward and lateral connections within IT, combined with constraining the feedforward processing to be strictly excitatory, results in a hierarchical, topographic organization. This organization replicates a number of key properties of primate IT cortex, including the presence of domain-selective spatial clusters preferentially involved in the representation of faces, objects, and scenes, within-domain topographic organization such as animacy and indoor/outdoor distinctions, and generic spatial organization whereby the response correlation of pairs of units falls off with their distance. The model supports a view in which both domain-specific and domain-general topographic organization arise in the visual system from an optimization process that maximizes behavioral performance while minimizing wiring costs.

Autonomous learning of features for control: Experiments with embodied and situated agents

The efficacy of evolutionary or reinforcement learning algorithms for continuous control optimization can be enhanced by including an additional neural network dedicated to features extraction trained through self-supervision. In this paper we introduce a method that permits to continue the training of the features extracting network during the training of the control network. We demonstrate that the parallel training of the two networks is crucial in the case of agents that operate on the basis of egocentric observations and that the extraction of features provides an advantage also in problems that do not benefit from dimensionality reduction. Finally, we compare different feature extracting methods and we show that sequence-to-sequence learning outperforms the alternative methods considered in previous studies.