Comparison of Multi-Methods for Identifying Maize Phenology Using PhenoCams

Accurately identifying the phenology of summer maize is crucial for both cultivar breeding and fertilizer controlling in precision agriculture. In this study, daily RGB images covering the entire growth of summer maize were collected using phenocams at sites in Shangqiu (2018, 2019 and 2020) and Nanpi (2020) in China. Four phenological dates, including six leaves, booting, heading and maturity of summer maize, were pre-defined and extracted from the phenocam-based images. The spectral indices, textural indices and integrated spectral and textural indices were calculated using the improved adaptive feature-weighting method. The double logistic function, harmonic analysis of time series, Savitzky–Golay and spline interpolation were applied to filter these indices and pre-defined phenology was identified and compared with the ground observations. The results show that the DLF achieved the highest accuracy, with the coefficient of determination (R2) and the root-mean-square error (RMSE) being 0.86 and 9.32 days, respectively. The new index performed better than the single usage of spectral and textural indices, of which the R2 and RMSE were 0.92 and 9.38 days, respectively. The phenological extraction using the new index and double logistic function based on the PhenoCam data was effective and convenient, obtaining high accuracy. Therefore, it is recommended the adoption of the new index by integrating the spectral and textural indices for extracting maize phenology using PhenoCam data.

An improved Random Forest based on Feature Selection and Feature weighting for case retrieval in CBR system Application to medical data

: The medical diagnostic process works very similarly to the Case Based Reasoning (CBR) cycle scheme. CBR is a problem solving approach based on the reuse of past experiences called cases. To improve the performance of the retrieval phase, a Random Forest (RF) model is proposed, in this respect we used this algorithm in three different ways (three different algorithms): Classic Random Forest (CRF) algorithm, Random Forest with Feature Selection (RF_FS) algorithm where we selected the most important attributes and deleted the less important ones and Weighted Random Forest (WRF) algorithm where we weighted the most important attributes by giving them more weight. We did this by multiplying the entropy with the weight corresponding to each attribute.We tested our three algorithms CRF, RF_FS and WRF with CBR on data from 11 medical databases and compared the results they produced. We found that WRF and RF_FS give better results than CRF. The experiemental results show the performance and robustess of the proposed approach.

Feature-reduction Fuzzy c-means Clustering for Basketball Players Positioning

One of the best-known clustering methods is the fuzzy c-means clustering algorithm, besides k-means and hierarchical clustering. Since FCM treats all data features as equally important, it may obtain a poor clustering result. To solve the problem, feature selection with feature weighting is needed. Besides feature selection by assigning feature weights, there is also feature selection by assigning feature weights and eliminating the unrelated feature(s). THE Feature-reduction FCM (FRFCM) clustering algorithm can improve the FCM clustering result by weighting the features and discarding the unrelated feature(s) during the clustering process. Basketball is one of the famous sports, both international and national. There are five players in basketball, each with a different position. A player can generally be in guard, forward, or center position. Those three general positions need different characteristics of players’ physical conditions. In this paper, FRFCM is used to select the related physical feature(s) for basketball players, consisting of height, weight, age, and body mass index. to determine the basketball players’ position. The result shows that FRFCM can be applied to determine the basketball players’ position, where the most related physical feature is the player’s height. FRFCM gets one incorrect player’s position, so the error rate is 0.0435. As a comparison, FCM gets five incorrect player’s positions, with an error rate of 0.2174. This method can help the coach decide the basketball new player’s position.

Evolutionary Computation for Feature Manipulation in Salient Object Detection

<p>The human visual system can efficiently cope with complex natural scenes containing various objects at different scales using the visual attention mechanism. Salient object detection (SOD) aims to simulate the capability of the human visual system in prioritizing objects for high-level processing. SOD is a process of identifying and localizing the most attention grabbing object(s) of a scene and separating the whole extent of the object(s) from the scene. In SOD, significant research has been dedicated to design and introduce new features to the domain. The existing saliency feature space suffers from some difficulties such as having high dimensionality, features are not equally important, some features are irrelevant, and the original features are not informative enough. These difficulties can lead to various performance limitations. Feature manipulation is the process which improves the input feature space to enhance the learning quality and performance. Evolutionary computation (EC) techniques have been employed in a wide range of tasks due to their powerful search abilities. Genetic programming (GP) and particle swarm optimization (PSO) are well-known EC techniques which have been used for feature manipulation. The overall goal of this thesis is to develop feature manipulation methods including feature weighting, feature selection, and feature construction using EC techniques to improve the input feature set for SOD. This thesis proposes a feature weighting method utilizing PSO to explore the relative contribution of each saliency feature in the feature combination process. Saliency features are referred to the features which are extracted from different levels (e.g., pixel, segmentation) of an image to compute the saliency values over the entire image. The experimental results show that different datasets favour different weights for the employed features. The results also reveal that by considering the importance of each feature in the combination process, the proposed method has achieved better performance than that of the competitive methods. This thesis proposes a new bottom-up SOD method to detect salient objects by constructing two new informative saliency features and designing a new feature combination framework. The proposed method aims at developing features which target to identify different regions of the image. The proposed method makes a good balance between computational time and performance. This thesis proposes a GP-based method to automatically construct foreground and background saliency features. The automatically constructed features do not require domain-knowledge and they are more informative compared to the manually constructed features. The results show that GP is robust towards the changes in the input feature set (e.g., adding more features to the input feature set) and improves the performance by introducing more informative features to the SOD domain. This thesis proposes a GP-based SOD method which automatically produces saliency maps (a 2-D map containing saliency values) for different types of images. This GP-based SOD method applies feature selection and feature combination during the learning process for SOD. GP with built-in feature selection process which selects informative features from the original set and combines the selected features to produce the final saliency map. The results show that GP can potentially explore a large search space and find a good way to combine different input features. This thesis introduces GP for the first time to construct high-level saliency features from the low-level features for SOD, which aims to improve the performance of SOD, particularly on challenging and complex SOD tasks. The proposed method constructs fewer features that achieve better saliency performance than the original full feature set.</p>

Evolutionary Computation for Feature Manipulation in Salient Object Detection

<p>The human visual system can efficiently cope with complex natural scenes containing various objects at different scales using the visual attention mechanism. Salient object detection (SOD) aims to simulate the capability of the human visual system in prioritizing objects for high-level processing. SOD is a process of identifying and localizing the most attention grabbing object(s) of a scene and separating the whole extent of the object(s) from the scene. In SOD, significant research has been dedicated to design and introduce new features to the domain. The existing saliency feature space suffers from some difficulties such as having high dimensionality, features are not equally important, some features are irrelevant, and the original features are not informative enough. These difficulties can lead to various performance limitations. Feature manipulation is the process which improves the input feature space to enhance the learning quality and performance. Evolutionary computation (EC) techniques have been employed in a wide range of tasks due to their powerful search abilities. Genetic programming (GP) and particle swarm optimization (PSO) are well-known EC techniques which have been used for feature manipulation. The overall goal of this thesis is to develop feature manipulation methods including feature weighting, feature selection, and feature construction using EC techniques to improve the input feature set for SOD. This thesis proposes a feature weighting method utilizing PSO to explore the relative contribution of each saliency feature in the feature combination process. Saliency features are referred to the features which are extracted from different levels (e.g., pixel, segmentation) of an image to compute the saliency values over the entire image. The experimental results show that different datasets favour different weights for the employed features. The results also reveal that by considering the importance of each feature in the combination process, the proposed method has achieved better performance than that of the competitive methods. This thesis proposes a new bottom-up SOD method to detect salient objects by constructing two new informative saliency features and designing a new feature combination framework. The proposed method aims at developing features which target to identify different regions of the image. The proposed method makes a good balance between computational time and performance. This thesis proposes a GP-based method to automatically construct foreground and background saliency features. The automatically constructed features do not require domain-knowledge and they are more informative compared to the manually constructed features. The results show that GP is robust towards the changes in the input feature set (e.g., adding more features to the input feature set) and improves the performance by introducing more informative features to the SOD domain. This thesis proposes a GP-based SOD method which automatically produces saliency maps (a 2-D map containing saliency values) for different types of images. This GP-based SOD method applies feature selection and feature combination during the learning process for SOD. GP with built-in feature selection process which selects informative features from the original set and combines the selected features to produce the final saliency map. The results show that GP can potentially explore a large search space and find a good way to combine different input features. This thesis introduces GP for the first time to construct high-level saliency features from the low-level features for SOD, which aims to improve the performance of SOD, particularly on challenging and complex SOD tasks. The proposed method constructs fewer features that achieve better saliency performance than the original full feature set.</p>

SAMGEP: A Novel Method for Prediction of Phenotype Event Times Using the Electronic Health Record

While there exist numerous methods to identify binary phenotypes (i.e. COPD) using electronic health record (EHR) data, few exist to ascertain the timings of phenotype events (i.e. COPD onset or exacerbations). Estimating event times could enable more powerful use of EHR data for longitudinal risk modeling, including survival analysis. Here we introduce Semi-supervised Adaptive Markov Gaussian Embedding Process (SAMGEP), a semi-supervised machine learning algorithm to estimate phenotype event times using EHR data with limited observed labels, which require resource-intensive chart review to obtain. SAMGEP models latent phenotype states as a binary Markov process, and it employs an adaptive weighting strategy to map timestamped EHR features to an embedding function that it models as a state-dependent Gaussian process. SAMGEP’s feature weighting achieves meaningful feature selection, and its predictions significantly improve AUCs and F1 scores over existing approaches in diverse simulations and real-world settings. It is particularly adept at predicting cumulative risk and event counting process functions, and is robust to diverse generative model parameters. Moreover, it achieves high accuracy with few (50-100) labels, efficiently leveraging unlabeled EHR data to maximize information gain from costly-to-obtain event time labels. SAMGEP can be used to estimate accurate phenotype state functions for risk modeling research.

Attention-Based CNN and Bi-LSTM Model Based on TF-IDF and GloVe Word Embedding for Sentiment Analysis

Sentiment analysis (SA) detects people’s opinions from text engaging natural language processing (NLP) techniques. Recent research has shown that deep learning models, i.e., Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Transformer-based provide promising results for recognizing sentiment. Nonetheless, CNN has the advantage of extracting high-level features by using convolutional and max-pooling layers; it cannot efficiently learn a sequence of correlations. At the same time, Bidirectional RNN uses two RNN directions to improve extracting long-term dependencies. However, it cannot extract local features in parallel, and Transformer-based like Bidirectional Encoder Representations from Transformers (BERT) are the computational resources needed to fine-tune, facing an overfitting problem on small datasets. This paper proposes a novel attention-based model that utilizes CNNs with LSTM (named ACL-SA). First, it applies a preprocessor to enhance the data quality and employ term frequency-inverse document frequency (TF-IDF) feature weighting and pre-trained Glove word embedding approaches to extract meaningful information from textual data. In addition, it utilizes CNN’s max-pooling to extract contextual features and reduce feature dimensionality. Moreover, it uses an integrated bidirectional LSTM to capture long-term dependencies. Furthermore, it applies the attention mechanism at the CNN’s output layer to emphasize each word’s attention level. To avoid overfitting, the Guasiannoise and GuasianDroupout are adopted as regularization. The model’s robustness is evaluated on four English standard datasets, i.e., Sentiment140, US-airline, Sentiment140-MV, SA4A with various performance matrices, and compared efficiency with existing baseline models and approaches. The experiment results show that the proposed method significantly outperforms the state-of-the-art models.