Sentiment classification is increasingly used to automatically identify a positive or negative sentiment in a text review. In classification, feature selection had always been a critical and challenging problem. Most of the related feature selection for sentiment classification techniques unable to overcome problems of evaluating the significant features that will reduce the classification performance. This paper proposes an enhanced hybrid feature selection technique to improve the sentiment classification based on machine learning approaches. First, two customer review datasets namely Sentiment Labelled and large IMDB are retrieved and pre-processed. Next, the proposed feature selection technique which is the hybridization of Term Frequency-Inverse Document Frequency (TF-IDF) and Supports Vector Machine (SVM-RFE) is developed and tested on these two datasets. TF-IDF aims to measure features importance. The SVM-RFE iteratively evaluates and ranks the features. For sentiment classification, only the ktop features from the ranked features will be used. Finally, the Support Vector Machine (SVM) classifier is deployed to observe the performance of the proposed technique. The performance is measured using accuracy, precision, recall, and F-measure. The experimental results show promising performances with 84.54% to 89.56% in the measurements especially from the large IMDB dataset. The results also outperformed other related techniques in certain datasets. Consequently, the proposed technique able to reduce from 19.25% to 70.5% of the features to be classified. This reduction rate is significant in optimally utilizing the computational resources while maintaining the efficiency of the classification performance.

Several deep image-based models which depend on deep learning have shown great success in the recorded computational and reconstruction efficiencies, especially for single high-resolution images. In the past, the use of super-resolution was commonly characterized by interference, and hence, the need for a model with higher performance. This study proposed a method for low to super-resolution face recognition, called efficient sub-pixel convolution neural network. This is a convolutional neural network which is usually employed at the time of image pre-processing to increase the chances of recognizing images with low resolution. The proposed Efficient Sub-Pixel Convolutional Neural Network is used for the conversion of low-resolution images into a high-resolution format for onward recognition. This conversion is based on the features extracted from the image. Using several evaluation tools, the proposed Efficient Sub-Pixel Convolutional Neural Network recorded a higher performance in terms of image resolution when compared to the performance of the benchmarked traditional methods. The evaluations were carried out on a Yale face database and ORL dataset faces. For Yale and ORL datasets, the obtained accuracy of the proposed method was 95.3% and 93.5%, respectively, which were higher than those of the other related methods.

Sentiment analysis techniques are increasingly exploited to categorize the opinion text to one or more predefined sentiment classes for the creation and automated maintenance of review-aggregation websites. In this paper, a Malay sentiment analysis classification model is proposed to improve classification performances based on the semantic orientation and machine learning approaches. First, a total of 2,478 Malay sentiment-lexicon phrases and words are assigned with a synonym and stored with the help of more than one Malay native speaker, and the polarity is manually allotted with a score. In addition, the supervised machine learning approaches and lexicon knowledge method are combined for Malay sentiment classification with evaluating thirteen features. Finally, three individual classifiers and a combined classifier are used to evaluate the classification accuracy. In experimental results, a wide-range of comparative experiments is conducted on a Malay Reviews Corpus (MRC), and it demonstrates that the feature extraction improves the performance of Malay sentiment analysis based on the combined classification. However, the results depend on three factors, the features, the number of features and the classification approach.

This tomato maturity estimator is developed to conduct tomato color grading using machine vision to replace human labor. Existing machine has not been widely applied in Malaysia since the cost is too expensive. The major problem in tomato color grading by human vision was due to the subjectivity of human vision and error prone by visual stress and tiredness. Therefore, this system is carried out to judge the tomato maturity based on their color and to estimate the expiry date of tomato by their color. Evolutionary methodology was implemented in this system design by using several image processing techniques including image acquisition, image enhancement and feature extraction. Fifty sample data of tomatoes were collected during image acquisition phase in the format of RGB color image. The quality of the collected images were being improved in the image enhancement phase; mainly converting to color space format (L*a*b*), filtering and threshold process. In the feature extraction phase, value of red-green is being extracted. The values are then being used as information for determining the percentage of tomato maturity and to estimate expiry date of tomato. According to the testing results, this system has met its objectives whereby 90.00% of the tomato tested has not rotten yet. This indicates that the judgment of tomato maturity and the estimation of tomato's expiry date were accurate in this project.

Handwriting recognition refers to recognizing a handwritten input that includes character(s) or digit(s) based on an image. Because most applications of handwriting recognition in real life contain sequential text in various languages, there is a need to develop a dynamic handwriting recognition system. Inspired by the neuroevolutionary technique, this paper proposes a Dynamically Configurable Convolutional Recurrent Neural Network (DC-CRNN) for the handwriting recognition sequence modeling task. The proposed DC-CRNN is based on the Salp Swarm Optimization Algorithm (SSA), which generates the optimal structure and hyperparameters for Convolutional Recurrent Neural Networks (CRNNs). In addition, we investigate two types of encoding techniques used to translate the output of optimization to a CRNN recognizer. Finally, we proposed a novel hybridized SSA with Late Acceptance Hill-Climbing (LAHC) to improve the exploitation process. We conducted our experiments on two well-known datasets, IAM and IFN/ENIT, which include both the Arabic and English languages. The experimental results have shown that LAHC significantly improves the SSA search process. Therefore, the proposed DC-CRNN outperforms the handcrafted CRNN methods.

In this paper, a vehicle type classification approach is proposed by using an enhanced feature extraction technique based on Sparse-Filtered Convolutional Neural Network with Layer-Skipping strategy (SF-CNNLS). To extract rich and discriminant vehicle features, we introduce Three-Channels of SF-CNNLS (TC-SF-CNNLS) as the feature extraction technique. Local and global features of vehicles are extracted from three channels of an image which are, luminance and chromatic components. This technique is inspired by how human eyes differentiating objects that share almost similar features. TC-SF-CNNLS is tested with a benchmark dataset that provides frontal-view images to classify vehicle types of the bus, passenger car, taxi, minivan, SUV, and truck with Softmax Regression as a classifier. This test aims to observe the ability of this technique in differentiating vehicles with almost similar features but different classes. A test is also conducted with the self-obtained dataset (SPINT) to observe the effectiveness of this technique. The results are observed based on accuracy, precision, recall, and f-score, whereby, TCSF-NNLS has successfully recognized all the classes with an average accuracy of 0.905, precision is between 0.8629 to 0.9548, recall is between 0.83 to 0.96 and f-score is between 0.8564 to 0.9523. In addition, this technique is able to outperform other existing techniques with an average accuracy of 93.% compared to only 89.2% when 5 classes of vehicles are tested.