Human facial emotion recognition (FER) has attracted the attention of the research community for its promising applications. Mapping different facial expressions to the respective emotional states are the main task in FER. The classical FER consists of two major steps: feature extraction and emotion recognition. Currently, the Deep Neural Networks, especially the Convolutional Neural Network (CNN), is widely used in FER by virtue of its inherent feature extraction mechanism from images. Several works have been reported on CNN with only a few layers to resolve FER problems. However, standard shallow CNNs with straightforward learning schemes have limited feature extraction capability to capture emotion information from high-resolution images. A notable drawback of the most existing methods is that they consider only the frontal images (i.e., ignore profile views for convenience), although the profile views taken from different angles are important for a practical FER system. For developing a highly accurate FER system, this study proposes a very Deep CNN (DCNN) modeling through Transfer Learning (TL) technique where a pre-trained DCNN model is adopted by replacing its dense upper layer(s) compatible with FER, and the model is fine-tuned with facial emotion data. A novel pipeline strategy is introduced, where the training of the dense layer(s) is followed by tuning each of the pre-trained DCNN blocks successively that has led to gradual improvement of the accuracy of FER to a higher level. The proposed FER system is verified on eight different pre-trained DCNN models (VGG-16, VGG-19, ResNet-18, ResNet-34, ResNet-50, ResNet-152, Inception-v3 and DenseNet-161) and well-known KDEF and JAFFE facial image datasets. FER is very challenging even for frontal views alone. FER on the KDEF dataset poses further challenges due to the diversity of images with different profile views together with frontal views. The proposed method achieved remarkable accuracy on both datasets with pre-trained models. On a 10-fold cross-validation way, the best achieved FER accuracies with DenseNet-161 on test sets of KDEF and JAFFE are 96.51% and 99.52%, respectively. The evaluation results reveal the superiority of the proposed FER system over the existing ones regarding emotion detection accuracy. Moreover, the achieved performance on the KDEF dataset with profile views is promising as it clearly demonstrates the required proficiency for real-life applications.

Handwritten character recognition complexity varies among different languages due to distinct shapes, strokes and number of characters. Numerous works in handwritten character recognition are available for English with respect to other major languages such as Bangla. Existing methods use distinct feature extraction techniques and various classification tools in their recognition schemes. Recently, Convolutional Neural Network (CNN) is found efficient for English handwritten character recognition. In this paper, a CNN based Bangla handwritten character recognition is investigated. The proposed method normalizes the written character images and then employ CNN to classify individual characters. It does not employ any feature extraction method like other related works. 20000 handwritten characters with different shapes and variations are used in this study. The proposed method is shown satisfactory recognition accuracy and outperformed some other prominent exiting methods.

Electroencephalography (EEG), despite its inherited complexity, is a preferable brain signal for automatic human emotion recognition (ER), which is a challenging machine learning task with emerging applications. In any automatic ER, machine learning (ML) models classify emotions using the extracted features from the EEG signals, and therefore, such feature extraction is a crucial part of ER process. Recently, EEG channel connectivity features have been widely used in ER, where Pearson correlation coefficient (PCC), mutual information (MI), phase-locking value (PLV), and transfer entropy (TE) are well-known methods for connectivity feature map (CFM) construction. CFMs are typically formed in a two-dimensional configuration using the signals from two EEG channels, and such two-dimensional CFMs are usually symmetric and hold redundant information. This study proposes the construction of a more informative CFM that can lead to better ER. Specifically, the proposed innovative technique intelligently combines CFMs’ measures of two different individual methods, and its outcomes are more informative as a fused CFM. Such CFM fusion does not incur additional computational costs in training the ML model. In this study, fused CFMs are constructed by combining every pair of methods from PCC, PLV, MI, and TE; and the resulting fused CFMs PCC + PLV, PCC + MI, PCC + TE, PLV + MI, PLV + TE, and MI + TE are used to classify emotion by convolutional neural network. Rigorous experiments on the DEAP benchmark EEG dataset show that the proposed CFMs deliver better ER performances than CFM with a single connectivity method (e.g., PCC). At a glance, PLV + MI-based ER is shown to be the most promising one as it outperforms the other methods.

Ant Colony Optimization (ACO) is a practical and well-studied bio-inspired algorithm to generate feasible solutions for combinatorial optimization problems such as the Traveling Salesman Problem (TSP). ACO is inspired by the foraging behavior of ants, where an ant selects the next city to visit according to the pheromone on the trail and the visibility heuristic (inverse of distance). ACO assigns higher heuristic desirability to the nearest city without considering the issue of returning to the initial city or starting point once all the cities are visited. This study proposes an improved ACO-based method, called ACO with Adaptive Visibility (ACOAV), which intelligently adopts a generalized formula of the visibility heuristic associated with the final destination city. ACOAV uses a new distance metric that includes proximity and eventual destination to select the next city. Including the destination in the metric reduces the tour cost because such adaptation helps to avoid using longer links while returning to the starting city. In addition, partial updates of individual solutions and 3-Opt local search operations are incorporated in the proposed ACOAV. ACOAV is evaluated on a suite of 35 benchmark TSP instances and rigorously compared with ACO. ACOAV generates better solutions for TSPs than ACO, while taking less computational time; such twofold achievements indicate the proficiency of the individual adoption techniques in ACOAV, especially in AV and partial solution update. The performance of ACOAV is also compared with the other ten state-of-the-art bio-inspired methods, including several ACO-based methods. From these evaluations, ACOAV is found as the best one for 29 TSP instances out of 35 instances; among those, optimal solutions have been achieved in 22 instances. Moreover, statistical tests comparing the performance revealed the significance of the proposed ACOAV over the considered bio-inspired methods.