CNN-Based Facial Expression Recognition with Simultaneous Consideration of Inter-Class and Intra-Class Variations

Facial expression recognition is crucial for understanding human emotions and nonverbal communication. With the growing prevalence of facial recognition technology and its various applications, accurate and efficient facial expression recognition has become a significant research area. However, most previous methods have focused on designing unique deep-learning architectures while overlooking the loss function. This study presents a new loss function that allows simultaneous consideration of inter- and intra-class variations to be applied to CNN architecture for facial expression recognition. More concretely, this loss function reduces the intra-class variations by minimizing the distances between the deep features and their corresponding class centers. It also increases the inter-class variations by maximizing the distances between deep features and their non-corresponding class centers, and the distances between different class centers. Numerical results from several benchmark facial expression databases, such as Cohn-Kanade Plus, Oulu-Casia, MMI, and FER2013, are provided to prove the capability of the proposed loss function compared with existing ones.

Design and Development of a Non-Contact ECG-Based Human Emotion Recognition System Using SVM and RF Classifiers

Emotion recognition becomes an important aspect in the development of human-machine interaction (HMI) systems. Positive emotions impact our lives positively, whereas negative emotions may cause a reduction in productivity. Emotionally intelligent systems such as chatbots and artificially intelligent assistant modules help make our daily life routines effortless. Moreover, a system which is capable of assessing the human emotional state would be very helpful to assess the mental state of a person. Hence, preventive care could be offered before it becomes a mental illness or slides into a state of depression. Researchers have always been curious to find out if a machine could assess human emotions precisely. In this work, a unimodal emotion classifier system in which one of the physiological signals, an electrocardiogram (ECG) signal, has been used is proposed to classify human emotions. The ECG signal was acquired using a capacitive sensor-based non-contact ECG belt system. The machine-learning-based classifiers developed in this work are SVM and random forest with 10-fold cross-validation on three different sets of ECG data acquired for 45 subjects (15 subjects in each age group). The minimum classification accuracies achieved with SVM and RF emotion classifier models are 86.6% and 98.2%, respectively.

Motor imagery electroencephalogram classification algorithm based on joint features in the spatial and frequency domains and instance transfer

Introduction

Motor imagery electroencephalography (MI-EEG) has significant application value in the field of rehabilitation, and is a research hotspot in the brain-computer interface (BCI) field. Due to the small training sample size of MI-EEG of a single subject and the large individual differences among different subjects, existing classification models have low accuracy and poor generalization ability in MI classification tasks.

Methods

To solve this problem, this paper proposes a electroencephalography (EEG) joint feature classification algorithm based on instance transfer and ensemble learning. Firstly, the source domain and target domain data are preprocessed, and then common space mode (CSP) and power spectral density (PSD) are used to extract spatial and frequency domain features respectively, which are combined into EEG joint features. Finally, an ensemble learning algorithm based on kernel mean matching (KMM) and transfer learning adaptive boosting (TrAdaBoost) is used to classify MI-EEG.

Results

To validate the effectiveness of the algorithm, this paper compared and analyzed different algorithms on the BCI Competition IV Dataset 2a, and further verified the stability and effectiveness of the algorithm on the BCI Competition IV Dataset 2b. The experimental results show that the algorithm has an average accuracy of 91.5% and 83.7% on Dataset 2a and Dataset 2b, respectively, which is significantly better than other algorithms.

Discussion

The statement explains that the algorithm fully exploits EEG signals and enriches EEG features, improves the recognition of the MI signals, and provides a new approach to solving the above problem.

Classification of motor imagery electroencephalogram signals by using adaptive cross-subject transfer learning

Introduction

Electroencephalogram (EEG)-based motor imagery (MI) classification is an important aspect in brain-computer interfaces (BCIs), which bridges between neural system and computer devices decoding brain signals into recognizable machine commands. However, due to the small number of training samples of MI electroencephalogram (MI-EEG) for a single subject and the great individual differences of MI-EEG among different subjects, the generalization and accuracy of the model on the specific MI task may be poor.

Methods

To solve these problems, an adaptive cross-subject transfer learning algorithm is proposed, which is based on kernel mean matching (KMM) and transfer learning adaptive boosting (TrAdaBoost) method. First, the common spatial pattern (CSP) is used to extract the spatial features. Then, in order to make the feature distribution more similar among different subjects, the KMM algorithm is used to compute a sample weight matrix for aligning the mean between source and target domains and reducing distribution differences among different subjects. Finally, the sample weight matrix from KMM is used as the initialization weight of TrAdaBoost, and then TrAdaBoost is used to adaptively select source domain samples that are closer to the target task distribution to assist in building a classification model.

Results

In order to verify the effectiveness and feasibility of the proposed method, the algorithm is applied to BCI Competition IV datasets and in-house datasets. The results show that the average classification accuracy of the proposed method on the public datasets is 89.1%, and the average classification accuracy on the in-house datasets is 80.4%.

Discussion

Compared with the existing methods, the proposed method effectively improves the classification accuracy of MI-EEG signals. At the same time, this paper also applies the proposed algorithm to the in-house dataset, the results verify the effectiveness of the algorithm again, and the results of this study have certain clinical guiding significance for brain rehabilitation.

Smart Distribution Network Situation Awareness for High-Quality Operation and Maintenance: A Brief Review

In order to meet the requirements of high-tech enterprises for high power quality, high-quality operation and maintenance (O&M) in smart distribution networks (SDN) is becoming increasingly important. As a significant element in enhancing the high-quality O&M of SDN, situation awareness (SA) began to excite the significant interest of scholars and managers, especially after the integration of intermittent renewable energy into SDN. Specific to high-quality O&M, the paper decomposes SA into three stages: detection, comprehension, and projection. In this paper, the state-of-the-art knowledge of SND SA is discussed, a review of critical technologies is presented, and a five-layer visualization framework of the SDN SA is constructed. SA detection aims to improve the SDN observability, SA comprehension is associated with the SDN operating status, and SA projection pertains to the analysis of the future SDN situation. The paper can provide researchers and utility engineers with insights into the technical achievements, barriers, and future research directions of SDN SA.

Fast Target Recognition Based on Improved ORB Feature

A novel fast target recognition algorithm is proposed under the dynamic scene moving target recognition. Aiming at the poor matching effect of the traditional Oriented Fast and Rotated Brief (ORB) algorithm on underexposed or overexposed images caused by illumination, the idea of combining adaptive histogram equalization with the ORB algorithm is proposed to get better feature point quality and matching efficiency. First, the template image and each frame of the video stream are processed by grayscale. Second, the template image and the image to be input in the video stream are processed by adaptive histogram equalization. Third, the feature point descriptors of the ORB feature are quantized by the Hamming distance. Finally, the K-nearest-neighbor (KNN) matching algorithm is used to match and screen feature points. According to the matching good feature point logarithm, a reasonable threshold is established and the target is classified. The comparison and verification are carried out by experiments. Experimental results show that the algorithm not only maintains the superiority of ORB itself but also significantly improves the performance of ORB under the conditions of underexposure or overexposure. The matching effect of the image is robust to illumination, and the target to be detected can be accurately identified in real time. The target can be accurately classified in the small sample scene, which can meet the actual production requirements.

CorrNet: Fine-Grained Emotion Recognition for Video Watching Using Wearable Physiological Sensors

Recognizing user emotions while they watch short-form videos anytime and anywhere is essential for facilitating video content customization and personalization. However, most works either classify a single emotion per video stimuli, or are restricted to static, desktop environments. To address this, we propose a correlation-based emotion recognition algorithm (CorrNet) to recognize the valence and arousal (V-A) of each instance (fine-grained segment of signals) using only wearable, physiological signals (e.g., electrodermal activity, heart rate). CorrNet takes advantage of features both inside each instance (intra-modality features) and between different instances for the same video stimuli (correlation-based features). We first test our approach on an indoor-desktop affect dataset (CASE), and thereafter on an outdoor-mobile affect dataset (MERCA) which we collected using a smart wristband and wearable eyetracker. Results show that for subject-independent binary classification (high-low), CorrNet yields promising recognition accuracies: 76.37% and 74.03% for V-A on CASE, and 70.29% and 68.15% for V-A on MERCA. Our findings show: (1) instance segment lengths between 1–4 s result in highest recognition accuracies (2) accuracies between laboratory-grade and wearable sensors are comparable, even under low sampling rates (≤64 Hz) (3) large amounts of neutral V-A labels, an artifact of continuous affect annotation, result in varied recognition performance.

Emotion Recognition for Human-Robot Interaction: Recent Advances and Future Perspectives

A fascinating challenge in the field of human-robot interaction is the possibility to endow robots with emotional intelligence in order to make the interaction more intuitive, genuine, and natural. To achieve this, a critical point is the capability of the robot to infer and interpret human emotions. Emotion recognition has been widely explored in the broader fields of human-machine interaction and affective computing. Here, we report recent advances in emotion recognition, with particular regard to the human-robot interaction context. Our aim is to review the state of the art of currently adopted emotional models, interaction modalities, and classification strategies and offer our point of view on future developments and critical issues. We focus on facial expressions, body poses and kinematics, voice, brain activity, and peripheral physiological responses, also providing a list of available datasets containing data from these modalities.