Computer Interaction Research Articles

Evaluation of perceived urgency from single-trial EEG data elicited by upper-body vibration feedback using deep learning

Notification systems that convey urgency without adding cognitive burden are crucial in human–computer interaction. Haptic feedback systems, particularly those utilizing vibration feedback, have emerged as a compelling solution, capable of providing desirable levels of urgency depending on the application. High-risk applications require an evaluation of the urgency level elicited during critical notifications. Traditional evaluations of perceived urgency rely on subjective self-reporting and performance metrics, which, while useful, are not real-time and can be distracting from the task at hand. In contrast, EEG technology offers a direct, non-intrusive method of assessing the user’s cognitive state. Leveraging deep learning, this study introduces a novel approach to evaluate perceived urgency from single-trial EEG data, induced by vibration stimuli on the upper body, utilizing our newly collected urgency-via-vibration dataset. The proposed model combines a 2D convolutional neural network with a temporal convolutional network to capture spatial and temporal EEG features, outperforming several established EEG models. The proposed model achieves an average classification accuracy of 83% through leave-one-subject-out cross-validation across three urgency classes (not urgent, urgent, and very urgent) from a single trial of EEG data. Furthermore, explainability analysis showed that the prefrontal brain region, followed by the central brain region, are the most influential in predicting the urgency level. A follow-up neural statistical analysis revealed an increase in event-related synchronization (ERS) in the theta frequency band (4–7 Hz) with the increased level of urgency, which is associated with high arousal and attention in the neuroscience literature. A limitation of this study is that the proposed model’s performance was tested only the urgency-via-vibration dataset, which may affect the generalizability of the findings.

An Interactive Web Interface for Facial Expression Recognition Using Deep Learning Framework: A Review

Facial expression is the instant reaction which shows on the face in a very short time. Visual system and brain easily understands the emotions of the person. Many computer vision researchers struggle to automate human emotion recognition. Facial expression recognition plays an important role in the area of human computer interaction, camera surveillance, security, identity verification in modern electronic devices. Working of human brain with neurons is represented using deep learning paradigm. This learning usually consists of a neural network model where neurons act as input and each of them are connected to move as outputs. In deep learning number of level are available which provides the interpretation of the data inserted. Proposed system use a Python-based framework that provides access to deep learning libraries such as TensorFlow and Keras. We are going to develop developed an interactive web interface to enable ease of use, scalability and adaptability of the system to different use-case scenarios. Here we have studied more than 30 papers of standard publications which are published after 2020 so as to have a recent ongoing research in this topic.

Structure-Activity Relationship of Truncated 4'-Selenonucleosides: A3 Adenosine Receptor Activity and Binding Selectivity.

This study explored the impact of structural modifications on truncated 4'-selenonucleosides as ligands for the A3 adenosine receptor (AR). We synthesized and evaluated a series of these compounds for their binding affinities, functional activities, and structural interactions by using computational modeling. The SAR study revealed that all compounds exhibited selective and notable hA3AR binding, among which 6l (K i = 5.2 nM) and 6m (K i = 5.7 nM) were found as the best binding compounds. The representative N 6-cyclopropyl compound 6m was found to be a partial agonist, contrasting with the antagonist profiles of truncated 4'-oxo and 4'-thionucleosides. Computational docking highlighted 6m's unique interaction with Thr94 at the A3AR binding site. This research not only advances our understanding of A3AR ligand interactions but also highlights the potential of truncated 4'-selenonucleosides as effective A3AR modulators.

Investigating the User Experience Design of Home Ventilators Through the Lens of Kansei Engineering

Abstract Obstructive sleep apnea hypopnea syndrome (OSAHS) is a disease characterized by respiratory disorders, and its prevalence rate is on the rise worldwide. Home ventilator can replace or enhance the respiratory function of human body and alleviate the symptoms of OSAHS, and has become an important treatment, rehabilitation, and nursing equipment for patients. However, the existing products lack humanistic care in emotional level, which leads to negative emotions in the process of human–computer interaction. This study seeks to enhance the user experience of home ventilators by applying the principles of Kansei Engineering (KE). Through a principal component analysis of nine pairs of Kansei image adjectives associated with home ventilators, we concluded that users prefer home ventilators that are “friendly,” “technological,” “pleasant ,” “orderly ,” and “easy to understand.” These findings were utilized in the Kansei design of home ventilators. The effectiveness of these conclusions in improving the user experience of ventilators was subsequently validated using the PrEmo method.

A Study of Model Iterations of Fitts’ Law and Its Application to Human–Computer Interactions

Fitts’ law, a predictive model for motor task completion time, is widely utilized in human–computer interaction (HCI) research. While its formulas in two dimensions have achieved consensus over the decades, research diverges on its application in three dimensions. This paper synthesizes practical applications across touchscreens, virtual reality (VR), pedals, handheld devices, etc., with a specific emphasis on enhancing interaction experiences for vulnerable populations. This review studies Fitts’ law’s applicability in diverse interaction scenarios, highlighting design considerations for touchscreens and handheld/foot-held devices. This article underscores the need for future research to explore three-dimensional applications and consider user age, with potential expansions into medical and sports domains. This systematic review aims to empower designers in crafting more ergonomic products and improving HCI experiences.

Skeuomorphic or flat? The effects of icon style on visual search and recognition performance

Although there have been many previous studies on icon visual search and recognition performance, only a few have considered the effects of both the internal and external characteristics of icons. In this behavioral study, we employed a visual search task and a semantic recognition task to explore the effects of icon style, semantic distance (SD), and task difficulty on users’ performance in perceiving and identifying icons. First, we created and filtered 64 new icons, which were divided into four different groups (flat design & close SD, flat design & far SD, skeuomorphic design & close SD, skeuomorphic design & far SD) through expert evaluation. A total of 40 participants (13 men and 27 women, ages ranging from 19 to 25 years, mean age = 21.9 years, SD=1.93) were asked to perform an icon visual search task and an icon recognition task after a round of learning. Participants’ accuracy and response time were measured as a function of the following independent variables: two icon styles (flat or skeuomorphic style), two levels of SD (close or far), and two levels of task difficulty (easy or difficult). The results showed that flat icons had better visual search performance than skeuomorphic icons; this beneficial effect increased as the task difficulty increased. However, in the icon recognition task, participants’ performance in recalling skeuomorphic icons was significantly better than that in recalling flat icons. Furthermore, a strong interaction effect between icon style and task difficulty was observed for response time. As the task difficulty decreased, the difference in recognition performance between these two different icon styles increased significantly. These findings provide valuable guidance for the design of icons in human–computer interaction interfaces.

Flexible sensor based on conformable, sticky, transparent elastomers for electronic skin

As 5G technology advances and enhances the interconnection of science and technology, the demand for advanced sensors has increased. Conventional rigid sensors are inadequate to meet these new requirements, thus sparking significant interest in flexible sensors. However, taking into account the biocompatibility, skin compliance, sensing performance, mechanical properties and optical properties of flexible sensors is still the direction of efforts. Therefore, in this study, the flexible sensor with a sandwich structure was prepared using AgNWs as a conductive filler and P32-PDMS elastomer as a flexible substrate. The PDMS elastomer is modified by blending PEG-PPG-PEG and PDMS, giving the P32-PDMS elastomer low Young’s modulus (32.35 kPa), high elongation at break (over 450 %) and good adhesion (18.94 N/m), and the P32-PDMS elastomer still retains a certain light transmittance (82.22 %) and biocompatibility (RGR=89.524). These properties simultaneously endow the flexible sensor with good sensitivity (GF=17.27), wide detection range (0–100 % strain), and excellent cycling stability (5000 cycles). When the flexible sensor is used as e-skin to monitor human body movements, stable signals are generated regardless of the low-strain movements of the human body (pulse and sound) or the high-strain movements of the human body (pressing and joint bending). Therefore, the prepared flexible sensor has great potential as e-skin in many fields such as personal health monitoring, human motion detection, human–computer interaction, flexible display, etc.

Immersive human–computer interaction and digital entertainment new media application in English e-learning mode

With the rapid development of e-learning, more and more learners use electronic devices to learn English. The traditional way of learning is often lack of interest and interaction, therefore, this paper discusses how to improve the effect of English learning through the application of immersive human–computer interaction and digital entertainment new media. Research on the selection of appropriate virtual reality, augmented reality or game platforms, design interactive content and scenes according to learning objectives, and use elements such as virtual scenes, virtual characters and audio-visual effects to improve learners’ immersion. Through careful design and production, learners can be presented with a lively, interesting and challenging learning environment to stimulate their interest and enthusiasm in learning. Develop interactive learning tools and applications that enable learners to interact with virtual environments or games, make appropriate adjustments and feedback based on learner feedback and behavior, and provide personalized learning support and guidance. Through the collection of learner feedback and behavioral data, combined with the evaluation indicators of learning outcomes, the immersive learning environment and content can be evaluated and improved and optimized according to the evaluation results, so as to further enhance learners’ learning motivation and learning outcomes.

Biobased, degradable and directional porous carboxymethyl chitosan/lignosulfonate sodium aerogel-based piezoresistive pressure sensor with dual-conductive network for human motion detection

The rapid growth of wearable electronics, healthcare monitoring, and human–computer interaction has sparked growing interest in flexible piezoresistive pressure sensors, which in turn raised considerable concerns about the increasingly serious environmental pollution caused by electronic waste. Herein, a radial inward directional freezing-drying method was proposed to prepare biobased, degradable and directional porous carboxymethyl chitosan/lignosulfonate sodium aerogel with dual-conductive network constructed by carboxylated multiwalled carbon nanotubes (C-CNTs) and MXene for piezoresistive pressure sensor. Owing to the synergistic conductive network of C-CNTs and MXene as well as directional porous structure, the sensor exhibited high sensitivity (2.33 kPa−1 in 0–10 kPa, 1.04 kPa−1 in 10–31 kPa, 0.53 kPa−1 in 31–53 kPa), fast response (response/recovery time of 140/60 ms), and excellent repeatability (2,000 loading–unloading cycles). Moreover, the sensor was successfully applied for human motion detection, healthy monitoring, micro-expression identification, and speech recognition. In addition, the aerogel for sensor was able to be completely degraded within 70 h in 1 M hydrochloric acid solution or partially degraded in boiling water within 2.5 h for the recycling of conductive materials, which was beneficial for not only environment protection but also saving resource. Our findings conceivably stand out as a new strategy to prepare environmentally friendly and high-performance piezoresistive pressure sensor and will promote the further development and application of flexible electronics.

Next-Gen Dynamic Hand Gesture Recognition: MediaPipe, Inception-v3 and LSTM-Based Enhanced Deep Learning Model

Gesture recognition is crucial in computer vision-based applications, such as drone control, gaming, virtual and augmented reality (VR/AR), and security, especially in human–computer interaction (HCI)-based systems. There are two types of gesture recognition systems, i.e., static and dynamic. However, our focus in this paper is on dynamic gesture recognition. In dynamic hand gesture recognition systems, the sequences of frames, i.e., temporal data, pose significant processing challenges and reduce efficiency compared to static gestures. These data become multi-dimensional compared to static images because spatial and temporal data are being processed, which demands complex deep learning (DL) models with increased computational costs. This article presents a novel triple-layer algorithm that efficiently reduces the 3D feature map into 1D row vectors and enhances the overall performance. First, we process the individual images in a given sequence using the MediaPipe framework and extract the regions of interest (ROI). The processed cropped image is then passed to the Inception-v3 for the 2D feature extractor. Finally, a long short-term memory (LSTM) network is used as a temporal feature extractor and classifier. Our proposed method achieves an average accuracy of more than 89.7%. The experimental results also show that the proposed framework outperforms existing state-of-the-art methods.

RS-Xception: A Lightweight Network for Facial Expression Recognition

Facial expression recognition (FER) utilizes artificial intelligence for the detection and analysis of human faces, with significant applications across various scenarios. Our objective is to deploy the facial emotion recognition network on mobile devices and extend its application to diverse areas, including classroom effect monitoring, human–computer interaction, specialized training for athletes (such as in figure skating and rhythmic gymnastics), and actor emotion training. Recent studies have employed advanced deep learning models to address this task, though these models often encounter challenges like subpar performance and an excessive number of parameters that do not align with the requirements of FER for embedded devices. To tackle this issue, we have devised a lightweight network structure named RS-Xception, which is straightforward yet highly effective. Drawing on the strengths of ResNet and SENet, this network integrates elements from the Xception architecture. Our models have been trained on FER2013 datasets and demonstrate superior efficiency compared to conventional network models. Furthermore, we have assessed the model’s performance on the CK+, FER2013, and Bigfer2013 datasets, achieving accuracy rates of 97.13%, 69.02%, and 72.06%, respectively. Evaluation on the complex RAF-DB dataset yielded an accuracy rate of 82.98%. The incorporation of transfer learning notably enhanced the model’s accuracy, with a performance of 75.38% on the Bigfer2013 dataset, underscoring its significance in our research. In conclusion, our proposed model proves to be a viable solution for precise sentiment detection and estimation. In the future, our lightweight model may be deployed on embedded devices for research purposes.

FQTrack:Object Tracking Method Based on a Feature-Enhanced Memory Network and Memory Quality Selection Mechanism

Visual object tracking technology is widely used in intelligent security, automatic driving and other fields, and also plays an important role in frontier fields such as human–computer interactions and virtual reality. The memory network improves the stability and accuracy of tracking by using historical frame information to assist in the positioning of the current frame in object tracking. However, the memory network is still insufficient in feature mining and the accuracy and robustness of the model may be reduced when using noisy observation samples to update it. In view of the above problems, we propose a new tracking framework, which uses the attention mechanism to establish a feature-enhanced memory network and combines cross-attention to aggregate the spatial and temporal context information of the target. The former introduces spatio-temporal adaptive attention and cross-spatial attention, embeds spatial location information into channels, realizes multi-scale feature fusion, dynamically emphasizes target location information, and obtains richer feature maps. The latter guides the tracker to focus on the area with the largest amount of information in the current frame to better distinguish the foreground and background. In addition, through the memory quality selection mechanism, the accuracy and richness of the feature samples are improved, thereby enhancing the adaptability and discrimination ability of the tracking model. Experiments on benchmark test sets such as OTB2015, TrackingNet, GOT-10k, LaSOT and UAV 123 show that this method achieves comparable performance with advanced trackers.

Emotion recognition using hierarchical spatial–temporal learning transformer from regional to global brain

Emotion recognition is an essential but challenging task in human–computer interaction systems due to the distinctive spatial structures and dynamic temporal dependencies associated with each emotion. However, current approaches fail to accurately capture the intricate effects of electroencephalogram (EEG) signals across different brain regions on emotion recognition. Therefore, this paper designs a transformer-based method, denoted by R2G-STLT, which relies on a spatial–temporal transformer encoder with regional to global hierarchical learning that learns the representative spatiotemporal features from the electrode level to the brain-region level. The regional spatial–temporal transformer (RST-Trans) encoder is designed to obtain spatial information and context dependence at the electrode level aiming to learn the regional spatiotemporal features. Then, the global spatial–temporal transformer (GST-Trans) encoder is utilized to extract reliable global spatiotemporal features, reflecting the impact of various brain regions on emotion recognition tasks. Moreover, the multi-head attention mechanism is placed into the GST-Trans encoder to empower it to capture the long-range spatial–temporal information among the brain regions. Finally, subject-independent experiments are conducted on each frequency band of the DEAP, SEED, and SEED-IV datasets to assess the performance of the proposed model. Results indicate that the R2G-STLT model surpasses several state-of-the-art approaches.

Rechargeable Self-Powered pressure sensor based on Zn-ion battery with high sensitivity and Broad-Range response

Flexible pressure sensors find broad applications in electronic skin, human–computer interaction, and health monitoring. However, developing self-powered flexible sensors capable of detecting both dynamic and static pressures with high sensitivity and a wide detection range remains a significant challenge. Here, we report the design and fabrication of a new rechargeable Zn-ion battery-type flexible self-powered pressure sensor (RZIB-FPS). In the device, the anode of a flexible Zn-ion battery is designed into a sandwich configuration with a porous isolation layer in between a conductive layer decorated with polymethylmethacrylate microspheres and a flexible Zn electrode. The self-powered pressure sensing mechanism relies on the variation in output voltage resulting from the resistance change of the anode when subjected to external pressure. This RZIB-FPS exhibits an open-circuit voltage of 1.46 V, an energy density of 392 µWh cm−2, a high sensitivity (up to 42.6 mV kPa−1), a wide pressure detection range (up to 330 kPa), and excellent cycling stability (up to 12,000 cycles). Furthermore, the proposed all-in-one device design demonstrates excellent charge–discharge performance, manifesting its high integration level and potential for sensor miniaturization. This study introduces a new strategy for developing high-performance sensors for future self-powered smart wearable electronics.

Nanocellulose and multi-walled carbon nanotubes reinforced polyacrylamide/sodium alginate conductive hydrogel as flexible sensor

Conductive hydrogels have been widely applied in human–computer interaction, tactile sensing, and sustainable green energy harvesting. Herein, a double cross-linked network composite hydrogel (MWCNTs/CNWs/PAM/SA) by constructing dual enhancers acting together with PAM/SA was constructed. By systematically optimizing the compositions, the hydrogel displayed features advantages of good mechanical adaptability, high conductivity sensitivity (GF = 5.65, 53 ms), low hysteresis (<11 %), and shape memory of water molecules and temperature. The nanocellulose crystals (CNWs) were bent and entangled with the backbone of the polyacrylamide/ sodium alginate (PAM/SA) hydrogel network, which effectively transferred the external mechanical forces to the entire physical and chemical cross-linking domains. Multi-walled carbon nanotubes (MWCNTs) were filled into the cross-linking network of the hydrogel to enhance the conductivity of the hydrogel effectively. Notably, hydrogels are designed as flexible tactile sensors that can accurately recognize and monitor electrical signals from different gesture movements and temperature changes. It was also assembled as a friction nanogenerator (TENG) that continuously generates a stable open circuit voltage (28 V) for self-powered small electronic devices. This research provides a new prospect for designing nanocellulose and MWCNTs reinforced conductive hydrogels via a facile method.

Optimal condition design of cannabis drying for vacuum heat pump dryer using computational fluid dynamic method interaction with heat transfer

Utilizing low temperatures and short drying cycles, the vacuum heat pump dryer (VHPD) is ideal for cannabis drying due to the plant's sensitivity to heat and light. To achieve uniform drying and maintain cannabis quality, it is essential to design the dryer with an efficient temperature distribution throughout the drying chamber. CFD models are developed in this study to simulate various scenarios within the VHPD system. The optimization of pressure and temperature is carried out using a systematic approach with the Latin Hypercube Sampling experimental design. This method generates twenty pairs of values for the pressure and temperature variables, confined to ranges of 20–40 kPa and 30–45 °C, respectively. To confirm the simulation results, an experimental study is performed using a VHPD designed from insights gained through a detailed CFD analysis. The conditions of 20.2 kPa at 31.6 °C are considered optimal due to their more uniform temperature distribution and lower static enthalpy relative to other conditions. The temperature in the upper chamber is maintained slightly lower, within the range of 30.5–31.5 °C. Furthermore, the airflow distribution demonstrates uniform movement within the central region of the chamber, with velocities ranging from 2.5 to 3.5 m/s. The simulated temperature results demonstrated a strong correlation with a temperature difference in the range of 0–0.05 °C, evidenced by an RMSE of 0.0191. The VHPD successfully dries 18 kg of fresh cannabis in 180 min, reaching the desired moisture content range of 10–14 % on a dry basis.

Wearable high-density EMG sleeve for complex hand gesture classification and continuous joint angle estimation

High-density electromyography (HD-EMG) can provide a natural interface to enhance human–computer interaction (HCI). This study aims to demonstrate the capability of a novel HD-EMG forearm sleeve equipped with up to 150 electrodes to capture high-resolution muscle activity, decode complex hand gestures, and estimate continuous hand position via joint angle predictions. Ten able-bodied participants performed 37 hand movements and grasps while EMG was recorded using the HD-EMG sleeve. Simultaneously, an 18-sensor motion capture glove calculated 23 joint angles from the hand and fingers across all movements for training regression models. For classifying across the 37 gestures, our decoding algorithm was able to differentiate between sequential movements with 97.3±0.3%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$97.3 \\pm 0.3\\%$$\\end{document} accuracy calculated on a 100 ms bin-by-bin basis. In a separate mixed dataset consisting of 19 movements randomly interspersed, decoding performance achieved an average bin-wise accuracy of 92.8±0.8%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$92.8 \\pm 0.8\\%$$\\end{document}. When evaluating decoders for use in real-time scenarios, we found that decoders can reliably decode both movements and movement transitions, achieving an average accuracy of 93.3±0.9%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$93.3 \\pm 0.9\\%$$\\end{document} on the sequential set and 88.5±0.9%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$88.5 \\pm 0.9\\%$$\\end{document} on the mixed set. Furthermore, we estimated continuous joint angles from the EMG sleeve data, achieving a R2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$R^2$$\\end{document} of 0.884±0.003\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$0.884 \\pm 0.003$$\\end{document} in the sequential set and 0.750±0.008\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$0.750 \\pm 0.008$$\\end{document} in the mixed set. Median absolute error (MAE) was kept below 10° across all joints, with a grand average MAE of 1.8±0.04∘\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$1.8 \\pm 0.04^\\circ$$\\end{document} and 3.4±0.07∘\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$3.4 \\pm 0.07^\\circ$$\\end{document} for the sequential and mixed datasets, respectively. We also assessed two algorithm modifications to address specific challenges for EMG-driven HCI applications. To minimize decoder latency, we used a method that accounts for reaction time by dynamically shifting cue labels in time. To reduce training requirements, we show that pretraining models with historical data provided an increase in decoding performance compared with models that were not pretrained when reducing the in-session training data to only one attempt of each movement. The HD-EMG sleeve, combined with sophisticated machine learning algorithms, can be a powerful tool for hand gesture recognition and joint angle estimation. This technology holds significant promise for applications in HCI, such as prosthetics, assistive technology, rehabilitation, and human–robot collaboration.

Automatic Age and Gender Recognition Using Ensemble Learning

The use of speech-based recognition technologies in human–computer interactions is increasing daily. Age and gender recognition, one of these technologies, is a popular research topic used directly or indirectly in many applications. In this research, a new age and gender recognition approach based on the ensemble of different machine learning algorithms is proposed. In the study, five different classifiers, namely KNN, SVM, LR, RF, and E-TREE, are used as base-level classifiers and the majority voting and stacking methods are used to create the ensemble models. First, using MFCC features, five base-level classifiers are created and the performance of each model is evaluated. Then, starting from the one with the highest performance, these classifiers are combined and ensemble models are created. In the study, eight different ensemble models are created and the performances of each are examined separately. The experiments conducted with the Turkish subsection of the Mozilla Common Voice dataset show that the ensemble models increase the recognition accuracy, and the highest accuracy of 97.41% is achieved with the ensemble model created by stacking five classifiers (SVM, E-TREE, RF, KNN, and LR). According to this result, the proposed ensemble model achieves superior accuracy compared to similar studies in recognizing age and gender from speech signals.

Responsible Automation: Exploring Potentials and Losses through Automation in Human–Computer Interaction from a Psychological Perspective

Responsible Automation: Exploring Potentials and Losses through Automation in Human–Computer Interaction from a Psychological Perspective

A lightweight and continuous dimensional emotion analysis system of facial expression recognition under complex background

Facial expression recognition technology has a brilliant prospect in applying the Internet of Things systems. Concerning the limited hardware computing capability and high real-time processing requirements, this paper proposes a lightweight emotion analysis system based on edge computing, which could be deployed on edge devices. To further improve the accuracy of dimensional emotion analysis, we propose a modified network structure of MobileNetV3 to measure the intensity of dimensional emotion. The optimization scheme includes introducing the improved efficient channel attention mechanism and the feature pyramid network, adjusting the structure of the model, and optimizing the loss function. Furthermore, the system uses Intel’s OpenVINO toolkit to make the model more suitable for stable operation and provides an operable human–computer interaction interface. The experimental results show that the system has the advantages of few parameters, high recognition accuracy, and low latency. The optimized network size is reduced by 67% compared with the original, the root mean square error of potency and activation is 0.413 and 0.389, and the latency is up to 9ms in Myriad. This work meets the requirements of practical applications and has essential significance with the demand for continuous dimensional emotion analysis. The source code is available at https://github.com/SCNU-RISLAB/Lightweight-and-Continuous-Dimensional-Emotion-Analysis-System-of-Facial-Expression-Recognition/.