Interactive Applications Research Articles

Bidirectional Service Function Chain Embedding for Interactive Applications in Mobile Edge networks

Bidirectional service function chain (BSFC) consists of multiple virtual network functions (VNFs). Through VNF deployment and link mapping, BSFCs can be embedded into resource-constrained mobile edge networks to provide low-latency network function services to users participating in interactive applications such as multi-player online games. Data from these users are routed through BSFCs to the edge node where the application is located for interaction and then returned to the users through the BSFCs, thus enabling synchronization among multiple users. However, the edge nodes or links have limited computing or bandwidth resources to serve only a fraction of users simultaneously. Therefore, the embedding decisions among different users can affect each other. In this paper, we propose a novel BSFC embedding strategy for interactive applications with the goal of minimizing computing and bandwidth resources while satisfying users' latency requirements. We first model the BSFC embedding problem as an integer nonlinear programming problem. Then, by closely examining the complexity of the problem, we propose a distributed algorithm based on game theory. We theoretically analyze the properties of the proposed algorithm and show that it can obtain a solution with a worst-case performance bound. Finally, extensive experiments show that the proposed algorithm outperforms several existing algorithms.

CSINet: Channel–Spatial Fusion Networks for Asymmetric Facial Expression Recognition

Occlusion or posture change of the face in natural scenes has typical asymmetry; however, an asymmetric face plays a key part in the lack of information available for facial expression recognition. To solve the problem of low accuracy of asymmetric facial expression recognition, this paper proposes a fusion of channel global features and a spatial local information expression recognition network called the “Channel–Spatial Integration Network” (CSINet). First, to extract the underlying detail information and deepen the network, the attention residual module with a redundant information filtering function is designed, and the backbone feature-extraction network is constituted by module stacking. Second, considering the loss of information in the local key area of face occlusion, the channel–spatial fusion structure is constructed, and the channel features and spatial features are combined to enhance the accuracy of occluded facial recognition. Finally, before the full connection layer, more local spatial information is embedded into the global channel information to capture the relationship between different channel–spatial targets, which improves the accuracy of feature expression. Experimental results on the natural scene facial expression data sets RAF-DB and FERPlus show that the recognition accuracies of the modeling approach proposed in this paper are 89.67% and 90.83%, which are 13.24% and 11.52% higher than that of the baseline network ResNet50, respectively. Compared with the latest facial expression recognition methods such as CVT, PACVT, etc., the method in this paper obtains better evaluation results of masked facial expression recognition, which provides certain theoretical and technical references for daily facial emotion analysis and human–computer interaction applications.

Web Real-Time Communication Using Gesture

Gesture recognition has emerged as a promising technology for enhancing human-computer interaction in various domains. In this paper, we propose a novel approach to gesture recognition using WebRTC (Web Real-Time Communication), a powerful web technology that enables real-time communication between web browsers. Our approach leverages the capabilities of WebRTC to capture live video streams from webcams and process them in real-time for gesture recognition. We present a detailed methodology for integrating WebRTC with a custom deep learning techniques. We evaluate the performance of our system using a diverse set of hand gestures and demonstrate its effectiveness in real-world scenarios. Our experimental results show an average recognition accuracy of 90%, outperforming existing methods in terms of both accuracy and computational efficiency. Potential applications of our approach in interactive web applications, gaming, and augmented reality systems. This work contributes the research on gesture recognition and demonstrates the feasibility of using WebRTC for real-time gesture recognition applications. Key Words: gesture recognition, WebRTC , Real-time communication

Improving Speech Recognition with Convolutional Neural Networks

This project explores advanced techniques in speech recognition, focusing on emotion identification using Convolutional Neural Networks for improved accuracy and real-time processing efficiency. Emotion recognition from speech signals plays a crucial role in various applications, including human-computer interaction, customer service, mental health monitoring, and entertainment. This project proposes an innovative approach to emotion recognition using Convolutional Neural Networks (CNNs) applied to speech data. By leveraging advanced deep learning techniques, the proposed system aims to accurately identify and classify emotions conveyed through vocal expressions. The project begins with a comprehensive review of existing literature on emotion recognition and speech processing, identifying key challenges and opportunities in the field. Building upon prior research, the project introduces a novel CNN architecture optimized for emotion recognition tasks. This architecture is designed to extract relevant features from speech signals and capture subtle nuances indicative of different emotional states. One of the distinguishing features of the proposed approach is its multi-modal integration, which combines information from both audio and visual modalities to enhance emotion recognition accuracy. In addition to analysing speech signals, the system incorporates visual cues such as facial expressions and gestures, providing a more comprehensive understanding of the speaker's emotional state. Real-time processing efficiency is prioritized in the design of the system, ensuring prompt and responsive emotion recognition in interactive applications. Optimization techniques such as model quantization and lightweight architecture design are employed to minimize computational overhead while maintaining high accuracy. To address the variability and subjectivity of emotional expression, the system incorporates user-specific adaptation mechanisms. Through continuous learning and feedback integration, the system dynamically adapts to individual speakers' speech patterns and emotional characteristics, enhancing its ability to accurately recognize emotions in diverse contexts. The project also explores ensemble learning strategies to improve robustness and generalization performance. By combining predictions from multiple CNN models trained on diverse datasets, the system achieves greater resilience to variations in emotional expression and environmental factors. Ethical considerations, including privacy protection and responsible data handling, are integral aspects of the project's design and implementation. Measures are implemented to ensure the ethical collection, storage, and usage of speech data, safeguarding user privacy and maintaining trust in the system. Overall, the proposed system represents a significant advancement in emotion recognition technology, offering a sophisticated and versatile solution for accurately identifying emotions from speech signals. By leveraging deep learning techniques, multi-modal integration, real-time processing optimization, user-specific adaptation, and ensemble learning, the system demonstrates promising potential for various practical applications requiring robust and context-aware emotion recognition capabilities. Keywords: Speech Recognition, Emotion Identification, Convolutional Neural Networks (CNNs), Real-time Processing, Multi-modal Integration, User-specific Adaptation, Ensemble Learning, Deep Learning, Emotional Expression, Ethical Data Handling

Ultrasensitive Biomimetic Skin with Multimodal and Photoelectric Dual-Signal Sensing.

Mimicking biological skin enabling direct, intelligent interaction between users and devices, multimodal sensing with optical/electrical (OE) output signals is urgently required. Owing to this, this work aims to logically design a stretchable OE biomimetic skin (OE skin), which can sensitively sense complex external stimuli of pressure, strain, temperature, and localization. The OE skin consists of elastic thin polymer-stabilized cholesteric liquid crystal films, an ion-conductive hydrogel layer, and an elastic protective membrane formed with thin polydimethylsiloxane. The as-designed OE skin exhibits customizable structural color on demand, good thermochromism, and excellent mechanochromism, with the ability to extend the full visible spectrum, a good linearity of over 0.99, fast response speed of 93 ms, and wide temperature range of 119 °C. In addition, the conduction resistance variation of ion-conductive hydrogel exhibits excellent sensing capabilities under pressure, stretch, and temperature, endowing a good linearity of 0.99998 (stretching from 0 to 150%) and high thermal sensitivity of 0.86% per °C. Such an outstanding OE skin provides design concepts for the development of multifunctional biomimetic skin used in human-machine interaction and can find wide applications in intelligent wearable devices and human-machine interactions.

Design and Optimization of Human-Computer Interaction System for Education Management Based on Artificial Intelligence

The continuous improvement and refinement of artificial intelligence (AI) technology has facilitated the broader application of human-computer interaction in the field of education management. The construction of an educational management human-computer interaction system based on AI technology can optimize and improve key parameters of educational management human-computer interaction scenarios, thereby creating a more comprehensive mobile learning (m-learning) application system. This paper is based on AI technology, analyzing gesture semantics and speech semantics, and combining fusion algorithms to construct an education management human interaction system. The performance changes of the system were compared with real experimental operations and the NOBOOK platform analysis. The results show that the education management human-computer interaction system constructed in this article can enhance the m-learning experience of participants. It ensures high recognition accuracy, leading to higher scores in all dimensions of indicator evaluation. Therefore, as one of the crucial forms of m-learning, the human-computer interaction system for education management based on AI can establish a foundation for the further enhancement and development of education management.

Epidemiology and Healthcare Expenditure for Skin Disease in Emergency Departments in Alberta, Canada.

There are limited data on the epidemiology and costs associated with managing dermatologic conditions in emergency departments (EDs). To assess the incidence and mean cost per case of skin diseases in EDs in Alberta. Alberta Health Services' Interactive Health Data Application was used to determine the epidemiology and costs associated with nonneoplastic dermatologic diseases in EDs in the province of Alberta, Canada, from 2018 to 2022. Skin conditions were identified using the International Classification of Disease 10th edition diagnostic groupings. Skin disease represented 3.59% of all ED presentations in Alberta in 2022. The total costs associated with managing dermatologic conditions have remained stable over time at approximately 15 million Canadian Dollars (CAD) annually, but the mean cost per case has risen from 188.88 (SD 15.42) in 2018 to 246.25 CAD (SD 27.47) in 2022 (7.59%/year). Infections of skin and subcutaneous tissue were the most expensive diagnostic grouping. The most common dermatologic diagnostic groupings presenting to the ED were infections of skin and subcutaneous tissue [mean age-standardized incidence rate (ASIR) of 143.67 per 100,000 standard population (SD 241.99)], urticaria and erythema [mean ASIR 33.57 per 100,000 standard population (SD 59.13)], and dermatitis and eczema [mean ASIR 18.59 per 100,000 standard population (SD 23.65)]. Cellulitis was both the most common and the costliest individual diagnosis. The majority of patients were triaged as less urgent or nonurgent. Skin disease represents a substantial public health burden in EDs. Further research into drivers of cost change and areas for cost savings is essential.

Construction and application of interactive platform of art design based on multimedia technology

Contemporary art design not only pursues the quality of the work itself, but also pays attention to the sensory aspects of people’s needs for art design. Traditional art design methods can be limited by time, space and other objective conditions, and often fail to achieve the designer’s expected effect, and visitors’ experience is not strong. The usage of multimedia technology in art and design can enrich its expression and enhance visitors’ experience. In order to increase the sense of interaction between the platform and users, multimedia technology is incorporated into the interactive art design platform generated by VR technology in this paper. This article combines multimedia technology with interactive technology to construct an interactive platform for art and design, and applies it to the display of Dunhuang murals. Through the analysis of user experience feedback, the effectiveness of art and design display and interaction is verified. Display and interact with Dunhuang murals as interactive platform applications. This test is to extract women’s clothing colors from the same tradition in different times in the color extraction exploration module of the interactive platform, so as to provide accurate information for displaying women’s clothing color changes and comparing interactions. The findings show that the platform is capable of extracting and recognizing the color characteristics of the murals, accurately identifying user signals, and noticing 3D modeling of images via VR technology. This capability provides solid technical and data support for the platform’s interaction module. The interaction design, platform functionality, and layout can support the majority of users in terms of cognition, perception, and interaction, pique their interest, and enhance their experience, according to evaluation of trial user information. The interaction ends abruptly, according to a small percentage of users, and they had a bad experience overall.

Remote practical instruction using web browsers

<p>This paper introduces a novel approach to remote coaching, specifically targeting the body movements of learners participating remotely. The proposed system employs a smartphone camera to capture the learner’s body and represent it as a 3D avatar. The instructor can then offer guidance and instruction by manipulating the 3D avatar’s shape, which is displayed on a web browser. The main challenge faced by the system is to enable the sharing and editing of 3D objects among users. Since the HTML5 drag-and-drop feature is inadequate for transforming virtual objects consisting of multiple interconnected rigid bodies, the system tracks the pivot point of the manipulated rigid body. It assigns attributes such as pivot points and action points to each object, extending beyond their 2D screen coordinates. To implement the system, an interactive web application framework following the model-view-view-model (MVVM) architecture is utilized, incorporating Vue.js, Three.js, and Google Firebase. The prototype system takes advantage of the data binding capability of the framework and successfully operates within the 3D space of a web browser. Experimental results demonstrate that it can effectively share transformation information with an average delay of 300 ms.</p>

ПІДВИЩЕННЯ ЯКОСТІ НАВЧАННЯ ТА ПІДГОТОВКИ ДО НАДЗВИЧАЙНИХ СИТУАЦІЙ ЗА ДОПОМОГОЮ ВЕБ-САЙТУ "BE READY"

The article discusses the growing popularity of using artificial intelligence for creating websites and applications. It also highlights the importance of knowledge about behavior in emergency situations, especially in a country like Ukraine, which is experiencing a war. The article mentions the "Be Ready" project, which was developed during the SHEBUILDS UKRAINE hackathon by the Asterisks ITS team. The project is an interactive web application with a comic-quest feature aimed at providing users with the necessary information and materials to prepare for emergency situations effectively. The article further the tools and technologies used to develop the project, including Angular.js, Typescript, and Photoshop. The "Be Ready" project includes a set of tools to help users create an action plan for emergency situations and access useful information about different types of emergency situations. Overall, the article emphasizes the significance of using modern technologies and educational tools to prepare for emergency situations effectively.

EndoGeneAnalyzer: A tool for selection and validation of reference genes.

The selection of proper reference genes is critical for accurate gene expression analysis in all fields of biological and medical research, mainly because there are many distinctions between different tissues and specimens. Given this variability, even in known classic reference genes, demands of a comprehensive analysis platform is needed to identify the most suitable genes for each study. For this purpose, we present an analysis tool for assisting in decision-making in the analysis of reverse transcription-quantitative polymerase chain reaction (RT-qPCR) data. EndoGeneAnalyzer, an open-source web tool for reference gene analysis in RT-qPCR studies, was used to compare the groups/conditions under investigation. This interactive application offers an easy-to-use interface that allows efficient exploration of datasets. Through statistical and stability analyses, EndoGeneAnalyzer assists in the select of the most appropriate reference gene or set of genes for each condition. It also allows researchers to identify and remove unwanted outliers. Moreover, EndoGeneAnalyzer provides a graphical interface to compare the evaluated groups, providing a visually informative differential analysis.

Examining the factors fostering metaverse experience browser acceptance under unified theory of acceptance and use of technology (UTAUT)

Metaverse technology has various uses in communication, education, entertainment, and other aspects of life. Consequently, it necessitates using some interactive mobile applications to enter the virtual world and gain real-time, face-to-face experiences, particularly among students. This research focused on the factors accelerating metaverse technology acceptance particularly, Metaverse Experience Browser application acceptance among the students under the factors proposed by the unified theory of acceptance and use of technology (UTAUT) model. Notably, lack of studies in metaverse browsers and their prevalence during the post pandemic era, indicates a strong literature gap. The researchers gathered data from n = 384 higher education students from the two cities in the United Arab Emirates and applied Structural Equation modelling (SEM) for data analysis. Results revealed that Performance Expectancy (p < 0.003) and Social Influence (p = 0.000) were significant factors affecting the Behavioral Intention of the students to consider Metaverse Experience Browser as an interactive mobile application. On the other hand, behavioural Intention significantly affects (p = 0.000) Effort Expectancy, which shows how fewer efforts and greater accessibility are associated with one’s behavioural Intention. Besides, the effect of Behavioral Intention (p = 0.000) on Metaverse Experience Browser acceptance also remained validated. Finally, Effort Expectancy (p = 0.000) also indicated its significant effect on the Metaverse Experience Browser. These results indicated that the factors proposed by UTAUT have greater applicability on the Metaverse Experience Browser as they showed their relevance to its acceptance. The present study concludes that the acceptance of Metaverse Experience Browser as an interactive mobile application is a level ahead in improving students’ experiences. Thus, the Metaverse Experience Browser is considered a modified way of creating, sharing, participating, and enjoying the virtual world, indicating its greater usage among students for different purposes, including education and learning.

Diving into CDC pregnancy data in the United States: longitudinal study and interactive application.

Preterm birth (PTB) is a major determinant of neonatal mortality, morbidity, and childhood disability. In this article, we present a longitudinal analysis of the risk factors associated with PTB and how they have varied over the years: starting from 1968 when the CDC first started, reporting the natality data, up until 2021. Along with this article, we are also releasing an RShiny web application that will allow for easy consumption of this voluminous dataset by the research community. Further, we hope this tool can aid clinicians in the understanding and prevention of PTB. This study used the CDC Natality data from 1968 to 2021 to analyze trends in PTB outcomes across the lens of various features, including race, maternal age, education, and interval length between pregnancies. Our interactive RShiny web application, CDC NatView, allows users to explore interactions between maternal risk factors and maternal morbidity conditions and the aforementioned features. Our study demonstrates how CDC data can be leveraged to conduct a longitudinal analysis of natality trends in the United States. Our key findings reveal an upward trend in late PTBs, which is concerning. Moreover, a significant disparity exists between African American and White populations in terms of PTB. These disparities persist in other areas, such as education, body-mass index, and access to prenatal care later in pregnancy. Another notable finding is the increase in maternal age over time. Additionally, we confirm that short interpregnancy intervals (IPIs) are a risk factor for PTBs. To facilitate the exploration of pregnancy risk factors, infections, and maternal morbidity, we developed an open-source RShiny tool called CDC NatView. This software offers a user-friendly interface to interact with and visualize the CDC natality data, which constitutes an invaluable resource. In conclusion, our study has shed light on the rise of late PTBs and the persistent disparities in PTB rates between African American and White populations in the US. The increase in maternal age and the confirmation of a short IPI as a risk factor for PTB are noteworthy findings. Our open-source tool, CDC NatView, can be a valuable resource for further exploration of the CDC natality data to enhance our understanding of pregnancy risk factors and the interaction of PTB outcomes and maternal morbidities.

Designable high-performance TPU foam strain sensors towards human-machine interfaces

Flexible, breathable, and stable sensors were important in developing human–computer interaction systems and novel wearable devices. However, major challenges were still faced in two aspects, 1) high-performance strain sensors with a large sensing range, and 2) an interaction mode that is both convenient and efficient. Herein, we developed a thermoplastic polyurethane large-skeleton foam (TPU-LS foam) through a steam-induced method. The strain sensor comprised three layers of breathable foam, with CNTs/rGO TPU-LS foam as the inner layer and pure foam as the protective layer. PDMS/TiO2 was sprayed to create a UV-resistant and self-repairing coating, achieving a 66% melanin inhibition rate and a 91% repair rate. The sensor presented a wide work range over 100%, a high gauge factor of 637.8, and long-term durability. We trained machine learning frameworks to recognize different gestures and designed two types of human–computer interaction applications, allowing users to operate apps with gestures.

Offloading Decision and Resource Allocation in Mobile Edge Computing for Cost and Latency Efficiencies in Real-Time IoT

Internet of Things (IoT) devices can integrate with applications requiring intensive contextual data processing, intelligent vehicle control, healthcare remote sensing, VR, data mining, traffic management, and interactive applications. However, there are computationally intensive tasks that need to be completed quickly within the time constraints of IoT devices. To address this challenge, researchers have proposed computation offloading, where computing tasks are sent to edge servers instead of being executed locally on user devices. This approach involves using edge servers located near users in cellular network base stations, and also known as Mobile Edge Computing (MEC). The goal is to offload tasks to edge servers, optimizing both latency and energy consumption. The main objective of this paper mentioned in the summary is to design an algorithm for time- and energy-optimized task offloading decision-making in MEC environments. Therefore, we developed a Lagrange Duality Resource Optimization Algorithm (LDROA) to optimize for both decision offloading and resource allocation for tasks, whether to locally execute or offload to an edge server. The LDROA technique produces superior simulation outcomes in terms of task offloading, with improved performance in computation latency and cost usage compared to conventional methods like Random Offloading, Load Balancing, and the Greedy Latency Offloading scheme.

Sentiment analysis on a low-resource language dataset using multimodal representation learning and cross-lingual transfer learning

Affect Sensing is a rapidly growing field with the potential to revolutionize human–computer interaction, healthcare, and many more applications. Multimodal Sentiment Analysis (MSA) is a recent research area that exploits the multimodal nature of video data for affect sensing. However, the success of a multimodal framework depends on addressing the challenges associated with integrating diverse modalities and selecting informative features. We propose a novel multimodal representation learning framework using multimodal autoencoders that learns a comprehensive representation of the underlying heterogeneous modalities. Affect Sensing is even more challenging in low-resource languages because annotated video datasets and language-specific models are limited. To address this concern, we introduce Multimodal Sentiment Analysis Corpus in Tamil (MSAT), a small-sized dataset in the Tamil language for MSA, and exhibit how a novel technique involving cross-lingual transfer learning in a multimodal setting, leverages the knowledge gained by training the model on a larger English MSA dataset to fine-tune a much smaller Tamil MSA dataset. Our transfer learning model achieves significant gain in the Tamil dataset by a large margin. Our experiments demonstrate that we can build efficient, generalized models for low-resource languages by using the existing MSA datasets.

A Study On The Usage Of M-Learning Applications Within Bulgarian Schools

The transformation of the educational model is directly linked to the key participants in the educational process. Modern pupils cannot imagine life without the usage of various digital technologies such as mobile devices. Moreover, today’s learners spend more time preparing for school using interactive mobile applications. That defines the purpose of this article: to explore the usage of m-learning applications in the educational process within Bulgarian schools. To achieve that it has been created a survey that consists of 11 questions and was distributed to 140 participants (pupils from Bulgarian schools). The results have shown that 54.28% of respondents use m-learning applications within the classroom and 72.86% of them use m-learning applications for self-study. Additionally, 60% of respondents believe that using such applications would enhance the educational process. This provides ample justification for directing efforts from all stakeholders (educational institutions, educators, and learners) toward wider and more comprehensive integration of these applications in the educational process. From the perspective of future research, there could be endeavors to conduct a more extensive and representative study by trying to utilize cluster sampling in order to overcome the limitations posed by the current research methodology.

INFORMEDQX: Informed Conflict Detection for Over-Constrained Problems

Conflict detection is relevant in various application scenarios, ranging from interactive decision-making to the diagnosis of faulty knowledge bases. Conflicts can be regarded as sets of constraints that cause an inconsistency. In many scenarios (e.g., constraint-based configuration), conflicts are repeatedly determined for the same or similar sets of constraints. This misses out on the valuable opportunity for leveraging knowledge reuse and related potential performance improvements, which are extremely important, specifically interactive constraint-based applications. In this paper, we show how to integrate knowledge reuse concepts into non-instructive conflict detection. We introduce the InformedQX algorithm, which is a reuse-aware variant of QuickXPlain. The results of a related performance analysis with the Linux-2.6.3.33 configuration knowledge base show significant improvements in terms of runtime performance compared to QuickXPlain.

Hand Gesture Gaming

Hand gesture recognition has emerged as a promising interface for interactive gaming applications, offering intuitive and immersive experiences. This research paper explores the development and implementation of a hand gesture recognition system using Python for gaming purposes. The study investigates various machine learning techniques, particularly convolutional neural networks (CNNs), for accurate detection and classification of hand gestures from video input. The research methodology involves collecting a diverse dataset of hand gesture samples, encompassing common gaming gestures such as swipes, taps, and rotations. Preprocessing techniques are employed to enhance the quality and consistency of the dataset. Subsequently, deep learning architectures, including CNNs, are trained on the dataset to recognize and classify hand gestures in real-time.

Individual-finger motor imagery classification: a data-driven approach with Shapley-informed augmentation

Objective. Classifying motor imagery (MI) tasks that involve fine motor control of the individual five fingers presents unique challenges when utilizing electroencephalography (EEG) data. In this paper, we systematically assess the classification of MI functions for the individual five fingers using single-trial time-domain EEG signals. This assessment encompasses both within-subject and cross-subject scenarios, supported by data-driven analysis that provides statistical validation of the neural correlate that could potentially discriminate between the five fingers. Approach. We present Shapley-informed augmentation, an informed approach to enhance within-subject classification accuracy. This method is rooted in insights gained from our data-driven analysis, which revealed inconsistent temporal features encoding the five fingers MI across sessions of the same subject. To evaluate its impact, we compare within-subject classification performance both before and after implementing this augmentation technique. Main results. Both the data-driven approach and the model explainability analysis revealed that the parietal cortex contains neural information that helps discriminate the individual five fingers’ MI apart. Shapley-informed augmentation successfully improved classification accuracy in sessions severely affected by inconsistent temporal features. The accuracy for sessions impacted by inconsistency in their temporal features increased by an average of 26.3%±6.70 , thereby enabling a broader range of subjects to benefit from brain–computer interaction (BCI) applications involving five-fingers MI classification. Conversely, non-impacted sessions experienced only a negligible average accuracy decrease of 2.01±5.44% . The average classification accuracy achieved is around 60.0% (within-session), 50.0% (within-subject) and 40.0% (leave-one-subject-out). Significance. This research offers data-driven evidence of neural correlates that could discriminate between the individual five fingers MI and introduces a novel Shapley-informed augmentation method to address temporal variability of features, ultimately contributing to the development of personalized systems.