Development and Evaluation of a Serious Game-Based Exercise Therapy System for Sarcopenia Using Pose Recognition Technology

Based on image recognition technology, a method of defect detection for cigarette packet seal sticker is proposed in this paper. Based on the proposed method, a defect detection system for cigarette packet seal has been developed. The captured image with CCD can be filtered and its edge can also be extracted with the developed system. The Radon transform was applied to detect the position and angle of the straight line of the extracted edge. Support vector data description with Gaussian kernel was applied to classify the defective packet seal stickers based on the feature of the captured image. The cigarette packet with seal defection can be detected and pushed out of the production line with the developed system. The long term application results in one factory of China Tobacco have verified the effectiveness and precision of the proposed method and the developed system.

This paper introduces a hybrid system for vehicle access control using RFID and automatic license plate recognition (ALPR) technologies. RFID technology is proven to provide an effective solution to different tracking and localization problems. However, the technology has its shortcomings in tracking objects/users without a tag. As such, we propose to complement this technology with ALPR to control the access of different types of vehicles to the area of Makkah (Saudi Arabia) during Pilgrimage seasons. This limited area can easily get congested with the huge number of vehicles attempting access. Before the start of the season, vehicles authorized to access the region are assigned passive RFID tags specifying their allowed schedule of entry. Violating vehicles that do not have RFID tags are detected and identified using ALPR. The developed system was tested over two pilgrimage seasons. The experiments showed that the developed RFID system was able to identify all passing vehicles with speeds up to 100 km/h, while the ALPR system achieved 94 % recognition accuracy of vehicles not equipped with RFID tags.

The test system is designed for the MDU unit of the airborne display and control subsystem, and the test software is developed based on LabVIEW. The CNN image recognition and processing technology is used to realize the image recognition and test functions of the MDU unit. The image data collection system collects 8 channels of analog signals, converts the data collected in each channel, and then outputs the whole image, so as to obtain a complete frame of image information, combined with the threshold shrinkage and the two coefficients of noise pollution by judging the degree of noise pollution image noise reduction processing, image text recognition processing based on CNN and image CNN model training. Experimental results show that the test system can successfully realize the functions of recognition, analysis, detection and processing of displayed images.

Exercise therapy is a common and effective approach for managing chronic knee pain. However, individuals often receive minimal supervision from physical therapists when exercises are performed at home. In this study, we developed a video-based training system to allow individuals to perform lower limb exercises, based on a machine learning algorithm for pose detection and estimation. The system included three key features: (1) an exercise video demonstration, (2) real-time tracking and feedback of exercise movements, and (3) an overall score of exercise performance. We also pilot tested the system by having participants (n = 8) to use the system to perform lower limb exercises for 3 consecutive days. The results indicated that, compared with the baseline, the perceived usefulness of the system ( t = 3.25, p = 0.01) and perceived lower limb muscle strength ( t = 2.94, p = 0.02) significantly improved after 3 days. These findings provide knowledge about the initial views on this system by the participants. However, further enhancements of the features and full-scale experiments to examine the usability and acceptance of the system and its impact on knee health are needed.

The purpose of this study is to develop an Intuitive Wearable Interactive System (IWIS) based on augmented reality (AR) and object recognition technology, which comprises an object recognition module, an intuitive control module, an AR information display module and a server linking module, so that the users can master the AR information and 3D objects about the objects in an intuitive operation mode. This new technology application mode enables the users to view the information of virtual objects more easily and rapidly. This study combines the new object recognition technology with gesture recognition technology to generate a friendly man-machine interaction interface, the virtual information is integrated into the real world, applied to the smart glasses device, so that the users can interact with virtual information intuitively, which is integrated and used in ordinary life.

Pose recognition in character animations is an important avenue of research in computer graphics. However, the current use of traditional artificial intelligence algorithms to recognize animation gestures faces hurdles such as low accuracy and speed. Therefore, to overcome the above problems, this paper proposes a real-time 3D pose recognition system, which includes both facial and body poses, based on deep convolutional neural networks and further designs a single-purpose 3D pose estimation system. First, we transformed the human pose extracted from the input image to an abstract pose data structure. Subsequently, we generated the required character animation at runtime based on the transformed dataset. This challenges the conventional concept of monocular 3D pose estimation, which is extremely difficult to achieve. It can also achieve real-time running speed at a resolution of 384 fps. The proposed method was used to identify multiple-character animation using multiple datasets (Microsoft COCO 2014, CMU Panoptic, Human3.6M, and JTA). The results indicated that the improved algorithm improved the recognition accuracy and performance by approximately 3.5% and 8–10 times, respectively, which is significantly superior to other classic algorithms. Furthermore, we tested the proposed system on multiple pose-recognition datasets. The 3D attitude estimation system speed can reach 24 fps with an error of 100 mm, which is considerably less than that of the 2D attitude estimation system with a speed of 60 fps. The pose recognition based on deep learning proposed in this study yielded surprisingly superior performance, proving that the use of deep-learning technology for image recognition has great potential.

The current literature strongly supports the use of supervised exercise therapy (SET) as the first-line treatment for symptomatic peripheral arterial disease (PAD) such as intermittent claudication (IC). However, this form of treatment remains underutilised in clinical practice. The home-based exercise therapy (HBET), in which patients must conduct themselves unsupervised is generally less effective than SET in terms of improving functional walking capacity. Nevertheless, it may be a useful alternative where SET is unavailable. The objective of this systematic review is to determine the effectiveness of HBET in reducing symptoms of IC in patients with PAD. Studies eligible for inclusion in this systematic review were parallel-group randomised controlled trials (RCTs) published in the English language that compared the effect of HBET to a comparator arm (SET or no exercise/attention control) in adults with PAD and IC. Studies were eligible if outcome measures were available at baseline and at 12 weeks of follow-up or more. The electronic databases PubMed, Google Scholar, and the Cochrane Library were searched from the earliest records up to January 2021. The Cochrane Collaboration risk of bias tool for RCTs (RoB 2)was used to assess the risk of bias in individual studies, and the Grading of Recommendations Assessment, Development, and Evaluation (GRADE) classification system was used to appraise the quality of evidence for each outcome across all studies. The primary investigator independently collected, pooled, and analysed the data. The data was then entered into the ReviewManager 5 (RevMan 5) software, and a meta-analysis was performed by using a fixed or random effects model depending on the presence or absence of statistical heterogeneity. The review author identified seven RCTs involving a total of 754 patients which were included in this study. Overall, the risk of bias in the included studies was moderate. Even though the results were variable, this analysis supported the ability of HBET to improve functional walking capacity and self-reported quality of life (QoL) to an extent. This review shows that a home-based exercise intervention with regular professional support and encouragement is beneficial in improving functional walking capacity as well as some aspects of QoL in patients with PAD and IC when compared to no exercise. However, when HBET is compared to hospital-based supervised exercise intervention, SET yields greater benefits.

Due to progress in technology of speech recognition and understanding, the Spoken dialogue systems (SDS) have started to emerge as a practical alternative for a conversational computer interface. They are more effective than Interactive Voice Response (IVR) systems since they allow a more free and natural interaction. The Spoken dialogue systems are designed for providing automatic dialogue-based voice services accessible through telephone. Such systems consist of a number of components that need to work together for the system to function successfully (McTear, 2005). The basic architecture of the SDS consists of (more or less indispensable) modules – dialogue manager, language understanding, speech recognition, access device interface, language generation and text to speech synthesis. Easiness of implementation and rapid development of voice services led to the standardization effort. The World Wide Web Consortium plays an important role in this area. The book chapter proposed will be focused on design, development and evaluation of the Spoken dialogue systems based on the W3C Recommendations. The World Wide Web Consortium is an international community that develops standards to ensure the long-term growth of the Web (W3C, 2010). One of their workgroups, Voice Browser Working Group, deals with preparing standards for voice-enabled technologies. The main idea is to build “Voice browser” enabling access to the information by voice, similarly as in the case of web browser. Comparison of definitions of the Spoken dialogue system and Voice browser lead to the conclusion, that both systems are very similar or de facto identical. A group of XMLbased languages (SIF Speech Interface Framework) was defined by Voice Browser Working Group to enable speech communication between user and computer. The W3C SIF recommendations became the industry standards in voice-enabled technology domain during the last decade. Languages in SIF also define the interfaces between fundamental subsystems of Spoken dialogue system and thus determine the basic structure of such system. The main languages in the framework are VoiceXML, SRGS and SSML that enable composing dialogues, speech grammars and instructions for text-to-speech systems. The CCXML serves for handling I/O (telephony) devices. The SISR specification defines the semantic tags for speech grammars to enable extracting of the meaning of user’s input. The meaning can be represented in the EMMA language, which was prepared by the W3C

Technologies for pattern recognition are used in various fields. One of the most relevant and important directions is the use of pattern recognition technology, such as gesture recognition, in socially significant tasks, to develop automatic sign language interpretation systems in real time. More than 5% of the world’s population—about 430 million people, including 34 million children—are deaf-mute and not always able to use the services of a living sign language interpreter. Almost 80% of people with a disabling hearing loss live in low- and middle-income countries. The development of low-cost systems of automatic sign language interpretation, without the use of expensive sensors and unique cameras, would improve the lives of people with disabilities, contributing to their unhindered integration into society. To this end, in order to find an optimal solution to the problem, this article analyzes suitable methods of gesture recognition in the context of their use in automatic gesture recognition systems, to further determine the most optimal methods. From the analysis, an algorithm based on the palm definition model and linear models for recognizing the shapes of numbers and letters of the Kazakh sign language are proposed. The advantage of the proposed algorithm is that it fully recognizes 41 letters of the 42 in the Kazakh sign alphabet. Until this time, only Russian letters in the Kazakh alphabet have been recognized. In addition, a unified function has been integrated into our system to configure the frame depth map mode, which has improved recognition performance and can be used to create a multimodal database of video data of gesture words for the gesture recognition system.

In educational institutions, effective communication plays a crucial role in ensuring smooth academic and administrative operations. Traditional methods, such as paper-based circulars and notice boards, often result in delays and miscommunication. This project introduces a voice-based college circular system aimed at real-time communication and enhanced campus connectivity. By leveraging speech recognition, fingerprint authentication, and smart display technology, the system provides a seamless way for faculty to broadcast messages efficiently. Users can log in using fingerprint authentication, speak their message, and have it converted into text for verification. The approved message is then broadcast to connected smart devices such as smart TVs. This ensures instant, paperless communication, reducing dependency on conventional methods while increasing accessibility and security. The system’s real-time capabilities and user-friendly interface make it an essential tool for modern educational institutions striving for digital transformation.

This research paper talks about the development of an innovative IoT-based smart door lock that also uses facial recognition, Internet of Things (IoT) integration, and the ESP32-CAM microcontroller to increase home security. As locks continue to evolve with more new features, the use of IoT is increasing and enhancing the security and usability. ESP32-CAM was selected for this project because of its built-in Wi-Fi connectivity and camera, which render it exceptionally suited for creating a smart lock system that is able to not only recognize the saved faces but also alert the user if there is an intruder. When compared to other microcontrollers like Raspberry Pi, the ESP32- CAM offers many more advantages, including enhanced security features, a userfriendly interface, and a lower cost, and much more in initial price. This paper also compares and talks about already existing facial recognition-based door locks, providing a detailed analysis of their plus points and limitations to understand the current state of the technology. The research also provides a detailed breakdown including the system's development process, selection of components for the device, and compilation of hardware components for the implementation of the model, The paper also includes the algorithms and user interface design. In this paper, you’ll see how each component works, its usage, and how each component works together to ensure reliable and accurate facial recognition. Also, model testing was done to get the device's performance in a number of different conditions and usage areas. The results of these tests show that ESP32-CAM based smart door lock is a good and powerful solution and it is also cost-effective, offering good amount of savings compared to other smart lock systems in the market. This paper highlights how the project talks about some of the common security problems associated with the old locking system. By offering a more accessible and reliable alternative, this smart lock system has the potential to revolutionize home security. The integration of advanced facial recognition technology with IoT makes the home door lock system a more secure and user-friendly approach to home access control.

Emerging technologies, like cloud computing, artificial intelligence (AI), and internet of things (IOT), are advancing the evolution of intelligent transportation systems (ITS). For successful technology integration, researches on ITS engineering often apply theories and tools of system engineering, among which system readiness level (SRL) is a fitting tool for system development. This paper built a model based on SRL analysis for highway ITS engineering. Further, the author analyzed the spatiotemporal features of highway ITS, including distributed computing resources and network capabilities, unbalanced development of existing information and communication technologies (ICT), and inherited architectural limitations of existing ITS infrastructures. The analysis indicated the need for economic consideration on highway ITS engineering. Therefore, this paper improved the SRL-based engineering model with a value engineering process. The effectiveness of the model was verified by the deployment of 5.8GHZ ambiguity path recognition technology, from aspects of system development and economic efficiency.

An important aspect of successful rehabilitation for musculoskeletal disorders is the continuity of the process, which is often disrupted after the patient is discharged. The development and implementation of remote rehabilitation methods is promising. The study presents a method for objectively assessing the quality of rehabilitation exercises using computer vision and machine learning. The developed system allows for automated monitoring of exercise technique performed by the patient using a mobile application. Analysis of data, including joint angles, speed, and execution time, provides the physician with graphs of indicator dynamics for remote progress assessment. The method has demonstrated clinical applicability, displaying reproducible angular profiles and informative metrics that facilitate the individualization of rehabilitation programs and the identification of problems. The technology is ready for pilot implementation in remote exercise therapy programs. Further research will require standardization of filming conditions and validation against traditional measurement methods.

Compared to more conventional techniques such as fingerprint recognition, the use of biometric authentication systems in computer-based examinations offers several advantages. To overcome the disadvantages of fingerprint biometrics, such as high administrative costs, long authentication times, and accuracy issues, this paper proposes an innovative solution that leverages state-of-the- art facial recognition technology. Although biometric fingerprint systems are reliable to a certain extent, they present significant challenges in the context of computer-assisted examinations. The authentication process can be time-consuming and can result in delays and logistical problems. These systems can also be prone to errors, including false positives and false negatives, compromising the integrity of the investigation process. These limitations require research into more efficient and accurate biometric solutions. The developed system uses FaceNet and Multi- Task Cascaded Convolutional Neural Network (MTCNN) algorithms in achieving superior accuracy, efficiency, as well as security in verifying candidates' identities during exams. FaceNet excels at facial recognition by mapping faces in a compact Euclidean space, ensuring high accuracy even with slight variations in facial expressions, angles or lighting conditions. MTCNN increases the robustness of the system through precise face detection and alignment, which are critical for reliable performance. The results show that the facial recognition system outperforms traditional fingerprint-based methods. Accuracy is significantly improved, reducing misidentifications, while streamlining the authentication process, minimizing delays, and improving overall efficiency. The robustness of the system ensures consistent performance despite environmental fluctuations.

Attendance management methods that use QR codes and face recognition technology to identify and verify an individual’s features are widely used in many aspects of people’s lives nowadays, notably in pandemic situations where contact-less systems are used. In this paper, the development of enhanced attendance monitoring system using was introduced. The Isabela State University Angadanan Campus has implemented a biometric attendance monitoring system. However, it is limited to the number of employees’ registrations, leave management and generation of Daily Time Record. The biometric system can only store 60 employees in every device, leave application and credits cannot be catered by the system and the Daily Time Record is not auto-generated and auto-formatted. For this reason, an enhanced attendance monitoring system was developed. The system uses a camera and QR Code reader to take attendance electronically, and the attendance records be saved in a database. It can store multiple number of employees, process leave application, manage remaining leave credits, and provide auto-generated Daily Time Record. This method, on the other hand, reduces the requirement for fixed materials and employees to retain records. From the developed system and the gathered data, it has addressed the problem of the conventional way of checking employee’s attendance. The general mean of 4.72 shows that the software quality of the system based on ISO 25010 is found to be functional that the users have strongly agreed on the different characteristics of the system as it addresses the issues in the current attendance monitoring system of ISU.