Parts Of Human Body Research Articles

Identification and relative depth estimation in natural images of single human body parts

Identification and relative depth estimation in natural images of single human body parts

Identification of ambiguous human body parts depends on pair-wise structural knowledge in natural images

Identification of ambiguous human body parts depends on pair-wise structural knowledge in natural images

Potential bacterial pathogens associated in wound infections at University Health Centre of a Southwest in Nigeria

Healthy skin forms a formidable obstacle against microorganisms but once this defense process is altered or obstructed creating a wound, bacteria have an ideal environment for growth and reproduction. lt is hardly inevitable not to have a wound because bacteria are ambiguously present in every part of human body. Emergency cuts, wounds, burns and accident cases are common occurrence in most Teaching Hospitals, however this is not so rampant in the University Health Centre and this form the basis of the study to know the extent of potential bacterial pathogens associated in wound infections at the Health Centre of the Federal university of Technology, Akure. Nigeria. Method: One hundred and seventy wound swab samples were collected from staff and students of the university aged 1-69 years from March 2022 to August 2022.The samples were processed via microscopy and cultured on MacConkey, Blood and Chocolate Agar respectively in the Microbiology laboratory where standard cultural techniques was carried out to identify,isolate and characterize the bacteria isolated. Result: Of the 170 wound swab samples examined, 74(43.6%) was positive to bacteria growth, while 96(56.4%) had no bacteria isolated. Conclusion: The result illustrated there were potential bacterial pathogens associated in wound infections isolated from the samples that was analyzed. This indicated that potential bacterial when not properly managed and treated appropriately can complicate the healing process of wound.

Dual-attention Network for View-invariant Action Recognition

View-invariant action recognition has been widely researched in various applications, such as visual surveillance and human–robot interaction. However, view-invariant human action recognition is challenging due to the action occlusions and information loss caused by view changes. Modeling spatiotemporal dynamics of body joints and minimizing representation discrepancy between different views could be a valuable solution for view-invariant human action recognition. Therefore, we propose a Dual-Attention Network (DANet) aims to learn robust video representation for view-invariant action recognition. The DANet is composed of relation-aware spatiotemporal self-attention and spatiotemporal cross-attention modules. The relation-aware spatiotemporal self-attention module learns representative and discriminative action features. This module captures local and global long-range dependencies, as well as pairwise relations among human body parts and joints in the spatial and temporal domains. The cross-attention module learns view-invariant attention maps and generates discriminative features for semantic representations of actions in different views. We exhaustively evaluate our proposed approach on the NTU-60, NTU-120, and UESTC large-scale challenging datasets with multi-type evaluation metrics including Cross-Subject, Cross-View, Cross-Set, and Arbitrary-view. The experimental results demonstrate that our proposed approach significantly outperforms state-of-the-art approaches in view-invariant action recognition.

Radiation injury and gut microbiota-based treatment.

The exposure to either medical sources or accidental radiation can cause varying degrees of radiation injury (RI). RI is a common disease involving multiple human body parts and organs, yet effective treatments are currently limited. Accumulating evidence suggests gut microbiota are closely associated with the development and prevention of various RI. This article summarizes 10 common types of RI and their possible mechanisms. It also highlights the changes and potential microbiota-based treatments for RI, including probiotics, metabolites, and microbiota transplantation. Additionally, a 5P-Framework is proposed to provide a comprehensive strategy for managing RI.

STATISTICAL INDICATORS FOR ACCIDENTS AT WORK IN CONSTRUCTION SECTOR ACCORDING TO THE PART OF BODY INJURED AND TYPES OF INJURIES

In this paper, the statistical indicators related to the number of non-fatal and fatal accidents at work according to certain injuries of human body parts and type of injury in the construction sector in the member states of the European Union (EU-28) for 2017 were analyzed. The most common body parts injured in non-fatal workplace accidents were the upper extremities (shoulders, arms and hands), with 42.3 % of the total number. The most common body parts injured in fatal workplace accidents in the EU-28 were whole body and multiple sites, with 32.5 % of the total number of non-fatal accidents at work in the construction sector. Most common injuries in the EU-28 resulting from non-fatal accidents in construction activity were wounds and superficial injuries (32.4% of the total number), dislocations, sprains and strains (25.8 %), concussion and internal injuries (18.0 %) and bone fractures (13.9 %). Poisoning and infections comprise 26.6% of the total number, dislocations, sprains and strains comprise 26.5 %, concussion and internal injuries make up 18.0 %, while bone fractures account for 13.9 %. The next most frequent types of injuries from all fatal accidents are unspecified injuries (18%) and bone fractures.

Single Human Parsing Based on Visual Attention and Feature Enhancement

Human parsing is one of the basic tasks in the field of computer vision. It aims at assigning pixel-level semantic labels to each human body part. Single human parsing requires further associating semantic parts with each instance. Aiming at the problem that it is difficult to distinguish the body parts with similar local features, this paper proposes a single human parsing method based on the visual attention mechanism. The proposed algorithm integrates advanced semantic features, global context information, and edge information to obtain accurate results of single human parsing resolution. The proposed algorithm is validated on standard look into part (LIP) dataset, and the results prove the effectiveness of the proposed algorithm.

Effectiveness of peer-assisted teaching of medical English skills to non-native English-speaking medical students

Background: Peer-assisted learning has been shown to be constructive in numerous aspects of undergraduate medical education. The purpose of this study was to evaluate the effectiveness of peer-assisted teaching of medical English skills to non-native English-speaking students. Methods: A medical English conversation course was conducted at Damascus University by a group of students. Targeted participants were intermediate level fellow students from the same program. A longitudinal study was carried out between 1st to 31st March 2019 to assess changes in self-assessment of English language skills among course participants. Pre- and post-course appraisal involved a review of previous experience with medical English language, a self-assessment of five English language skills, and an objective measurement of medical English knowledge. In addition, participants were requested to respond to a set of statements related to the importance and the usefulness of peer-assisted teaching of medical English skills. Paired-sample Student t-test was used to compare pre- and post-course appraisal results. Results: 42 students attended the course and completed pre- and post-course appraisals in full. Data analyses showed a statistically significant increase in participants’ confidence in speaking medical English in public (p<0.001) and using English in various medical settings (presenting and discussing cases, writing clinical reports, interviewing patients and reading English medical texts). Objective measurements of medical English knowledge confirmed a significant increase in participants’ knowledge of methods of administration of therapeutics, knowledge of human body parts in English and familiarity with English medical abbreviations. Most participants agreed that peer-education was effective in teaching medical English skills to non-native English-speaking students and in increasing their confidence when using English in real-life medical scenarios. Conclusions:The present study highlights the effectiveness of peer-assisted teaching of medical English skills to non-native English-speaking medical students. Further validation is required and should compare the effectiveness of traditional versus peer-assisted teaching approaches.

Flexible and strain conductive cotton yarn enabled by low-temperature sintering of silver paste with multifunctional sensing capability in human motion detection and wearable applications

Flexible wearable textiles have attracted increasing attention, due to their potential applications in human motion detection, electric heating and humidity monitoring. However, the rigidity of metal materials contradicts the flexibility of textiles, and the complex preparation process and unfriendly environment hinder the development of metal materials as conductive materials of smart textiles. This study proposed a simple and environmentally friendly solution for smart textile preparation. Drawing on the bionic design principle of long-horned beetle’s exocuticle, the conductive layer on the surface of cotton yarn (CY) was formed by sintering the silver paste under low temperature of 200 ˚C. Silver Paste (SP) mainly composed with silver particles, terpineol (TE) and ethyl cellulose (EC). The resultant conductive yarn was characterized with high flexibility and high conductivity (4.08 × 103 S/cm). The conductivity of the yarn increases under tensile force, while decreases under non-tensile bending action. The strain sensor prepared by the yarn has a wide working range and high sensitivity, with distinguish performances of signal output according to the motion of different human body parts. The sensing behavior was also highlighted with the capability of micro-vibration strain of the human body, such as response to the pulse and throat. Furthermore, the conductive property of sintered silver paste cotton yarn (SSP-CY) has the capability of electric heating. The electric heating device based on SSP-CY can realize wired and radio heating, which resulted a maximum temperature of about 41 ℃. Therefore, the novel conductive cotton yarn has great potential in the application of high-sensitive wearable electronic devices.

Human Part Semantic Segmentation Using CDGNET Architecture for Human Activity Recognition

The segmentation of human body parts is a task that entails assigning labels to pixels in an image to identify the corresponding body part classes. To enhance accuracy, a technique known as sample class distribution was developed, considering the hierarchical structure of the human body and the unique positioning of each part. This technique involves gathering and applying primary human parsing labels in both vertical and horizontal dimensions to exploit the distribution of classes. By combining these guided features, a spatial guidance map is generated and incorporated into the backbone network. These semantic-guided features contribute to the effective recognition of human activity through semantic segmentation-enabled human pose. To assess the effectiveness of this approach, extensive experiments were performed on a large dataset called CIHP, using metrics such as mean IOU, pixel accuracy, and mean accuracy.

Systematic survey on generative adversarial networks for brain tumor segmentation and classification

SummaryBrain cancer is one of the leading diseases of death in the world caused due to unwanted proliferation of cells. If left untreated, this growth can spread into other human body parts. So early detection helps to enhance long‐term survival and reduce the mortality rate. A lot of research has been done in the field of brain tumors. There have been numerous previous studies conducted using traditional approaches. So far, few review studies are available on brain tumor segmentation and classification and moreover, they were quite limited in explaining the connections of Generative Adversarial Networks (GAN) for brain tumor segmentation and classification. This review mainly focuses on the GAN architectures for brain tumor segmentation and classification. Therefore, first, an overview of brain tumors, GAN‐based publications, approaches to brain tumor segmentation and classification, data sets, software platforms, and performance parameters, are presented. Finally, GAN applications and current trends are discussed. This thorough survey will aid researchers and beginners in the future in creating a better decision support system.

Multi-Person Pose Estimation in the Wild: Using Adversarial Method to Train a Top-Down Pose Estimation Network

Recent studies estimate human anatomical key points through the single monocular image, in which multichannel heatmaps are the key factor in determining the quality of human pose estimation. Multichannel heatmaps can efficiently handle the image-to-coordinate mapping task and the processing of semantic features. Most methods ignore physical constraints and internal relationships of human body parts, which easily misclassify left and right symmetrical parts as similar features. Some studies use RNNs on the top to incorporate priors about the structure of pose components and body configuration. Therefore, a novel top-down convolutional network is proposed to consider these priors during training, which can improve the robustness under complex field conditions in the wild. In order to learn the prior knowledge of human pose configuration, the hierarchy of fully convolutional networks (discriminator) is used to distinguish real poses from fake ones. Consequently, the pose network is inclined to make a pose estimation that the discriminator misjudges as true, which is reasonable in complex situations. The performance of the method is experimentally validated by pose estimation on the MS COCO human key point detection task. The proposed approach outperforms the original method and generates robust pose predictions, demonstrating efficiency by using adversarial learning.

AR Mobile Application for Human Anatomy

Abstract: Anatomy is the main topic of human biology. The study of interior body organs, from cells to organ systems, is known as human anatomy. Studying the 2D model of the internal structure is difficult and tiresome. The purpose of this study is to develop a 3D Augmented Reality anatomy of human learning system. When learning anatomy through textbooks, puppets, or 2D models, it might be difficult to understand the internal structure. One solution that has been developed is an Android app that uses augmented reality. An interactive menu in the program allows you to scan an image and see a 3D version of a model in actual space. This study uses Augmented Reality technology to create a human body learning system. It is hoped that by using this approach, students will be able to visualize the human body's parts in 3D with ease. Students can learn more quickly with the use of AR technology.

From Robotics to Prosthetics: What Design and Engineering Can Do Better Together

This paper discusses how the disciplines of Design and Engineering are jointly addressing disability and somehow affecting its very interpretation. The discussion focuses on high-tech prostheses, where robotic devices substitute human body parts. The application of robotic technologies to prosthetics has a relatively long history. Nevertheless, only in the last decade have we witnessed applications reach the market and become available for a large base of users who were offered prostheses with superior motor and sensory performance. The process of bringing ever more advanced technologies to fruition by prosthetic users is fully ongoing today, with some promising solutions coming from robotics (such as, e.g. AI techniques or soft robotics materials) to be transferred to human use. In this transfer process, technology alone is insufficient to warrant success, and the need for a close collaboration between the Engineering domain and the Design disciplines is apparent. We address this point with specific reference to a case study, i.e. the transformation of an innovative but by-now established technology in the industrial robotics field (the “Pisa/IIT SoftHand”) into a prosthetic hand (the “SoftHand Pro”). Besides obvious technical considerations about size, connections, control, and so on, which can be addressed with a thorough technical revision of the design, what makes the profound difference between the two devices is that, as a prosthesis, the SoftHand is intended as a human body part, and not as an external tool. To reach its ultimate goals, the hand should become a part of the human user, with his body and mind. The empirical approach and tools of Designers afford the possibility to enrich the re-design process, considering the final user at the centre of the process, in a sort of renewed humanistic approach. The paper reflects this multidisciplinary approach and is structured as follows: the first part describes a cultural framework for the use of high-technology upper limb prostheses. This culture is defined through two significant relations (Users & Society; Users & Device). Inputs come from desk research conducted in different fields, ranging from Social Psychology to Medicine and Rehabilitation area. In this scenario, it is possible to extract design insights applicable to the design brief. The introduction of a robotic prosthetic hand (SoftHand Pro) and a related, single-user case study follow. The aim here is also to illustrate a process where engineering innovations are facilitated by tools from the Design field in the attempt to make the whole process coherently centred on users. Involved are all aspects, from material technology to the covering and finishing of the prosthetic device. The resulting, final prototype of the SoftHand Pro is finally presented.

Smoothing Module for Optimization Cranium Segmentation Using 3D SlicerSmoothing Module for Optimization Cranium Segmentation Using 3D Slicer

Anatomy is the most essential course in health and medical education to study parts of human body and also the function of it. Cadaver is a media used by medical student to study anatomical subject. Because of limited access to cadaver and also due to high prices, this situation makes it necessary to develope an alternative anatomical education media, one of them is the use 3D printing to produce anatomical models. Before 3D Print the cranium, it is necessary to do the segmentation process and often the segmentation result is not good enough and appear a lot of noises. The purpose of this research is to optimize a 3D cranium based on DICOM (digital imaging and communications in medicine) data processing using the smoothing modules on 3D Slicer. The method of this research is to process the Cranium DICOM data using 3D Slicer software by varying the 5 types of smoothing modules. The results with default parameter fill holes and median have better results compared to others. Kernel size variations are performed for smoothing module fill holes and medians. The result is fill holes get optimal segmentation results using a kernel size of 3 mm and the median is 5 mm.

Student behavior recognition for interaction detection in the classroom environment

With the development of multimedia technologies, surveillance videos and other multimedia data have received widespread attention in several fields. Surveillance videos can monitor students' learning statuses in real time. However, the current action recognition methods for teaching have limitations. First, the ethical privacy of AI and education makes public datasets on student behavior scarce. Therefore, based on the summarization of seven typical student behaviors in the classroom, course videos were obtained from the smart classroom to generate a dataset of student behavior. Compared with existing student behavior recognition datasets, the proposed dataset is distinguished by cluttered backgrounds, crowded scenes, and occlusions. Second, relational reasoning using existing methods is not ideal for distinguishing between students' body parts and small objects in a cluttered background; the interactive utilization rate of different relational features is low, and it cannot take advantage of the complementarity of different relational features, resulting in poor performance of interaction action recognition. Therefore, the attention-based relational reasoning module strengthens the interactive representation between small objects and human body parts. At the same time, considering that there is a certain complementary relationship between relational features, this study constructs a relational feature fusion module which models a human-to-human interaction relationship built upon supporting human's body part and surrounding context. Finally, the reconstructed features and human-appearance features were fused to achieve accurate interactive action recognition. Through an experimental comparison between the proposed and current mainstream algorithms on the generated student behavior dataset, it was verified that the proposed model achieves state-of-the-art performance in action recognition.

Non-Invasive antenna sensor based continuous glucose monitoring using pancreas dielectric radiation signal energy levels and machine learning algorithms

In this paper, H shape with I slot patch (HSIS) antenna is utilized as sensor for proposed continuous glucose monitoring (CGM) device. HSIS antenna sensor is placed on pancreas of human body and acquires dielectric radiation signals from the pancreas. Pancreas dielectric property changes during insulin secretion. HSIS antenna as a passive sensor acquires pancreas dielectric radiation signals from pancreas more effectively due to H shape and I slot. H shape antenna covers maximum region on human pancreas. During signal acquisition, crumbling effect causes bending and stretching in pancreas and leads to noise in signal, which is prevented through H-shape in HSIS antenna. Traditional CGM method measures diabetic value through invasive sensors. Non-invasive diabetic measurement device never measures CGM because of sensor mount for long duration on human body which is the major problem and leads to infections due to pricked sensor on the body for more than 14 days. In this paper, pancreas is identified as optimized location for CGM through HSIS antenna, among other human body parts such as stomach, carpus and thumb finger. Optimized location is identified through return loss and VSWR values. HSIS antenna acquired pancreas dielectric radiation signals process with Rational Dilation Wavelet Transforms (RADWT). Energy band and statistical values are obtained from signals and correlated with laboratory diabetic values. Experimental study of CGM is performed in 150 diabetic persons. The proposed HSIS antenna as sensor shows the fluctuation in diabetic value through signals and predict the diabetic value with 91.85% accuracy, when compared to laboratory based diabetic value measurement.

Recognition and 3D Visualization of Human Body Parts and Bone Areas Using CT Images

Abstract The advent of medical imaging significantly assisted in disease diagnosis and treatment. This study introduces to a framework for detecting several human body parts in Computerised Tomography (CT) images formatted in DICOM files. In addition, the method can highlight the bone areas inside CT images and transform 2D slices into a visual 3D model to illustrate the structure of human body parts. Firstly, we leveraged shallow convolutional Neural Networks to classify body parts and detect bone areas in each part. Then, Grad-CAM was applied to highlight the bone areas. Finally, Insight and Visualization libraries were utilized to visualize slides in 3D of a body part. As a result, the classifiers achieved 98 % in F1-score in the classification of human body parts on a CT image dataset, including 1234 slides capturing body parts from a woman for the training phase and 1245 images from a male for testing. In addition, distinguishing between bone and non-bone images can reach 97 % in F1-score on the dataset generated by setting a threshold value to reveal bone areas in CT images. Moreover, the Grad-CAM-based approach can provide clear, accurate visualizations with segmented bones in the image. Also, we successfully converted 2D slice images of a body part into a lively 3D model that provided a more intuitive view from any angle. The proposed approach is expected to provide an interesting visual tool for supporting doctors in medical image-based disease diagnosis.

Compensating the NLoS Occlusion Errors of UWB for Pedestrian Localization With MIMU

The Ultra-Wideband (UWB) technology has become a competitive choice for indoor pedestrian localization due to its advantages in accuracy, compact size, reliability, power efficiency, and easy setup. However, the None-Line-of-Sight (NLoS) occlusion caused by the human body parts and obstacles in its propagation path may introduce significant location errors that limit its performance and field of application. To handle the NLoS occlusion errors and promote the localization accuracy for complex indoor environments, a Micro-Electro-Mechanical System (MEMS) Inertial Measurement Unit (MIMU)-assisted UWB localization system with NLoS occlusion error compensation techniques is provided. Firstly, an NLoS occlusion detection method using the built-in channel information of the UWB transceivers and the variation pattern of anchor-node distance is proposed. Secondly, an Extended Kalman Filter (EKF)-based attitude computation and a Zero-Velocity Update (ZUPT)-based continuous gait segmentation are introduced for inertial navigation during occlusion intervals. Then, the UWB and IMU parameters are integrated with an Unscented Kalman Filter (UKF) framework to compensate for the occlusion error and improve the accuracy and robustness. Finally, a battery-powered miniature wearable device is developed and the proposed techniques are verified with experimental studies. The results demonstrate the feasibility and effectiveness of the presented techniques, which provides a good reference for related Internet of Things (IoT) applications.

Design and fabrication of curved sensor based on polyvinylidene fluoride/graphene composite film with a self-assembling mechanism for monitoring of human body parts movement

Design and fabrication of curved sensor based on polyvinylidene fluoride/graphene composite film with a self-assembling mechanism for monitoring of human body parts movement