Robust Interactive Method for Hand Gestures Recognition Using Machine Learning

The Hand Gestures Recognition(HGR)System can be employed to facilitate communication between humans and computers instead of using special input and output devices.These devices may complicate communication with computers especially for people with disabilities.Hand gestures can be defined as a natural human-to-human communication method,which also can be used in human-computer interaction.Many researchers developed various techniques and methods that aimed to understand and recognize specific hand gestures by employing one or two machine learning algorithms with a reasonable accuracy.Thiswork aims to develop a powerful hand gesture recognition model with a 100%recognition rate.We proposed an ensemble classification model that combines the most powerful machine learning classifiers to obtain diversity and improve accuracy.The majority voting method was used to aggregate accuracies produced by each classifier and get the final classification result.Our model was trained using a self-constructed dataset containing 1600 images of ten different hand gestures.The employing of canny’s edge detector and histogram of oriented gradient method was a great combination with the ensemble classifier and the recognition rate.The experimental results had shown the robustness of our proposed model.Logistic Regression and Support Vector Machine have achieved 100%accuracy.The developed model was validated using two public datasets,and the findings have proved that our model outperformed other compared studies.

基于HAND的流域洪水淹没快速分析技术

快速分析计算流域洪水淹没,对于防洪具有重要作用,而基于水动力学模型的经典淹没算法在时效性方面存在不足,制约防洪“四预”功能实现和数字孪生流域建设。针对此,本文建立了基于HAND(Height Above Nearest Drainage)的形态淹没模型,用于快速分析流域洪水淹没情况,在乐安河流域上游进行了应用验证。结果表明,模型可在5秒内完成洪水淹没计算,对四场历史洪水和三场设计洪水淹没范围的总体模拟精度平均为0.95,达到水动力学模型的模拟精度;对淹没水深的模拟存在较大误差,平均误差为0.79 m。基于HAND的形态淹没模型可快速绘制全流域洪水淹没范围图,大幅提升影响预报和防洪预演的时效性水平。

Dynamic Hand Gesture-Based Person Identification Using Leap Motion and Machine Learning Approaches

Person identification is one of the most vital tasks for network security. People are more concerned about theirsecurity due to traditional passwords becoming weaker or leaking in various attacks. In recent decades, fingerprintsand faces have been widely used for person identification, which has the risk of information leakage as a resultof reproducing fingers or faces by taking a snapshot. Recently, people have focused on creating an identifiablepattern, which will not be reproducible falsely by capturing psychological and behavioral information of a personusing vision and sensor-based techniques. In existing studies, most of the researchers used very complex patternsin this direction, which need special training and attention to remember the patterns and failed to capturethe psychological and behavioral information of a person properly. To overcome these problems, this researchdevised a novel dynamic hand gesture-based person identification system using a Leap Motion sensor. Thisstudy developed two hand gesture-based pattern datasets for performing the experiments, which contained morethan 500 samples, collected from 25 subjects. Various static and dynamic features were extracted from the handgeometry. Randomforest was used to measure feature importance using the Gini Index. Finally, the support vectormachinewas implemented for person identification and evaluate its performance using identification accuracy. Theexperimental results showed that the proposed system produced an identification accuracy of 99.8% for arbitraryhand gesture-based patterns and 99.6% for the same dynamic hand gesture-based patterns. This result indicatedthat the proposed system can be used for person identification in the field of security.

Deep Reinforcement Learning Based Unmanned Aerial Vehicle (UAV) Control Using 3D Hand Gestures

The evident change in the design of the autopilot system produced massive help for the aviation industry and it required frequent upgrades.Reinforcement learning delivers appropriate outcomes when considering a continuous environment where the controlling Unmanned Aerial Vehicle(UAV)required maximum accuracy.In this paper,we designed a hybrid framework,which is based on Reinforcement Learning and Deep Learning where the traditional electronic flight controller is replaced by using 3D hand gestures.The algorithm is designed to take the input from 3D hand gestures and integrate with the Deep Deterministic Policy Gradient(DDPG)to receive the best reward and take actions according to 3D hand gestures input.The UAV consist of a Jetson Nano embedded testbed,Global Positioning System(GPS)sensor module,and Intel depth camera.The collision avoidance system based on the polar mask segmentation technique detects the obstacles and decides the best path according to the designed reward function.The analysis of the results has been observed providing best accuracy and computational time using novel design framework when compared with traditional Proportional Integral Derivatives(PID)flight controller.There are six reward functions estimated for 2500,5000,7500,and 10000 episodes of training,which have been normalized between 0 to−4000.The best observation has been captured on 2500 episodes where the rewards are calculated for maximum value.The achieved training accuracy of polar mask segmentation for collision avoidance is 86.36%.

Implementation of natural hand gestures in holograms for 3D object manipulation

Holograms provide a characteristic manner to display and convey information, and have been improved to provide better user interactions Holographic interactions are important as they improve user interactions with virtual objects. Gesture interaction is a recent research topic, as it allows users to use their bare hands to directly interact with the hologram. However, it remains unclear whether real hand gestures are well suited for hologram applications. Therefore, we discuss the development process and implementation of three-dimensional object manipulation using natural hand gestures in a hologram. We describe the design and development process for hologram applications and its integration with real hand gesture interactions as initial findings. Experimental results from Nasa TLX form are discussed. Based on the findings, we actualize the user interactions in the hologram.

Japanese Sign Language Recognition by Combining Joint Skeleton-Based Handcrafted and Pixel-Based Deep Learning Features with Machine Learning Classification

Sign language recognition is vital for enhancing communication accessibility among the Deaf and hard-of-hearing communities.In Japan,approximately 360,000 individualswith hearing and speech disabilities rely on Japanese Sign Language(JSL)for communication.However,existing JSL recognition systems have faced significant performance limitations due to inherent complexities.In response to these challenges,we present a novel JSL recognition system that employs a strategic fusion approach,combining joint skeleton-based handcrafted features and pixel-based deep learning features.Our system incorporates two distinct streams:the first stream extracts crucial handcrafted features,emphasizing the capture of hand and body movements within JSL gestures.Simultaneously,a deep learning-based transfer learning stream captures hierarchical representations of JSL gestures in the second stream.Then,we concatenated the critical information of the first stream and the hierarchy of the second stream features to produce the multiple levels of the fusion features,aiming to create a comprehensive representation of the JSL gestures.After reducing the dimensionality of the feature,a feature selection approach and a kernel-based support vector machine(SVM)were used for the classification.To assess the effectiveness of our approach,we conducted extensive experiments on our Lab JSL dataset and a publicly available Arabic sign language(ArSL)dataset.Our results unequivocally demonstrate that our fusion approach significantly enhances JSL recognition accuracy and robustness compared to individual feature sets or traditional recognition methods.

子痫前期病人长链非编码RNA H19和长链非编码RNA HAND2-AS1表达水平与胰岛素抵抗的相关性研究

目的检测子痫前期病人胎盘组织、血清长链非编码RNA H19(LncRNA H19)与长链非编码RNAHAND2-AS1(Ln⁃cRNA HAND2-AS1)表达水平,并分析其与病人胰岛素抵抗(IR)的相关性。方法将2021年1—12月在唐山市妇幼保健院建卡的子痫前期孕妇105例作为子痫前期组,根据子痫前期孕妇严重程度分为轻度子痫前期组与重度子痫前期组,另选取同期孕周、年龄相符的健康孕妇97例作为对照组,收集所有孕妇身体质量指数(BMI)、孕周、收缩压、舒张压、空腹胰岛素(FINS)、空腹血糖(FBG)等一般资料,并计算稳态模型的IR指数(HOMA-IR);实时荧光定量PCR(qRT-PCR)法测定孕妇血清、胎盘组织中LncRNA H19,LncRNA HAND2-AS1水平;比较对照组与子痫前期组、轻度子痫前期组与重度子痫前期组间血清、胎盘组织LncRNA H19、LncRNA HAND2-AS1水平;Pearson法分析子痫前期孕妇血清、胎盘组织LncRNA H19、LncRNA HAND2-AS1与HOMA-IR的相关性。结果子痫前期组病人收缩压、舒张压高于对照组(P<0.05),且重度子痫前期病人收缩压、舒张压高于轻度子痫前期病人,孕周低于轻度子痫前期病人(P<0.05);与对照组相比,子痫前期组孕妇24 h尿蛋白、FBG[(5.84±0.97)mmol/L比(4.22±0.70)mmol/L]、FINS[(13.37±2.23)mU/L比(7.52±1.25)mU/L]、HOMI-IR水平(3.47±0.57比1.41±0.23)升高(P<0.05),且重度子痫前期孕妇24 h尿蛋白、FBG[(6.90±1.15)mmol/L比(5.24±0.85)mmol/L]、FINS[(13.97±2.32)mU/L比(13.05±2.17)mU/L]、HOMI-IR水平(4.27±0.71比3.03±0.50)高于轻度子痫前期孕妇(P<0.05);与对照组相比,子痫前期组孕妇血清、胎盘组织Ln⁃cRNA H19(2.52±1.42比1.01±0.15,3.75±0.62比1.02±0.17)与LncRNA HAND2-AS1水平(1.98±0.33比1.01±0.15,2.87±0.47比1.02±0.17)升高(P<0.05),且重度子痫前期孕妇血清、胎盘组织LncRNA H19(2.84±0.47比2.34±0.39,4.28±0.71比3.45±0.57)与LncRNA HAND2-AS1水平(2.59±0.43比1.63±0.27,3.56±0.59比2.49±0.41)高于轻度子痫前期孕妇(P<0.05);子痫前期病人血清与胎盘组织间LncRNA H19水平呈正相关(r=0.55,P<0.05),血清与胎盘组织间LncRNA HAND2-AS1水平呈正相关性(r=0.65,P<0.05)。子痫前期孕妇血清、胎盘组织LncRNA H19水平分别与HOMI-IR呈正相关(r=0.53、0.59,P<0.05);血清、胎盘组织LncRNA HAND2-AS1水平分别与HOMI-IR呈正相关(r=0.60、0.61,P<0.05)。结论子痫前期病人血清、胎盘组织LncRNA H19、LncRNA HAND2-AS1高表达,二者与IR密切相关,可能通过影响IR参与子痫前期发生发展。

Hand Gestures Recognition Based on One-Channel Surface EMG Signal

This paper presents an experiment using OPENBCI to collect data of two hand gestures and decoding the signal to distinguish gestures. The signal was extracted with three electrodes on the subiect’s forearm and transferred in one channel. After utilizing a Butterworth bandpass filter, we chose a novel way to detect gesture action segment. Instead of using moving average algorithm, which is based on the calculation of energy, We developed an algorithm based on the Hilbert transform to find a dynamic threshold and identified the action segment. Four features have been extracted from each activity section, generating feature vectors for classification. During the process of classification, we made a comparison between K-nearest-neighbors (KNN) and support vector machine (SVM), based on a relatively small amount of samples. Most common experiments are based on a large quantity of data to pursue a highly fitted model. But there are certain circumstances where we cannot obtain enough training data, so it makes the exploration of best method to do classification under small sample data imperative. Though KNN is known for its simplicity and practicability, it is a relatively time-consuming method. On the other hand, SVM has a better performance in terms of time requirement and recognition accuracy, due to its application of different Risk Minimization Principle. Experimental results show an average recognition rate for the SVM algorithm that is 1.25% higher than for KNN while SVM is 2.031 s shorter than that KNN.

Holographic Raman Tweezers Controlled by Hand Gestures and Voice Commands

Several attempts have appeared recently to control optical trapping systems via touch tablets and cameras instead of a mouse and joystick. Our approach is based on a modern low-cost hardware combined with fingertips and speech recognition software. Positions of operator's hands or fingertips control the positions of trapping beams in holographic optical tweezers that provide optical manipulation with microobjects. We tested and adapted two systems for hands position detection and gestures recognition – Creative Interactive Gesture Camera and Leap Motion. We further enhanced the system of Holographic Raman tweezers (HRT) by voice commands controlling the micropositioning stage and acquisition of Raman spectra. Interface communicates with HRT either directly by which requires adaptation of HRT firmware, or indirectly by simulating mouse and keyboard messages. Its utilization in real experiments speeded up the operator’s communication with the system cca. Two times in comparison with the traditional control by the mouse and the keyboard.

Virtual Keyboard:A Real-Time Hand Gesture Recognition-Based Character Input System Using LSTM and Mediapipe Holistic

In the digital age,non-touch communication technologies are reshaping human-device interactions and raising security concerns.A major challenge in current technology is the misinterpretation of gestures by sensors and cameras,often caused by environmental factors.This issue has spurred the need for advanced data processing methods to achieve more accurate gesture recognition and predictions.Our study presents a novel virtual keyboard allowing character input via distinct hand gestures,focusing on two key aspects:hand gesture recognition and character input mechanisms.We developed a novel model with LSTM and fully connected layers for enhanced sequential data processing and hand gesture recognition.We also integrated CNN,max-pooling,and dropout layers for improved spatial feature extraction.This model architecture processes both temporal and spatial aspects of hand gestures,using LSTM to extract complex patterns from frame sequences for a comprehensive understanding of input data.Our unique dataset,essential for training the model,includes 1,662 landmarks from dynamic hand gestures,33 postures,and 468 face landmarks,all captured in real-time using advanced pose estimation.The model demonstrated high accuracy,achieving 98.52%in hand gesture recognition and over 97%in character input across different scenarios.Its excellent performance in real-time testing underlines its practicality and effectiveness,marking a significant advancement in enhancing human-device interactions in the digital age.

基于隐喻与转喻的人体多义词hand的认知研究及其教学启示

人体是人类认知世界的起点,人体词的义项拓展严格遵循隐喻、转喻路径进行生成和演化。为帮助英语学习者更好地理解、记忆多义词,从隐喻映射和转喻映射角度出发,考察人体多义词hand的义项拓展路径及其类别。研究发现,hand的义项派生共有七种映射路径,分别为基本、抽象、人物、形貌、意动、计量、修饰,并探讨如何基于人体词分析其他多义词的义项拓展,尝试为二语词汇学习和教学提供思路。

Quantitative analysis of the morphing wing mechanism of raptors:IMMU-based motion capture system and its application on gestures of a Falco peregrinus

This paper presented a novel tinny motion capture system for measuring bird posture based on inertial and magnetic measurement units that are made up of micromachined gyroscopes, accelerometers, and magnetometers. Multiple quaternion-based extended Kalman filters were implemented to estimate the absolute orientations to achieve high accuracy.Under the guidance of ornithology experts, the extending/contracting motions and flapping cycles were recorded using the developed motion capture system, and the orientation of each bone was also analyzed. The captured flapping gesture of the Falco peregrinus is crucial to the motion database of raptors as well as the bionic design.

Hand Cooling Enhances the Proprioceptive Drift during Rubber Hand Illusion

Background: The neural representation of the body is easily altered by integrating multiple sensory signals in the brain. The “Rubber Hand Illusion” (RHI) is one of the most popular experimental paradigms to investigate this phenomenon. During this illusion, ownership of a rubber hand is temporarily induced. It was shown that external and continuous cooling of the palm enhanced the RHI, suggesting an association between altered the autonomic nervous system regulation and altered the sense of ownership of a specific limb. Purpose: To investigate whether artificially cooling the entire hand for a short period affects the magnitude of the illusion. Methods: Participants immersed their entire hand in cool, cold, or warm water for 1 min before the RHI procedure. Results: We found that cooling the entire hand enhanced the proprioceptive drift during the RHI but not the subjective feeling of ownership. In contrast, warming and intense cooling of the entire hand did not affect the RHI strength. Conclusion: Our results suggest that transient and moderate cooling of the entire hand was sufficient in enhancing the illusory disembodiment of one’s own hand.

Comparison between Care Strategies for Patients with Osteoarthritis of the Hands Based on the Use of Joint Protection, Assistive Technology and Exercises

Background: Osteoarthritis (OA) is a disabling disease that can affect 6% to 12% of the adult population and more than a third of people over 65 years of age. Purpose: To assess whether a group of people with hand osteoarthritis (hOA) who received different types of treatment improved their function after two years of follow-up. Method: The entire sample (n = 97) underwent three follow-up assessments regarding anthropometric parameters of the upper limbs and ability to perform functional activities. Subsequently, the sample was divided into two groups for the intervention periods, called the First Period (n = 73) and the Second Period (n = 24);the First Period kept the same protocol with orientations, and the Second Period went to an intervention with orientation strength exercises and use of orthosis. Findings: In the separate analysis of the three questions of the DASH pain module, no differences were found between the assessment moments for groups of guidelines, treatment, or symptoms. Significant effects were observed for F(2, 162) = 3.5, p = 0.033, η2 = 0.04, and interaction for moments and intervention F(2, 162) = 4.3, p = 0.016, η2 = 0.05. Implications: It can be concluded that only guidance treatment does not benefit patients with hand osteoarthritis. In contrast, guidance, exercise, and orthosis treatment can significantly improve the disease.

Tenosynovitis of hand: Causes and complications

Tenosynovitis represents a common clinical condition characterized by inflam-mation of the synovium that encases the tendon sheath.Although tenosynovities may be noted in any tendon in the body,extremities such as hand,and foot remain the sites of high predilection to acquire this condition.The predominant cause of this predilection rests in the intricate tendon arrangements in these extremities that permit fine motor actions.This editorial explores the common causes and the complications associated with this condition to improve the understanding of the readers of this common condition encountered in our everyday clinical practice.

Surgical management of adult hand macrodactyly in a 49-year-old patient:A case report

BACKGROUND Macrodactyly is a rare congenital malformation characterized by an increase in the size of all structures of a digit,accounting for less than 1%of all congenital upper extremity conditions.CASE SUMMARY We report a case involving a 49-year-old woman who presented for the first time with untreated,radial-sided hand macrodactyly.We performed soft tissue debulking,amputation,median nerve neurotomy and coaptation,and carpal tunnel release.At the 6-year follow-up,no significant growth was observed in the bone or soft tissue of the affected area.CONCLUSION Tissue overgrowth in patients with progressive macrodactyly can continue and progress excessively with age.Median nerve neurotomy and coaptation play a crucial role in preventing recurrence of the deformity.

Epidemiology of work-related hand and wrist injuries in a referral center: A descriptive study

BACKGROUND Occupational hand and wrist injuries(OHWIs)account for 25%of work-related accidents in low-and middle-income countries.In Colombia,more than 500000 occupational accidents occurred in 2021,and although the rate declined to less than 5%in 2020 and 2021,at least one in four accidents involved a hand or wrist injury.AIM To describe the OHWIs in workers seen at the emergency room at a second-level hospital in Colombia.METHODS An observational study was performed using data from workers who experienced OHWIs and attended a second-level hospital,between June,2020 and May,2021.The overall frequency of OHWIs,as well as their distribution by sociodemo-graphic,clinical,and occupational variables,are described.Furthermore,association patterns between sex,anatomical area(fingers,hand,wrist),and type of job were analyzed by correspondence analysis(CA).RESULTS There were 2.101 workers treated for occupational accidents,423(20.3%)were cases of OHWIs,which mainly affected men(93.9%)with a median age of 31 years and who worked mainly in mining(75.9%).OHWIs were more common in the right upper extremity(55.3%)and comprised different types of injuries,such as contusion(42.1%),laceration(27.9%),fracture(18.7%),and crush injury(15.6%).They primarily affected the phalanges(95.2%),especially those of the first finger(25.7%).The CAs showed associations between the injured anatomical area and the worker’s job that differed in men and women(explained variance>90%).CONCLUSION One out of five workers who suffered occupational accidents in Cundinamarca,Columbia had an OHWI,affecting mainly males employed in mining.This occupational profile is likely to lead to prolonged rehabilitation,and permanent functional limitations.Our results might be useful for adjusting preventive measures in cluster risk groups.

Design and Implementation of Hand Gesture Detection System Using HM Model for Sign Language Recognition Development

Gesture detection is the primary and most significant step for sign language detection and sign language is the communication medium for people with speaking and hearing disabilities. This paper presents a novel method for dynamic hand gesture detection using Hidden Markov Models (HMMs) where we detect different English alphabet letters by tracing hand movements. The process involves skin color-based segmentation for hand isolation in video frames, followed by morphological operations to enhance image trajectories. Our system employs hand tracking and trajectory smoothing techniques, such as the Kalman filter, to monitor hand movements and refine gesture paths. Quantized sequences are then analyzed using the Baum-Welch Re-estimation Algorithm, an HMM-based approach. A maximum likelihood classifier is used to identify the most probable letter from the test sequences. Our method demonstrates significant improvements over traditional recognition techniques in real-time, automatic hand gesture recognition, particularly in its ability to distinguish complex gestures. The experimental results confirm the effectiveness of our approach in enhancing gesture-based sign language detection to alleviate the barrier between the deaf and hard-of-hearing community and general people.

Non-steroidal anti-inflammatory drugs in postoperative hand fracture management:Do they positively or negatively impact recovery?

This editorial explores the impact of non-steroidal anti-inflammatory drugs(NSAIDs)on postoperative recovery in hand fracture patients,amidst shifting pain management strategies away from opioids due to their adverse effects.With hand fractures being significantly common and postoperative pain management crucial for recovery,the potential of NSAIDs offers a non-addictive pain control alternative.However,the controversy over NSAIDs'effects on bone healing—stemming from their Cyclooxygenase-2 inhibition and associated risks of fracture non-union or delayed union—necessitates further investigation.Despite a comprehensive literature search,the study finds a lack of specific research on NSAIDs in postoperative hand fracture management,highlighting an urgent need for future studies to balance their benefits against possible risks.

Epidemiology of Hand Injuries That Presented to the Emergency Department of a Tertiary Care Facility in Suburban Mumbai, India: A Study Including 489 Patients

Background: Hand injuries are very common and responsible for a significant number of emergency department (ED) visits, most of which are not to hand specialists [1]. The functionality and outcome of hand injuries can vary significantly depending on the mechanism and pattern of injuries, which is why it is imperative for emergency physicians to recognize the complexities, and the potential repercussion of missed injuries in such cases. Objective: The aim of this study is to provide epidemiological information on hand injuries and their patterns. The objective is 1) to assess whether most hand injuries are superficial (simple), or involve underlying deeper structures (complex) and 2) to assess whether most hand injuries presented to the emergency department were managed by the emergency physician or plastic/orthopaedic surgeon. Methods: This retrospective single-centre observational study conducted at an emergency department in a tertiary care hospital in Mumbai, India collected data from hand trauma patients using a standardized documentation form. Demographic data, trauma-related data, and disposition plans were analysed. Results: A total of 489 cases sustained hand injuries over a period of one year. The patients were predominantly males in the 20 - 30 year age group and injuries were mainly sustained over the right hand. Most of the injuries were sustained at home (42%). The most common mechanism (34%) was sharp object injury (including needle-stick and other sharps in hospital), followed by blunt injury (30%). Among grievous hand injuries, door jamb was a mechanism noted in 11% of patients, accounting for 50% of all crush injuries. Lacerations were the most common pattern (24.7%) noticed, followed closely by fractures (23.3%). Digits II - IV were injured most commonly (54%), followed by carpals (14%) and the thumb (10%). Nearly 80% of the hand injuries were managed by emergency physicians alone, with 61% of cases involving superficial structures. Though 14% of the cases required plastic surgery intervention, the initial evaluation of all these patients was performed by the emergency physician. Conclusions: Our study highlights the burden of hand injuries on the emergency physician, as well as the odds of missed injuries, directly indicating the necessity of a thorough anatomical knowledge of the structures of the hand, and in turn, a proper physical examination. A dedicated registry for hand trauma would help quantify the mechanism and pattern of injuries, and formulate preventive strategies.