Recognition Device Research Articles

Evaluation of Pattern Recognition Techniques in Response to Cardiac Resynchronization Therapy (CRT)

Cardiac resynchronization therapy (CRT) improves cardiac function in patients with heart failure (HF), and the result of this treatment is decrease in death rate and improving quality of life for patients. This research is aimed at predicting CRT response for the prognosis of patients with heart failure under CRT. According to international instructions, in the case of approval of QRS prolongation and decrease in ejection fraction (EF), the patient is recognized as a candidate of implanting recognition device. However, regarding many intervening and effective factors, decision making can be done based on more variables. Computer-based decision-making systems especially machine learning (ML) are considered as a promising method regarding their significant background in medical prediction. Collective intelligence approaches such as particles swarm optimization (PSO) algorithm are used for determining the priorities of medical decision-making variables. This investigation was done on 209 patients and the data was collected over 12 months. In HESHMAT CRT center, 17.7% of patients did not respond to treatment. Recognizing the dominant parameters through combining machine recognition and physician’s viewpoint, and introducing back-propagation of error neural network algorithm in order to decrease classification error are the most important achievements of this research. In this research, an analytical set of individual, clinical, and laboratory variables, echocardiography, and electrocardiography (ECG) are proposed with patients’ response to CRT. Prediction of the response after CRT becomes possible by the support of a set of tools, algorithms, and variables.

Virtual reality gesture recognition based on depth information

With the rapid development of computer technology, the information revolution is constantly affecting and changing our lives. Today’s virtual reality technology is no longer just a virtual model for viewing. Experiencers are more willing to personally interact with the virtual environment in a virtual scene to increase their sense of gaming experience.Today’s virtual reality interaction methods mainly interact through the handles that come with VR helmets. Previously, some scholars have researched gesture interaction in virtual environments. They use data gloves to obtain information about hand movements. This method makes users have to wear heavy data gloves, which limits the natural movement of their hands. To overcome this shortcoming, the need for low‐cost vision‐based virtual reality gesture interaction is becoming more and more urgent.Traditional gesture recognition technologies based on artificial modeling include template‐based matching, data‐based gloves, and machine learning. As machine learning gesture classifiers, Hidden Markov Model (HMM) and Support Vector Machine (SVM) [1] have been widely used. However, in the hand motion detection of ordinary cameras, the image is prone to speckles, lighting changes, and other factors, which seriously affects the performance of the classifier, making it difficult to accurately and efficiently detect the first image when the background is complex and the lighting is affected. In recent years, deep learning‐based object detection methods have achieved great breakthroughs [2]. In the past decade, many deep learning‐based dynamic gesture recognition algorithms have been introduced. In the case of changing lighting conditions, in order to improve the classification accuracy of gesture recognition [3]. Therefore, this article chooses a depth camera combined with HTC VIVE device for gesture recognition in virtual reality. First obtain the depth image of the hand through the depth camera, then label the depth image, and then learn through the deep learning network hand movement training [4], preprocess the detected human hand image, and recognize it by hand detection The position of the hand in the image is obtained, and the movement of the hand is recognized as a result of recognition.The algorithm in this paper uses the advanced deep learning network YOLOv3, and changes the network structure and multi‐scale structure based on the original network. This algorithm is compared with other deep learning algorithms for gesture recognition, and the recognition effect is better than other algorithms in the same category.

Gesture Classification for a Hand Controller Device Using Neural Networks.

This paper presents a convolutional neural network-based classification of the hand flexion and extension gestures used in wrist recovery after injury. The hand gesture recognition device used in our study is the Leap Motion controller. The Leap Motion device's inability to accurately differentiate the left hand from the right hand when performing hand rotation gestures was eliminated by introducing hand and thumb direction vectors into the database used to train the neural network. A 3D environment was created for the introduction of the data describing the gesture into the database. A classification accuracy of 95% was achieved for the hand flexion and extension gesture divided into three levels for each hand. The populated database may also be used to classify other gestures involving hand rotation.

A Novel Fingerprint Recovery Scheme using Deep Neural Network-based Learning

Minutiae used in most fingerprint recognition devices is robust to presentation attack, but generates a high false match rate. Thus, it is applied along with orientation map or skeleton images. There has been plenty of research on security vulnerability of minutiae, whereas few research has been conducted on orientation map or skeleton images. This study analyzes vulnerability of presentation attack for skeleton images. For this purpose, it proposes a new algorithm of recovering fingerprints with the use of machine learning and skeleton image features of fingerprints. In the proposed method, we suggest the new machine learning Pix2Pix model to generate more natural images. The suggested model is developed in the way of adding a latent vector to the conventional image-to-image translation model Pix2Pix. In the experiment, fingerprints were recovered with the use of the proposed Pix2Pix model, and it was found that a fingerprint recognition device which recognized the recovered fingerprints had a high success rate of recognition. Therefore, it was proved that a fingerprint recognition device using skeleton images as well was vulnerable to presentation attack. It is expected that the algorithm proposed in this study will be very useful to many different application areas related to image processing, including biometrics, fingerprint recognition and recovery, and image surveillance.

VIDEO SURVEILLANCE SYSTEMS FOR RAILWAY TRANSPORT

The article is devoted to analysis of ways to increase train traffic safety. One of ways to reduce accident rate on railways is timely detection of dangerous objects and notification of all traffic participants, primarily, the driver. Such a notification can be performed with the help of intelligent video surveillance system (IVS). The objective of the article is to study the possibility of using IVS to increase train traffic safety. Method (way to achieve the objective) consists of several stages: development of criteria of compliance of functional possibilities of IVS with tasks to increase train traffic safety, assessment, and calculation of permissible values of fitting criteria. The work suggests a scheme of organization of IVS based on fiber-optic data transmission system (FOTS) and data transmission network, highlights advantages and disadvantages of IVS, formulates requirements for IVS. Advantage of video surveillance is availability of video information about an object to a train driver, which allows to timely prevent an accident. Disadvantage of IVS is high probability of false detection, which can lead to false triggering of a system. To reduce the number of false triggering there are two ways: improvement of algorithms of video analytics in recognition device (RD) and increase of quality of video signals at the input of RD. The work is devoted to reduction of probability of false triggering due to improvement of communication quality. It is noted that an efficient method is the use of a new element base of electronics based on nanostructured materials. These materials allow to improve optoelectronic characteristics of main elements of IVS which are photosensors and photoreceivers.

Selfie interior: a fotografia como experiência estética de autorreconhecimento

Este artigo relata e discute uma experiência estética na qual a imagem fotográfica é inicialmente pensada sob a perspectiva de mediar as relações do eu com o mundo, do modo como vemos a nós mesmos e nos vemos também no outro e pelo outro. Baseou-se em um projeto denominado Selfie Interior, realizado com um grupo de estudantes universitários convidados a criar representações possíveis de si mesmos não por meio da própria imagem, mas mediante um olhar para aquilo no qual se veem representados. O percurso do projeto incluiu práticas de sensibilização e posteriormente de fotografia, a partir das quais este trabalho buscou compreender como se dá a construção de identidade na sociedade midiatizada, em relações cada vez mais intensas de interação entre o ser humano e os aparatos tecnológicos de comunicação e informação. A metodologia utilizada incluiu uma reflexão sobre o conceito Selfie Interior a partir de revisão bibliográfica que trouxe ideias como as de “bios mediático” (Sodré, 2002), de “sociedade em midiatização” (Braga, 2006) e de “pós-fotografia” (Fontcuberta, 2016) e discute o “ato de ver” (Didi-Huberman, 2010) e a “ação de fotografar” (Sontag, 2004). O que se viu nos trabalhos desenvolvidos pelos estudantes e está relatado no artigo são intensas experiências estéticas, nas quais aparecem relações de alteridade por meio da fotografia como dispositivo de reconhecimento de si próprio e de reconhecimento de um eu que existe no outro.

Deep Learning-Based Human Activity Real-Time Recognition for Pedestrian Navigation

Several pedestrian navigation solutions have been proposed to date, and most of them are based on smartphones. Real-time recognition of pedestrian mode and smartphone posture is a key issue in navigation. Traditional ML (Machine Learning) classification methods have drawbacks, such as insufficient recognition accuracy and poor timing. This paper presents a real-time recognition scheme for comprehensive human activities, and this scheme combines deep learning algorithms and MEMS (Micro-Electro-Mechanical System) sensors’ measurements. In this study, we performed four main experiments, namely pedestrian motion mode recognition, smartphone posture recognition, real-time comprehensive pedestrian activity recognition, and pedestrian navigation. In the procedure of recognition, we designed and trained deep learning models using LSTM (Long Short-Term Memory) and CNN (Convolutional Neural Network) networks based on Tensorflow framework. The accuracy of traditional ML classification methods was also used for comparison. Test results show that the accuracy of motion mode recognition was improved from , which was the highest accuracy and obtained by SVM (Support Vector Machine), to (LSTM) and (CNN); the accuracy of smartphone posture recognition was improved from , which is the highest accuracy and obtained by NN (Neural Network), to (LSTM) and (CNN). We give a model transformation procedure based on the trained CNN network model, and then obtain the converted model, which can be run in Android devices for real-time recognition. Real-time recognition experiments were performed in multiple scenes, a recognition model trained by the CNN network was deployed in a Huawei Mate20 smartphone, and the five most used pedestrian activities were designed and verified. The overall accuracy was up to . Overall, the improvement of recognition capability based on deep learning algorithms was significant. Therefore, the solution was helpful to recognize comprehensive pedestrian activities during navigation. On the basis of the trained model, a navigation test was performed; mean bias was reduced by more than 1.1 m. Accordingly, the positioning accuracy was improved obviously, which is meaningful to apply DL in the area of pedestrian navigation to make improvements.

A Soft Resistive Acoustic Sensor Based on Suspended Standing Nanowire Membranes with Point Crack Design

AbstractAn artificial basilar membrane (ABM) is an acoustic transducer that mimics the mechanical frequency selectivity of the real basilar membrane, which has the potential to revolutionize current cochlear implant technology. While such ABMs can be potentially realized using piezoelectric, triboelectric, and capacitive transduction methods, it remains notoriously difficult to achieve resistive ABM due to the poor frequency discrimination of resistive‐type materials. Here, a point crack technology on noncracking vertically aligned gold nanowire (V‐AuNW) films is reported, which allows for designing soft acoustic sensors with electric signals in good agreement with vibrometer output—a capability not achieved with corresponding bulk cracking system. The strategy can lead to soft microphones for music recognition comparable to the conventional microphone. Moreover, a soft resistive ABM is demonstrated by integrating eight nanowire‐based sensor strips on a soft trapezoid frame. The wearable ABM exhibits high‐frequency selectivity in the range of 319–1951 Hz and high sensitivity of 0.48–4.26 Pa−1. The simple yet efficient fabrication in conjunction with programmable crack design indicates the promise of the methodology for a wide range of applications in future wearable voice recognition devices, cochlea implants, and human–machine interfaces.

An Investigation of the Free Energy Principle for Emotion Recognition.

This paper offers a prospectus of what might be achievable in the development of emotional recognition devices. It provides a conceptual overview of the free energy principle; including Markov blankets, active inference, and—in particular—a discussion of selfhood and theory of mind, followed by a brief explanation of how these concepts can explain both neural and cultural models of emotional inference. The underlying hypothesis is that emotion recognition and inference devices will evolve from state-of-the-art deep learning models into active inference schemes that go beyond marketing applications and become adjunct to psychiatric practice. Specifically, this paper proposes that a second wave of emotion recognition devices will be equipped with an emotional lexicon (or the ability to epistemically search for one), allowing the device to resolve uncertainty about emotional states by actively eliciting responses from the user and learning from these responses. Following this, a third wave of emotional devices will converge upon the user's generative model, resulting in the machine and human engaging in a reciprocal, prosocial emotional interaction, i.e., sharing a generative model of emotional states.

Streaming of Repeated Noise in Primary and Secondary Fields of Auditory Cortex.

Statistical regularities in natural sounds facilitate the perceptual segregation of auditory sources, or streams. Repetition is one cue that drives stream segregation in humans, but the neural basis of this perceptual phenomenon remains unknown. We demonstrated a similar perceptual ability in animals by training ferrets of both sexes to detect a stream of repeating noise samples (foreground) embedded in a stream of random samples (background). During passive listening, we recorded neural activity in primary auditory cortex (A1) and secondary auditory cortex (posterior ectosylvian gyrus, PEG). We used two context-dependent encoding models to test for evidence of streaming of the repeating stimulus. The first was based on average evoked activity per noise sample and the second on the spectro-temporal receptive field. Both approaches tested whether differences in neural responses to repeating versus random stimuli were better modeled by scaling the response to both streams equally (global gain) or by separately scaling the response to the foreground versus background stream (stream-specific gain). Consistent with previous observations of adaptation, we found an overall reduction in global gain when the stimulus began to repeat. However, when we measured stream-specific changes in gain, responses to the foreground were enhanced relative to the background. This enhancement was stronger in PEG than A1. In A1, enhancement was strongest in units with low sparseness (i.e., broad sensory tuning) and with tuning selective for the repeated sample. Enhancement of responses to the foreground relative to the background provides evidence for stream segregation that emerges in A1 and is refined in PEG.SIGNIFICANCE STATEMENT To interact with the world successfully, the brain must parse behaviorally important information from a complex sensory environment. Complex mixtures of sounds often arrive at the ears simultaneously or in close succession, yet they are effortlessly segregated into distinct perceptual sources. This process breaks down in hearing-impaired individuals and speech recognition devices. By identifying the underlying neural mechanisms that facilitate perceptual segregation, we can develop strategies for ameliorating hearing loss and improving speech recognition technology in the presence of background noise. Here, we present evidence to support a hierarchical process, present in primary auditory cortex and refined in secondary auditory cortex, in which sound repetition facilitates segregation.

A Customized Convolutional Neural Network Model Integrated With Acceleration-Based Smart Insole Toward Personalized Foot Gesture Recognition

Foot gestures play an important role in human machine interface and also indicate the lower-limb motor functionalities. Lately, machine learning models have been integrated with different kinds of wearable devices for foot gesture recognition. However, most existing wearable devices lack of robustness and facileness and existing machine learning models suffer from inconsistent recognition accuracy due to limited and unbalanced training datasets and, therefore, do not work well for new users. To address this, a customized convolutional neural network model architecture is designed, and strategies for achieving personalized models are presented, considering potential fairness sensitive attributes of a diverse training group, including age, gender, body mass index (defined by height and weight), shoe size, and health conditions. The proposed model to be embodied into a flexible smart insole with only two accelerometers aims to recognize four types of foot gestures-toe tapping, heel tapping, foot kicking, and foot stepping-in a sitting posture at high accuracies. After the hyperparameters are well-tuned, average recognition accuracy reaches 92% in training sets, 88.05% in validation sets, 85.27% in test sets, and 83.09% in fivefold cross-validation. The evaluation results from both in-group and leave-one-subject-out show that our unified model is easily transformable for individual uses by further fine-tuning the key hyperparameters.

A Hidden Fingerprint Device on an Opaque Display Panel

In recent years, fingerprint recognition has become more and more widely used in mobile phones. A fingerprint recognition device hidden under an opaque display panel designed based on a waveguide and frustrated total internal reflection (FTIR) is proposed and demonstrated herein. In order to meet the demand for a high screen ratio for mobile phone displays, we use a symmetrical zoom-in and zoom-out coupler design. With this comprehensive coupler and waveguide design, not only can fingerprint recognition be achieved using an opaque display panel, but it also meets the appearance requirements for a mobile phone with a high screen ratio.

The Translational Potential of Electrochemical DNA-Based Liquid Biopsy.

Latest technological advancement has tremendously expanded the knowledge on the composition of body fluids and the cancer-associated changes, which has fueled the replacement of invasive biopsies with liquid biopsies by using appropriate specific receptors. DNA emerges as a versatile analytical reagent in electrochemical devices for hybridization-based or aptamer-based recognition of all kind of biomarkers. In this mini review, we briefly introduce the current affordable targets (tumor-derived nucleic acids, circulating tumor cells and exosomes) in body fluids, and then we provide an overview of selected electrochemical methods already applied in clinical samples by dividing them into three large categories according to sample type: red (blood), yellow (urine), and white (saliva and sweat) diagnostics. This review focuses on the hurdles of the complex matrices rather than a comprehensive and detailed revision of the format schemes of DNA-based electrochemical sensing. This diverse perspective compiles some challenges that are often forgotten and critically underlines real sample analysis or clinical validation assays. Finally, the needs and trends to reach the market are briefly outlined.

Software Development Framework for Real-Time Face Detection and Recognition in Mobile Devices

With the rapid use of Android OS in mobile devices and related products, face recognition technology is an essential feature, so that mobile devices have a strong personal identity authentication. In this paper, we propose Android based software development framework for real-time face detection and recognition using OpenCV library, which is applicable in several mobile applications. Initially, the Gaussian smoothing and gray-scale transformation algorithm is applied to preprocess the source image. Then, the Haar-like feature matching method is used to describe the characteristics of the operator and obtain the face characteristic value. Finally, the normalization method is used to match the recognition of face database. To achieve the face recognition in the Android platform, JNI (Java Native Interface) is used to call the local Open CV. The proposed system is tested in real-time in two different brands of smart phones, and results average success rate in both devices for face detection and recognition is 95% and 80% respectively.

A colour recognition device for the visually disabled people

<p>Visually disabled people rely on the sense of touch and sense of hearing to help them recognise anything in their everyday life. Colours, however, is also important in giving information about things such as the colour of cash note (blue, green, red, orange and purple), the colour of spices (yellow turmeric, red chilli, green chilli) and colour of cloth. Without a sense of visual, they are not able to recognise colour and perceive the beauty of colour. This study was conducted to develop a colour recognizer for visually <strong><em>‎</em></strong>disabled people<strong><em>‎</em></strong>. Colour recogniser used the colour sensor to sense the colour, microcontroller to recognise the colour and notify the user using a speech generator and speaker. The device is powered by dry cell batteries and designed to be user-friendly, practical and portable. The testing is done to show that this device was able to sense and differentiate 12 primary colours in the RGB colour wheel and validated the accuracy of this devices.</p>

A self-powered flexible-vision electronic skin based on piezophototronic GaN nanowires for rapid image recognition

A self-powered flexible-vision electronic skin for rapid image recognition has been fabricated from piezophototronic GaN nanowires. The basic structure of each photodetecting pixel consists of horizontally-aligned GaN nanowires crossing a cross-finger electrode, and 6 × 6 photodetecting pixels that form a patterned sensing matrix. The working mechanism is based on the piezophototronic effect, and the device can harvest a tiny amount of mechanical energy and directly output photodetecting signals without any external electrical power. The output piezoelectric voltage is significantly dependent on UV illumination, and the response is up to ~76 for 80 µW cm−2 light. The response and recovery times are very short. A practical application of the device for rapid image recognition has been simply demonstrated, and this shows the potential for realizing an artificial intelligent retina. This work can promote the development of wearable flexible electronics and expand the scope of self-powered nanosystems.

Larger contactor area increases low-frequency vibratory sensitivity in hairy skin.

BackgroundIn research, assessing vibratory cutaneous sensitivity is an important research branch to quantify various diseases or to develop devices for pattern recognition. The measured vibration perception thresholds (VPTs), however, are subjective and usually result in a large data variability. This might induce difficulties to detect differences, for example, when comparing different anatomical locations. Hence, a higher ability to detect changes is desirable. Another feature of VPTs is spatial summation, but in the literature it is controversially discussed whether or not this phenomenon is also present in the lower frequency range. For these reasons, the present study aimed to investigate whether an enlarged matrix contactor area (measured at the hairy skin) induces improvements in subjective sensitivity using high and low frequencies, and whether a large contactor area is better able to identify changes of VPTs than a small contactor area of a single contactor. For each frequency, we hypothesized an increased sensitivity for the matrix compared to the single contactor. We also hypothesized that changes can be better-detected between the anatomical locations when using the matrix than the single contactor.MethodsTwenty healthy and young participants voluntarily took part in this study. Three anatomical locations at the torso were measured at the middle aspect of the lower back, middle lateral aspect of the upper arm, and the region just below the armpit. At each location, two frequencies (30, 200 Hz) and two contactor conditions (single contactor: 0.48 cm2 , contactor matrix: 9 × 0.48 cm2 = 4.32 cm2) were tested in a randomized order.ResultsSupporting our hypothesis, we found that improved cutaneous sensitivity after increasing the contactor size occurs not only at high, but also at low frequencies at all anatomical locations. Large contactor sizes resulted in higher sensitivity and in a superior ability to detect changes. The superior behavior of the matrix to exhibit a lower variability could not always be proven. This work may be relevant for future studies aiming to identify changes of VPTs in various patient groups, for example.

Intuitive gesture-based control system with collision avoidance for robotic manipulators

PurposeThis paper aims to present an intuitive control system for robotic manipulators that pairs a Leap Motion, a low-cost optical tracking and gesture recognition device, with the ability to record and replay trajectories and operation to create an intuitive method of controlling and programming a robotic manipulator. This system was designed to be extensible and includes modules and methods for obstacle detection and dynamic trajectory modification for obstacle avoidance.Design/methodology/approachThe presented control architecture, while portable to any robotic platform, was designed to actuate a six degree-of-freedom robotic manipulator of our own design. From the data collected by the Leap Motion, the manipulator was controlled by mapping the position and orientation of the human hand to values in the joint space of the robot. Additional recording and playback functionality was implemented to allow for the robot to repeat the desired tasks once the task had been demonstrated and recorded.FindingsExperiments were conducted on our custom-built robotic manipulator by first using a simulation model to characterize and quantify the robot’s tracking of the Leap Motion generated trajectory. Tests were conducted in the Gazebo simulation software in conjunction with Robot Operating System, where results were collected by recording both the real-time input from the Leap Motion sensor, and the corresponding pose data. The results of these experiments show that the goal of accurate and real-time control of the robot was achieved and validated our methods of transcribing, recording and repeating six degree-of-freedom trajectories from the Leap Motion camera.Originality/valueAs robots evolve in complexity, the methods of programming them need to evolve to become more intuitive. Humans instinctively teach by demonstrating the task to a given subject, who then observes the various poses and tries to replicate the motions. This work aims to integrate the natural human teaching methods into robotics programming through an intuitive, demonstration-based programming method.

A self-powered character recognition device based on a triboelectric nanogenerator

Character recognition is a technology that digitizes data stored on paper for permanent archiving. Character recognition processes are divided into two steps: those that convert a character on paper as a digital image (scanning), and those that infer a scanned image as a character (recognition). Optical scanners and cameras are conventionally used for the scanning process. However, noise and distortion, which lower the recognition rate, can occur with such optical method. Herein, a triboelectric nanogenerator (TENG) is utilized for the scanning process. The TENG converts mechanical energy into electrical energy based on contact electrification. A single-electrode TENG with multiple aluminum cells was fabricated as a character-recognition TENG (CR-TENG). Using the difference in the intensity of the contact electrification, the aluminum cells of the CR-TENG distinguished ink-printed paper from bare paper. The CR-TENG has advantages in that it consists only of aluminum on the substrate and does not require additional electrical energy to operate. The CR-TENG converted numerical patterns on paper into images and a pre-trained deep neural network inferred the images as digits. Through optimization of the scanning and recognition process, a high recognition rate was achieved with this new character recognition system based on the CR-TENG.

Pengembangan Perangkat Speech Recognition Bagi Penyandang Bisu Tuli Sebagai Sarana Komunikasi

This study aims to produce a design for the development of speech recognition devices for deaf-mute people to make it easier for the public to communicate with deaf mute visitors during emergencies by using a sound sensor that is speech recognition. Data collection techniques used were observation, questionnaires and documentation. Then the data collected will be analyzed using descriptive analysis. The results of the study were obtained from 25 respondents in the SLB of South Sulawesi Province Development, resulting in an overall average response rate of 80% from the highest value of 100% and the lowest value of 0%. This tool works with voice commands that have been done by the word train first first Then if the word is detected, the word will automatically appear on the LCD screen and simultaneously with the vibration produced by the vibrator. So it can be concluded that the speech recognition device for deaf mutes is good based on the respondent response category table.