Gesture Recognition Algorithm of Human Motion Target Based on Deep Neural Network

To address the problems of the traditional human motion gesture tracking and recognition methods, such as poor tracking effect, low recognition accuracy, high frame loss rate, and long-time cost, a dynamic human motion gesture tracking and recognition algorithm using multimode deep learning was proposed. Firstly, the collected human motion images are repaired in the three-dimensional (3D) environment, and the multimodal 3D human motion model is reconstructed using the processed images. Secondly, according to the results of model reconstruction, the camera gesture and other parameters of the keyframe are used to construct the target tracking optimization function so as to achieve the purpose of accurate tracking of human motion. Finally, for multimodal human motion gesture learning, a convolutional neural network (CNN) is developed. The trained CNN is utilized to complete dynamic human motion recognition after convolutional and pooling calculations. The results demonstrate that the proposed algorithm is effective in tracking human motion gestures. The average recognition accuracy is 96%, the average frame loss rate is 8.8%, the time cost is low, and the proposed algorithm has a high F-measure and much lower power consumption than other algorithms, indicating that the proposed algorithm is effective.

Classification of Bisyllabic Lexical Stress Patterns Using Deep Neural Networks

The main work of human motion gesture recognition is to recognize and analyze the behavior of human objects in the video. Although the current research in the field of human motion gesture recognition has achieved certain results, the human motion gesture recognition in real life scenes has great effects due to factors such as camera movement, target scale transformation, dynamic background, viewing angle, and illumination. This article first proposes a new method of constructing human motion posture features to describe human behavior. This method is based on deep convolutional neural network features and topic models. Experiments have verified that compared with the traditional feature map extracted from the convolutional neural network fully connected layer, the feature map extracted from the convolutional neural network convolutional layer is not only lower in dimension but also has higher discrimination. Secondly, based on the feature map of the convolutional neural network, the training map downsampling strategy is used to overcome the interference caused by the object's scale change and shape change. Finally, based on the basketball gesture recognition method, the behavior performance of the legs and arms in 9 basketball actions of walking, running, jumping, standing dribbling, walking dribbling, running dribbling, shooting, passing and receiving is analyzed. As well as the corresponding signal waveform characteristics, a two-stage data division method for basketball is proposed. The unit action data is extracted for analysis to realize feature extraction. In order to select the most suitable classifier for basketball gesture recognition, the constructed feature vector uses four Different classifiers are trained to construct different classifiers to realize the division of actions.

Heartbeat classification is a crucial step for arrhythmia diagnosis during electrocardiographic (ECG) analysis. The new scenario of wireless body sensor network- (WBSN-) enabled ECG monitoring puts forward a higher-level demand for this traditional ECG analysis task. Previously reported methods mainly addressed this requirement with the applications of a shallow structured classifier and expert-designed features. In this study, modified frequency slice wavelet transform (MFSWT) was firstly employed to produce the time-frequency image for heartbeat signal. Then the deep learning (DL) method was performed for the heartbeat classification. Here, we proposed a novel model incorporating automatic feature abstraction and a deep neural network (DNN) classifier. Features were automatically abstracted by the stacked denoising auto-encoder (SDA) from the transferred time-frequency image. DNN classifier was constructed by an encoder layer of SDA and a softmax layer. In addition, a deterministic patient-specific heartbeat classifier was achieved by fine-tuning on heartbeat samples, which included a small subset of individual samples. The performance of the proposed model was evaluated on the MIT-BIH arrhythmia database. Results showed that an overall accuracy of 97.5% was achieved using the proposed model, confirming that the proposed DNN model is a powerful tool for heartbeat pattern recognition.

Human gesture recognition and motion representation has become a vital base of current intelligent human-machine interfaces because of ubiquitous and more comfortable interaction. Human-Gesture recognition chiefly deals with recognizing meaningful, expressive body movements involving physical motions of face, head, arms, fingers, hands or body. This review article presents a concise overview of optimal human-gesture and motion representation of medical images. This paper surveys various works undertaken on human gesture design and discusses various design methodologies used for image segmentation and gesture recognition. It further provides a general idea of modeling techniques for analysing hand gesture images and even discusses the diverse techniques involved in motion recognition. This survey provides an insight into various efforts and developments made in the gesture/motion recognition domain through analyzing and reviewing the procedures, datasets, recognition rates and approaches employed for identifying diverse human motions and gestures for supporting better and devising improved applications in near future.

Due to the advent of modern embedded systems and mobile devices with constrained resources, there is a great demand for incredibly efficient deep neural networks for machine learning purposes. There is also a growing concern of privacy and confidentiality of user data within the general public when their data is processed and stored in an external server which has further fueled the need for developing such efficient neural networks for real-time inference on local embedded systems. The scope of our work presented in this paper is limited to image classification using a convolutional neural network. A Convolutional Neural Network (CNN) is a class of Deep Neural Network (DNN) widely used in the analysis of visual images captured by an image sensor, designed to extract information and convert it into meaningful representations for real-time inference of the input data. In this paper, we propose a neoteric variant of deep convolutional neural network architecture to ameliorate the performance of existing CNN architectures for real-time inference on embedded systems. We show that this architecture, dubbed CondenseNeXt, is remarkably efficient in comparison to the baseline neural network architecture, CondenseNet, by reducing trainable parameters and FLOPs required to train the network whilst maintaining a balance between the trained model size of less than 3.0 MB and accuracy trade-off resulting in an unprecedented computational efficiency.

Outside the highly publicized victories in the game of Go, there have been numerous successful applications of deep learning in the fields of information retrieval, computer vision, and speech recognition. In cybersecurity, an increasing number of companies have begun exploring the use of deep learning (DL) in a variety of security tasks with malware detection among the more popular. These companies claim that deep neural networks (DNNs) could help turn the tide in the war against malware infection. However, DNNs are vulnerable to adversarial samples, a shortcoming that plagues most, if not all, statistical and machine learning models. Recent research has demonstrated that those with malicious intent can easily circumvent deep learning-powered malware detection by exploiting this weakness. To address this problem, previous work developed defense mechanisms that are based on augmenting training data or enhancing model complexity. However, after analyzing DNN susceptibility to adversarial samples, we discover that the current defense mechanisms are limited and, more importantly, cannot provide theoretical guarantees of robustness against adversarial sampled-based attacks. As such, we propose a new adversary resistant technique that obstructs attackers from constructing impactful adversarial samples by randomly nullifying features within data vectors. Our proposed technique is evaluated on a real world dataset with 14,679 malware variants and 17,399 benign programs. We theoretically validate the robustness of our technique, and empirically show that our technique significantly boosts DNN robustness to adversarial samples while maintaining high accuracy in classification. To demonstrate the general applicability of our proposed method, we also conduct experiments using the MNIST and CIFAR-10 datasets, widely used in image recognition research.

Many drink packages have expiry dates written in dot matrix characters (digits and non-digits, e.g., slashes or dots). We collected images of these packages and trained two existing deep neural networks (DNNs) to combine and form a system for detecting and recognizing expiry dates on drink packages. One of the DNNs is an object-detection DNN and the other is a character-recognition DNN. The object-detection DNN alone can localize the characters written on a drink package but its recognition accuracy is not sufficient. The character-recognition DNN alone cannot localize characters but has good recognition accuracy. Because the system is a combination of these two DNNs, it improves the recognition accuracy. The object-detection DNN is first used to detect and recognize the expiry date by localizing and obtaining the size of the character. It then scans the expiry-date region and clips the image. The character-recognition DNN then recognizes the characters from the clipped images. Finally, the system uses both DNNs to obtain the most accurate recognition result based on the spacing of the digits. We conducted an experiment to recognize the expiry dates written on the drink package. The experimental results indicate that the recognition accuracy of the object-detection DNN alone was 90%, that of the character-recognition DNN alone was also 90%, and that combining the results of both DNNs was 97%.

Deep Neural Networks (DNN) have strong capabilities of memories, feature identifications and automatic analyses, solving various complex problems. However, DNN classifiers have obvious fragility that adding several unnoticeable perturbations to the original examples will lead to the errors in the classifier identification. In the field of communications, the adversarial examples will greatly reduce the accuracy of the signal identification, causing great information security risks. Considering the adversarial examples pose a serious threat to the security of the DNN models, studying their generation mechanisms and testing their attack effects are critical to ensuring the information security of the communication networks. This paper will study the generation of the adversarial examples and the influences of the adversarial examples on the accuracy of the DNN-based communication signal identification. Meanwhile, this paper will study the influences of the adversarial examples under the white-box models and black-box models, and explore the adversarial attack influences of the factors such as perturbation levels and iterative steps. The insights of this study would be helpful for ensuring the security of information networks and designing robust DNN communication networks.

In recent years, machine learning is applied in the bioinformatics and medical fields to analyze relationships among biological features and behaviors. However, it is difficult to discover the significant features of large-scale datasets. A novel feature extraction method called bioinformatic explainable deep neural network (BioExpDNN) is proposed to filter the critical features with strong influences on the dataset and to explain the interaction of features. In the practical experiments, this study adopted three biomedical science datasets from the UCI (University of California, Irvine) Machine Learning Repository: (1). Cryotherapy Data Set (CDS) contains 6 attributes and 2 classes (i.e., recovery and non-recovery); (2). Cervical Cancer Behavior Risk Data Set (CCBRDS) consists of 18 attributes and 2 classes (i.e., cervical cancer patient and healthy body); (3). Heart Failure Clinical Records Data Set (HFCRDS) includes 12 clinical attributes and 2 classes (i.e., death and life). In comparison results, extracted features were considered as inputs of a classifier based on deep neural network for classification. The classification accuracy was selected as an evaluation factor to evaluate the performance of feature extraction methods. The experimental results showed that the classification accuracies of CDS, CCBRDS, and HFCRDS were 92.59%, 100%, and 78.9%, respectively.

Characterizing biobehavioral time series data recorded under different task conditions is a critical step in neuroscience data analysis. The inherent complexity and stochasticity present in these data pose significant modeling challenges. Deep Neural Network (DNN) models have been widely adopted for analyzing such data. Despite their success, DNNs have significant limitations: they are sensitive to noise in training data and require large training datasets. These issues limit the applicability of DNNs to neuroscience data - where sample size is often smaller and data are volatile and feature noise artifacts. The present manuscript introduces a novel framework that embeds a state-space model (SSM) in the classic DNN structure. We demonstrate that this framework, which we call SSM-DNN, can overcome the sample size and noise sensitivity issues that plague classic DNNs. For this purpose, we illustrate training and inference steps when SSM-DNN is applied to a dataset recorded during a Death Implicit Association Test (D-IAT) task. This task was designed to produce biobehavioral data that facilitate decoding of participant phenotypes (e.g., person with depression vs. psychologically healthy person). We show SSM-DNN performance reaches an accuracy of 78%, which is 20% higher than state-of-art DNN decoder models. Its area under curve (AUC) is 0.8, which reflects its high specificity and sensitivity. The SSM-DNN modeling framework is scalable to high-dimensional time-series data and it can be applied broadly to neuroscience data, providing a robust and accurate decoding performance.

With the continuous development of computer artificial intelligence technology, various applications based on artificial intelligence emerge in an endless stream, among which video image recognition technology is the most widely used in life. This article starts from the process of image recognition, based on the composite characteristics of artificial intelligence and video images, to discuss human gesture recognition technology.This article uses the feature extraction algorithm for image composite feature extraction as a method, and conducts human body movement collection experiments, analyzes the database and The gesture recognition step. This paper mainly introduces the extraction method of image composite features and the basic requirements of gesture recognition, and through the algorithm calculation of feature extraction, the function of human gesture recognition video and image composite features is completed, and the human action collection experiment is carried out to confirm. The results of images and data show the advantages of the algorithm support used in this article. We will Dmti. MsHOG is compared with other methods in the three subsets. In terms of the accuracy of all tests, our method performs better than other methods. The results show that the MSHOG (Multi-scale Histogram of Oriented Gradients) descriptor can represent the unique characteristics of human behavior, reflecting the effectiveness of our proposed method. In particular, this method achieved 100% recognition accuracy in Test, with an average recognition accuracy of 94.91%, which is significantly better than existing methods.

Recently, adversarial attacks have shown to lead the state-of-the-art deep neural networks (DNNs) to misclassification. However, most adversarial attacks are generated according to whether they are perceptual to human visual system, measured by geometric metrics such as the l2-norm, which ignores the common watermarks in cyber-physical systems. In this paper, we propose a fast adversarial watermark attack (FAWA) method based on fast differential evolution technique, which optimally superimposes a watermark on an image to fool DNNs. We also attempt to explain the reason why the attack is successful and propose two hypotheses on the vulnerability of DNN classifiers and the influence of the watermark attack on higher-layer features extraction respectively. In addition, we propose two countermeasure methods against FAWA based on random rotation and median filtering respectively. Experimental results show that our method achieves 41.3% success rate in fooling VGG-16 and have good transferability. Our approach is also shown to be effective in deceiving deep learning as a service (DLaaS) systems as well as the physical world. The proposed FAWA, hypotheses, and the countermeasure methods, provide a timely help for DNN designers to gain some knowledge of model vulnerability while designing DNN classifiers and related DLaaS applications.

Deep neural networks (DNNs) have transformed several artificial intelligence research areas including computer vision, speech recognition, and natural language processing. However, recent studies demonstrated that DNNs are vulnerable to adversarial manipulations at testing time. Specifically, suppose we have a testing example, whose label can be correctly predicted by a DNN classifier. An attacker can add a small carefully crafted noise to the testing example such that the DNN classifier predicts an incorrect label, where the crafted testing example is called adversarial example. Such attacks are called evasion attacks. Evasion attacks are one of the biggest challenges for deploying DNNs in safety and security critical applications such as self-driving cars.

Single-shot readout of charge and spin states by charge sensors such as quantum point contacts and quantum dots are essential technologies for the operation of semiconductor spin qubits. The fidelity of the single-shot readout depends both on experimental conditions such as signal-to-noise ratio, system temperature, and numerical parameters such as threshold values. Accurate charge sensing schemes that are robust under noisy environments are indispensable for developing a scalable fault-tolerant quantum computation architecture. In this study, we present a novel single-shot readout classification method that is robust to noises using a deep neural network (DNN). Importantly, the DNN classifier is automatically configured for spin-up and spin-down traces in any noise environment by tuning the trainable parameters using the datasets of charge transition signals experimentally obtained at a charging line. Moreover, we verify that our DNN classification is robust under noisy environment in comparison to the two conventional classification methods used for charge and spin state measurements in various quantum dot experiments.