Deep Learning Base Face Anti Spoofing -Convolutional Restricted Basis Neural Network Technique

By studying the effects of different types of feed forward neural networks in different fields, the applicable environment of different neural networks can be judged, which will make it easier for people to choose appropriate neural network when it's needed. To achieve this, in this article I summarize and classify the existing neural network experiences and feedback results, and compare the data before and after using the neural network. The data shows that BP networks can improve the resolution or accuracy of problems with no obvious influencing factors. Convolutional networks can increase the accuracy of image processing to more than 95%, and RBF networks can calculate high-precision data curves. Thus, it can be concluded that the BP network is suitable for solving problems with unclear influencing factors, the convolutional network has more image processing problems, and the RBF network has a higher frequency of use when higher results are required.

Gait recognition is a noncontact biometric procedure that determines the identity or health status of a person by analyzing his or her walking posture and habits, including skeletal and joint movements. The most remarkable feature of this method is the possibility of conducting recognition without demanding much cooperation from participants. Therefore, this recognition technique has attracted much attention from scholars. Additionally, because of the rapid development of graphics processing unit technology, related hardware and computation performance, the applications of deep-learning technology are considerably enhanced. The objective of this study was to apply a deep neural network (DNN), which employs deep-learning technology, to achieve gait-based automatic pedestrian detection and recognition. In contrast to using wearable devices to precisely capture skeletal and joint movements, pedestrian color-image sequences were used as input in this study. Subsequently, a pretraining convolutional neural network (CNN) was employed to capture pedestrian location and extract pedestrian dense optical flow to serve as concrete low-level feature inputs. Then, a finely-tuned DNN based on the wide residual network was employed to extract high-level abstract features. In addition, to overcome the difficulty of obtaining local temporal features by using a 2D CNN, part of the 3D convolutional structure was introduced into the CNN. This design enabled use of limited memory to acquire more effective features and enhance the DNN performance. The experimental results show that the proposed method has exceptional performance for pedestrian detection and recognition.

The study presents the results of the development and testing of deep learning neural network architectures, which demonstrate high accuracy rates in classifying neurophysiological data, in particular hemodynamic brain activation patterns obtained by functional near-infrared spectroscopy, during solving mathematical problems on spatial-numerical associations. The analyzed signal represents a multidimensional time series of oxyhemoglobin and deoxyhemoglobin dynamics. Taking the specificity of the fNIRS signal into account, a comparative analysis of 2 types of neural network architectures was carried out: (1) architectures based on recurrent neural networks: recurrent neural network with long short-term memory, recurrent neural network with long short-term memory with fully connected layers, bidirectional recurrent neural network with long short-term memory, convolutional recurrent neural network with long short-term memory; (2) architectures based on convolutional neural networks with 1D convolutions: convolutional neural network, fully convolutional neural network, residual neural network. Trained long short-term memory recurrent neural network architectures showed worse results in accuracy in comparison with 1D convolutional neural network architectures. Residual neural network (model_Resnet) demonstrated the highest accuracy rates in three experimental conditions more than 88% in detecting age-related differences in brain activation during spatial-numerical association tasks considering the individual characteristics of the respondents’ signal.

The past several years have seen both an explosion in the use of Convolutional Neural Networks (CNNs) and accelerators to make CNN inference practical. In the architecture community, the lion share of effort has targeted CNN inference for image recognition. The closely related problem of video recognition has received far less attention as an accelerator target. This is surprising, as video recognition is more computationally intensive than image recognition, and video traffic is predicted to be the majority of internet traffic in the coming years. This paper fills the gap between algorithmic and hardware advances for video recognition by providing a design space exploration and flexible architecture for accelerating 3D Convolutional Neural Networks (3D CNNs)—the core kernel in modern video understanding. When compared to (2D) CNNs used for image recognition, efficiently accelerating 3D CNNs poses a significant engineering challenge due to their large (and variable over time) memory footprint and higher dimensionality. To address these challenges, we design a novel accelerator called Morph, that can adaptively support different spatial and temporal tiling strategies depending on the needs of each layer of each target 3D CNN. We codesign a software infrastructure alongside the Morph hardware to find good-fit parameters to control the hardware. Evaluated on state-of-the-art 3D CNNs, Morph achieves up to 2.7× (1.9× average) reduction in energy consumption and improves performance/watt up to 4.4× (3× average) compared to a baseline 3D CNN accelerator, with an area overhead of 2%. Morph further achieves a 11.6× average energy reduction on 3D CNNs when compared to Eyeriss, a popular 2D CNN accelerator, while reducing efficiency compared to Eyeriss on a 2D CNN by 71%.

When using convolutional neural networks (CNNs) for segmentation of organs and lesions in medical images, the conventional approach is to work with inputs and outputs either as single slice [two-dimensional (2D)] or whole volumes [three-dimensional (3D)]. One common alternative, in this study denoted as pseudo-3D, is to use a stack of adjacent slices as input and produce a prediction for at least the central slice. This approach gives the network the possibility to capture 3D spatial information, with only a minor additional computational cost. In this study, we systematically evaluate the segmentation performance and computational costs of this pseudo-3D approach as a function of the number of input slices, and compare the results to conventional end-to-end 2D and 3D CNNs, and to triplanar orthogonal 2D CNNs. The standard pseudo-3D method regards the neighboring slices as multiple input image channels. We additionally design and evaluate a novel, simple approach where the input stack is a volumetric input that is repeatably convolved in 3D to obtain a 2D feature map. This 2D map is in turn fed into a standard 2D network. We conducted experiments using two different CNN backbone architectures and on eight diverse data sets covering different anatomical regions, imaging modalities, and segmentation tasks. We found that while both pseudo-3D methods can process a large number of slices at once and still be computationally much more efficient than fully 3D CNNs, a significant improvement over a regular 2D CNN was only observed with two of the eight data sets. triplanar networks had the poorest performance of all the evaluated models. An analysis of the structural properties of the segmentation masks revealed no relations to the segmentation performance with respect to the number of input slices. A post hoc rank sum test which combined all metrics and data sets yielded that only our newly proposed pseudo-3D method with an input size of 13 slices outperformed almost all methods. In the general case, multislice inputs appear not to improve segmentation results over using 2D or 3D CNNs. For the particular case of 13 input slices, the proposed novel pseudo-3D method does appear to have a slight advantage across all data sets compared to all other methods evaluated in this work.

The convolutional neural network (CNN) is a potent and popular neural network types and has been crucial to deep learning in recent years. A standard CNN which is known as 2-dimensions CNN was first proposed to solve image classification problems at first. With advancements in science and technology, as well as the growth of the internet, tasks involving video analysis have received increased attention in recent years. As a result, it was suggested that a 3-dimensions convolutional neural network (3D CNN) be applied to tackle 3D image processing or video analysis. 3D CNN is primarily used in the field of human activity recognition, video classification, medical imaging detection, and so on. This paper offers a succinct introduction to the general architecture and representative models of 3D CNN, contrasts the variations between 2D CNN and 3D CNN, explores the widely used models derived from 3D CNN, and displays the application outcomes of 3D CNN.

In this study, we introduce an innovative auto-stop car system empowered by deep learning technology, specifically employing two Convolutional Neural Networks (CNNs) for face recognition and travel drowsiness detection. Implemented on a Raspberry Pi 4, our system is designed to cater exclusively to certified drivers, ensuring enhanced safety through intelligent features. The face recognition CNN model accurately identifies authorized drivers, employing deep learning techniques to verify their identity before granting access to vehicle functions. This first model demonstrates a remarkable accuracy rate of 99.1%, surpassing existing solutions in secure driver authentication. Simultaneously, our second CNN focuses on real-time detecting+ of driver drowsiness, monitoring eye movements, and utilizing a touch sensor on the steering wheel. Upon detecting signs of drowsiness, the system issues an immediate alert through a speaker, initiating an emergency park and sending a distress message via Global Positioning System (GPS). The successful implementation of our proposed system on the Raspberry Pi 4, integrated with a real-time monitoring camera, attains an impressive accuracy of 99.1% for both deep learning models. This performance surpasses current industry benchmarks, showcasing the efficacy and reliability of our solution. Our auto-stop car system advances user convenience and establishes unparalleled safety standards, marking a significant stride in autonomous vehicle technology.

paper, we focus on exploring the relationship between weave patterns and their mechanical properties in woven fiber composites through Machine Learning. Specifically, we explore the interactions between woven architectures and in-plane stiffness properties through Deep Convolutional Neural Network (DCNN) and Generative Adversarial Network (GAN). Our research is important for exploring how woven composite’s pattern is related to its mechanical properties and accelerating woven composite design as well as optimization. We focus on two tasks: (1) Stiffness prediction: Predicting in-plane stiffness properties for given weave patterns. Our DCNN extracts high-level features through several convolutional and fully connected layers to determine the final predictions. (2) Weave pattern prediction: Predicting weave patterns for target stiffness properties, which can be treated as the reverse task of the first one. Due to many-to-one mapping between weave patterns and the composite properties, we utilize a Decoder Neural Network as our baseline model and compare its performance with GAN and Genetic Algorithm. We represent the weave patterns as 2D checkerboard models and use finite element analysis (FEA) to determine in-plane stiffness properties, which serve as input data for our ML framework. We show that: (1) for stiffness prediction, DCNN can predict stiffness values for a given weave pattern with relatively high accuracy (above 93%); (2) for weave pattern prediction, the GAN model gives the best prediction accuracy (above 92%) while Decoder Neural Network has the best time efficiency. HAOTIAN FENG

Background Incidence rate of thyroid cancer is steadily increasing due to overdiagnosis and overtreatment. Thyroid ultrasound is commonly used to diagnose thyroid cancer. The aim of this study is to examine the accuracy of using deep convolutional neural network (DCNN) models to improve diagnosis of thyroid cancer by analyzing sonographic imaging data from clinical thyroid ultrasound. Methods A total of 131,731 sonographic images from 17,627 thyroid cancer patients and 180,668 sonographic images from 25,325 controls used as training set were obtained from Tianjin Cancer Hospital. Images from anatomical sites that did not have cancer according to location sign on the image were not included. All thyroid cancer patients and 13·2% of controls (51,255 images) were confirmed by pathological reports. DCNN is a specific type of neural network optimized for image recognition. We trained two DCNN models on the training set and subsequently evaluated the performance on one independent internal (Tianjin, 1,118 individuals) and two external (Jilin,154 individuals; Weihai, 1,420 individuals) validation sets. Individuals in the validation sets all have pathological examinations. We compared the specificity/sensitivity of DCNN models with the performance of six thyroid ultrasound radiologists on these three validation sets. Findings DCNN model achieved high performance in identifying thyroid cancer patients versus six experience radiologists: for Tianjin validation set, sensitivity was 92·2% versus 96·9% (95% CI 89·7% - 94·3% vs. 93·9% - 98·6%; p = 0·003), and specificity was 85·6% versus 59·4% (95% CI 82·4% - 88·4% vs. 53% - 65·6%; p < 0·0001); for Jilin validation set, sensitivity was 84·3% versus 92·9% (95% CI 73·6% - 91·9% vs. 84·1% - 97·6%; p = 0·05), and specificity was 86·9% versus 57·1% (95% CI 77·8% - 93·3% vs. 45·9% - 67·9%; p < 0·0001); for Weihai validation set, sensitivity was 84·5% versus 89% (95% CI 81·2% - 87·4% vs. 81·9% - 94%; p = 0·2), and specificity was 87·5% versus 68·6% (95% CI 85·1% - 89·6% vs. 60·7% - 75·8%; p < 0·0001). Interpretation DCNN models exhibited high accuracy, sensitivity, and specificity in identifying thyroid cancer patients at levels comparable to or higher than six experienced radiologists. Conferred by the high specificity of DCNN models, the rate of overdiagnosis and overtreatment of patients with thyroid cancer is expected to decrease. This supports future application of the deep learning models to clinical practice for thyroid cancer diagnosis. However, further validation of these DCNN models in prospective clinical trials is warranted. Funding The Program for Changjiang Scholars and Innovative Research Team in University in China (IRT_14R40), National Natural Science Foundation of China (31801117). Citation Format: Xiangchun Li, Sheng Zhang, Qiang Zhang, Xi Wei, Yi Pan, Jing Zhao, Xiaojie Xin, Xiaoqing Wang, Fan Yang, Jianxin Li, Meng Yang, Qinghua Wang, Xiangqian Zheng, Yanhui Zhao, Lun Zhang, Xudong Wang, Zhimin Zheng, Christopher T. Whitlow, Metin N. Gurcan, Boris Pasche, Ming Gao, Wei Zhang, Kexin Chen. Diagnosis of thyroid cancer using deep convolutional neural network models applied to sonographic images from clinical ultrasound exams [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2019; 2019 Mar 29-Apr 3; Atlanta, GA. Philadelphia (PA): AACR; Cancer Res 2019;79(13 Suppl):Abstract nr 1394.

The study intended to explore the effect of different neural network algorithms in the electrocardiogram (ECG) classification of patients with congenital heart disease (CHD). Based on the single convolutional neural network (CNN) ECG algorithm and the recurrent neural network (RNN) ECG algorithm, a multimodal neural network (MNN) ECG algorithm was constructed utilizing the MIT-BIH database as training set and test set. Furthermore, the MNN ECG algorithm was optimized to establish an improved MNN (IMNN) algorithm, which was applied to the diagnosis of CHD patients. The CHD patients admitted between August 2016 and August 2019 were selected for analysis to compare the classification effect and accuracy rate of IMNN, MNN, CNN ECG, and RNN ECG algorithms. It was found that the RNN ECG algorithm had higher classification sensitivity and true positive rate in terms of normal or bundle (NB) branch block beat, supraventricular abnormal (SA) rhythm, abnormal ventricular (AV) beat, and fusion beat (FB) than the CNN ECG algorithm ( P < 0.05 ), and the classification sensitivity and true positive rate of IMNN algorithm in the four aspects were significantly higher than those of MNN algorithm ( P < 0.05 ). The classification accuracy of CNN ECG algorithm and RNN ECG algorithm was above 98%, while that of MNN algorithm and IMNN algorithm was better than that of CNN ECG algorithm and RNN ECG algorithm, and the accuracy rate can reach 98.5% or more. Moreover, the accuracy rate of the IMNN algorithm can reach more than 98%. In conclusion, IMNN not only has a good classification ability in the simulated environment but also performs well in the actual environment, which is worthy of clinical promotion.

Aims: This study aimed to explore the effect of training set diversity on the performance of deep learning models for predicting early gastric cancer (EGC) under endoscopy. Methods: Images of EGC and non-cancerous lesions under narrow-band imaging (ME-NBI) and magnifying blue laser imaging (ME-BLI) were retrospectively collected. Training set 1 was composed of 150 non-cancerous and 309 EGC ME-NBI images, training set 2 was composed of 1505 non-cancerous and 309 EGC ME-BLI images, and training set 3 was the combination of training set 1 and 2. Test set 1 was composed of 376 non-cancerous and 1052 EGC ME-NBI images, test set 2 consisted of 529 non-cancerous and 71 EGC ME-BLI images, and test set 3 was the combination of test set 1 and test set 2. Three deep learning models, convolutional neural network (CNN) 1, CNN 2 and CNN 3 (CNN 1, CNN 2 and CNN 3 were independently trained using training set 1, training set 2 and training set 3, respectively), were constructed, and their performances on each test set were respectively evaluated. One hundred and thirty-eight ME-NBI videos and 17 ME-BLI videos were further collected to evaluate and compare the performance of each model in real time. Results: On the whole, the performance of CNN 3 was the best. The accuracy (Acc), sensitivity (Sn), specificity (Sp) and area under the curve (AUC) of test set 1 in CNN 3 were 87.89% (1255/1428), 90.96% (342/376), 86.79% (913/1052) and 94.60%, respectively. The Acc, Sn, Sp and AUC of test set 2 in CNN 3 were 95% (570/600), 97.92% (518/529), 73.24% (52/71) and 90.93% respectively. The Acc, Sn, Sp and AUC of test set 3 in CNN 3 were 89.99% (1825/2028), 95.03% (860/905), 85.93% (965/1123) and 94.89%, respectively. The performance of CNN 3 was also the best in videos test set. The Acc, Sn and Sp of videos test set in CNN 3 were 91.03% (142/156), 90.58% (125/138) and 94.44% (17/18), respectively. Conclusions: The deep learning model with the most diverse training data has the best diagnostic effect.

Multimodal emotion recognition has become a hot topic in human-computer interaction and intelligent healthcare fields. However, combining information from different human different modalities for emotion computation is still challenging. In this paper, we propose a three-dimensional convolutional recurrent neural network model (referred to as 3FACRNN network) based on multimodal fusion and attention mechanism. The 3FACRNN network model consists of a visual network and an EEG network. The visual network is composed of a cascaded convolutional neural network-time convolutional network (CNN-TCN). In the EEG network, the 3D feature building module was added to integrate band information, spatial information and temporal information of the EEG signal, and the band attention and self-attention modules were added to the convolutional recurrent neural network (CRNN). The former explores the effect of different frequency bands on network recognition performance, while the latter is to obtain the intrinsic similarity of different EEG samples. To investigate the effect of different frequency bands on the experiment, we obtained the average attention mask for all subjects in different frequency bands. The distribution of the attention masks across the different frequency bands suggests that signals more relevant to human emotions may be active in the high frequency bands γ (31-50 Hz). Finally, we try to use the multi-task loss function Lc to force the approximation of the intermediate feature vectors of the visual and EEG modalities, with the aim of using the knowledge of the visual modalities to improve the performance of the EEG network model. The mean recognition accuracy and standard deviation of the proposed method on the two multimodal sentiment datasets DEAP and MAHNOB-HCI (arousal, valence) were 96.75 ± 1.75, 96.86 ± 1.33; 97.55 ± 1.51, 98.37 ± 1.07, better than those of the state-of-the-art multimodal recognition approaches. The experimental results show that starting from the multimodal information, the facial video frames and electroencephalogram (EEG) signals of the subjects are used as inputs to the emotion recognition network, which can enhance the stability of the emotion network and improve the recognition accuracy of the emotion network. In addition, in future work, we will try to utilize sparse matrix methods and deep convolutional networks to improve the performance of multimodal emotion networks.

Palm print scanning is a widespread method for biometric identity detection which has some advantages over other methods including its simplicity and relatively lower cost. In this study, a novel methods for biometric verification and identification by contactless palm scanning technique is proposed. In the study, Ripplet-I Transform (R-IT) which is a generalized form of Curvelet Transform (CuT), have been used in addition to multi-resolution transforms which were previously used in the literature as palm print verification and identification methods such as Discrete Cosine Transform (DCT), Discrete Wavelet Transform (DWT), Contourlet Transform (CoT). In addition, Principal Component Analysis (PCA) and Local Binary Pattern (LBP) have been utilized to increase the algorithm diversity. In order to investigate the effect of classification methods on the study results and the processing times, Artificial Neural Network (ANN), Euclidean Distance (ED) and Support Vector Machine (SVM) have been used separately for matching in the verification part of study. The performance of Convolutional Neural Network (CNN) as a classifier has also been examined. Verification and identification algorithms proposed in the study have been tested using palm print images of Hong Kong Polytechnic University Contact-free 3D/2D Hand Images Database (Version 1.0). The studies, that were carried out under two main sections yielded interesting results. At the end of the study, AUC (Area Under the ROC Curve) values ranging from 0.550 (Equal Error Rate (EER)= 0.4594) to 0.9875 (EER= 0.0336) were obtained for palm print verification. The highest AUC value without using LBP was obtained as 0.9563 (EER= 0.1096) using R-IT/CuT+DCT+CNN. Study results were showed that CNN is more successful than other classifiers without using LBP. It also has pointed out that the R-IT/CuT provides better results than the DWT and CoT. Using LBP in algorithms has increased success for ED, SVM and ANN. However, it has reduced overall for CNN. The highest AUC value (0.9875 and EER= 0.0336) was provided by the LBP+DWT+ED algorithm for palm print verification. The highest Identification Rate (IR) was achieved by using the LBP+CoT+ED algorithm with 84.444% for for palm print identification.

With the wide application of artificial intelligence technology in intelligent education, intelligent office and other fields, handwritten optical character recognition (OCR) as an important content of intelligent education research has been widely concerned. Traditional character recognition technology is mainly for high-quality printed images, but there are some problems in English handwriting, such as irregular handwriting, overlapping letters, word smearing, etc., which can not achieve the recognition accuracy of printed images. In particular, the lack of database construction for handwriting images with scrawl and daub increases the difficulty of model training, so handwriting recognition is a very challenging task. In view of the existing problems mentioned above and the limitations of traditional handwriting recognition methods, this paper studies the English handwriting recognition method based on deep learning technology, and realizes the English handwriting image detection and recognition system on this basis. The main tasks of this paper are as follows: 1. The database of English handwriting image is established, including neat, scrawl, neat and smeared and scrawl and smeared. Label information is assigned to each type of data, and SVM classifier is trained to classify new samples using this database. In order to reduce the interference of smear area and background information on the character recognition model, the image is preprocessed with smear block removal, gray scale and tilt correction, and the processing results are used as the input of the subsequent detection and recognition model. 2. A convolutional cyclic neural network based on cross-channel and cross-space attention mechanism is proposed. The convolutional neural network is used to extract local feature information and cross-channel and cross-space attention mechanisms are introduced to reduce the loss of key features. At the same time, bidirectional recurrent neural network is used to capture the context dependence of characters and obtain the word order information of English script. 3. An English handwritten recognition method based on Semantic Reasoning Networks (SRN) and CCSACRNN (SNCN) is proposed.

Skin cancer is one of the most lethal types of cancer worldwide. There are different types of cancer but the most dangerous one is melanoma. In US alone, 1 out of 5 people will develop skin cancer by the age of 70 and more than 2 people die of skin cancer every hour. Taking these facts under consideration, early detection of skin cancer is crucial, and many lives could be saved. Deep learning technologies are proven to be of great aid in early detection. In this master thesis, different convolutional neural networks will be presented and tested on HAM10000 dataset of ISIC challenge dataset of 2018, containing 10.000 images of skin lesion from seven different classes. Neural networks will be trained on a portion of the dataset and then tested in new images. The convolutional networks used are Densenet201, Inception V3 and an Ensemble model of the previous two. Lastly, an application is developed which uses by default a convolutional network defined by the user. The user is able to feed an image in the application and a result out of the seven classes predefined will be presented.