CNN-Based Spectrum Sensing Method for Low Probability of Detection Communication Systems

In recent years, AI(Artificial Intelligence) has achieved great development in modern society. More and more modern technologies are applied in surveillance and monitoring. Healthcare monitoring is growing ubiquitous in modern wearable devices, such as a smart watch, electrocardiogram (ECG) necklace, smart band. Many sensors are attached to these smart devices to record and monitor physiological signals caused by activities, and then propagated those recorded electrical data to be further processed to give health diagnosis, disease prevention or making a distress call automatically. Obstructive sleep apnea (OSA) is a sleep disorder with a high occurrence in adult people and observed as an autonomous risk factor for circulatory problems such as ischemic heart attacks and stroke. Numerous traditional neural network based methods have been developed to detect OSA, where these methods however could not provide the intended result because they rely on shallow network. In this paper, we propose an effective OSA detection based on Convolutional neural network. Our method first extracts features from Apnea-Electrocardiogram (ECG) recordings using RR-intervals (time interval from one R-wave to the next R-wave in an ECG signal) and then CNN model having three convolution layers and three fully connected layers is trained with extracted features and applied for OSA detection. The first two convolution layers are followed by batch normalization and pooling layer, and softmax is connected to the last fully connected layer to give final decision. Experimental results on extracted feature of Apnea-ECG signal reveal that our model have better results in terms of performance measure sensitivity, specificity and accuracy. It is expected that the related technology can be applied into smart sensors, especially wearable devices.

In this work, we design a neural network named MCRNN for classifying signals with slight distinction. This model combines advantages of both Convolutional Neural Network and Recurrent Neural Network, allowing the network to distinguish between long signals with long time-frequency maps. We use an architecture involving both convolutional layers, for extracting high-level features and reduce the dimension of data from time-frequency maps, and recurrent layers, for aggregating long-term dependencies. We apply techniques like Adam optimizer, batch normalization, and softmax layers, obtaining highly competitive results of 99.9% accuracy even in a low SNR of -2dB. Moreover, we conduct extensive experiment through a range of noisy scenarios from -10dB to 30dB. The model can be extended to signal dataset with short time-frequency maps easily. We leverage open source dataset like DeepSig as verification.

The application of deep learning technology has increased rapidly in recent years. Technologies in deep learning increasingly emulate natural human abilities, such as knowledge learning, problem-solving, and decision-making. In general, deep learning can carry out self-training without repetitive programming by humans. Convolutional neural networks (CNNs) are deep learning algorithms commonly used in wide applications. CNN is often used for image classification, segmentation, object detection, video processing, natural language processing, and speech recognition. CNN has four layers: convolution layer, pooling layer, fully connected layer, and non-linear layer. The convolutional layer uses kernel filters to calculate the convolution of the input image by extracting the fundamental features. The pooling layer combines two successive convolutional layers. The third layer is the fully connected layer, commonly called the convolutional output layer. The activation function defines the output of a neural network, such as 'yes' or 'no'. The most common and popular CNN activation functions are Sigmoid, Tanh, ReLU, Leaky ReLU, Noisy ReLU, and Parametric Linear Units. The organization and function of the visual cortex greatly influence CNN architecture because it is designed to resemble the neuronal connections in the human brain. Some of the popular CNN architectures are LeNet, AlexNet and VGGNet.

Optimizing convolutional neural networks on multi-core vector accelerator

In order to overcome the effects of posture, illumination, expression and other factors on face recognition, this paper proposes an algorithm which is based on local binary pattern (LBP) and convolutional neural network (CNN). LBP is a texture description method which describes the local texture features of an image. It has good robustness of illumination and posture. CNN can effectively extract the spatial features of images and reduce the dimensions of features. This paper combines the advantages of LBP and CNN to improve the accuracy of face recognition. The CNN in this algorithm has four convolution layers, two max-pooling layers, one activation layer, one fully connected layer, and one output layer. In order to optimize the network structure, batch normalization layer is added after the convolution layer. We get the local binary pattern coded images and put the images as the input of the CNN and train the network. Hence, we can use the well-trained CNN for classification and identification. The Experiments on the CMU-PIE face database show that our algorithm can effectively improve the rate of face recognition.

Recent research on fault diagnosis mainly focuses on how to improve diagnostic accuracy. For a given accuracy level, a variety of convolutional neural network architectures have been developed and available to achieve the specific accuracy level. With equivalent fault diagnosis accuracy, smaller convolutional neural network structure offers at least three advantages: (1) it can be deployed on hardware with limited memory, such as FPGAs; (2) the training of smaller convolutional neural networks can be faster under the same processor performance; (3) smaller network structures require less communication across severs during distributed training. So, in this paper, an improved convolutional neural network is constructed, and the following strategies are used to reduce network parameters and further make the convolutional neural networks with smaller structures: (1) equivalent replacement of large-scale convolution layers by multiple small-sized convolution layers; (2) avoid using a fully connected layer, and replace with a global pooling layer. Meanwhile, to ensure the model’s fault diagnosis accuracy and training effectiveness, inspired by the network in network, a 1*1 convolutional layer is inserted into a traditional convolutional layer to improve feature expression, and the batch-normalization layer is used to increase the training effectiveness.

Malaria is a disease which, despite being present for over a century, still claims a significant number of lives every year. The advancement of artificial intelligence have opened the door to developing innovative methods in malaria treatment. Introducing machine learning approaches to this field can be beneficial in the disease prevention, detection, and therapy. In this work, convolutional neural networks for malaria detection are developed, based on the classification of thin blood smear images of the potentially infected cells. Input data was preprocessed using the image segmentation, file organization, image size standardization, color channel adjustment, and data splitting. Further, the proposed methodology included image conversion, network architecture defining, parameter tuning and network training. Various architectures of convolutional neural networks were developed and evaluated. In addition, multiple values of different network layer parameters were assessed. This study was implemented in Clojure programming language. Proposed network architecture includes two convolutional and pooling layers followed by activation functions, batch normalization and two linear layers. This convolutional neural network provided the best results and achieved an 82.7% accuracy. Furthermore, this paper proposes another network model with lightweight configuration and a slight accuracy decrease.

In this study, we used two machine learning algorithms, namely, linear support vector machine (SVM) and convolutional neural network (CNN), to classify the BCI (Brain Computer interface) competition IV-2a 2-class MI (motor imagery) data set which consists of EEG data from 9 subjects. For each subject, 5 sessions of signals from three electrodes (C3, Cz, and C4) were recorded with sampling rate 250Hz. The training data, which consisted of the first 3 sessions, included 400 trials. The evaluation data, which consisted of the last 2 sessions, included 320 trials. Each trial started with gazing at fix cross on screen for 3 seconds followed by a one-second visual cue pointing either to the left or right to instruct the subject for left or right motor imagery over a period of 4 seconds, and then followed by a short break of at least 1.5 seconds. Features were extracted from the 0.5 to 2.5 second signals after the cue for each trial from C3 and C4. Each EEG trial was band pass filtered into different frequency bands, namely, delta (0.5-3Hz), theta (4-8Hz), alpha (8-12Hz), beta bands (13-30Hz), gamma bands (31-60Hz). Those filtered signals were then used as the input data for training the linear SVM. In addition, we generated a 2 by 500 matrix by down sampling the training data from each trial. There are 5760 such matrices in total generated from all subjects and serve as the input data for training CNN and the trained model was evaluated by another 340 matrices from each subject. Our CNN architecture consisted of 2 convolution layer and 2 fully connect layers, and there was a batch normalization layer before the activated layer and a dropout layer with a probability of 50% after the activated layer. The classification accuracies evaluated by averaged kappa values obtained from linear SVM and CNN are 0.5 and 0.621, respectively, suggesting the deep learning CNN method is superior to the classical linear SVM on the EEG classification.

High-Efficiency Video Coding (HEVC) is the latest video coding standard developed by the Joint Collaborative Team on Video Coding (JCT-VC). An effective rate control mechanism plays a critical role in making the best possible use of the network resources. The coding performance can be maximised through the appropriate allocation of bits under the constraints of a total bit rate budget and the buffer size. Existing rate control strategies generally determine the rate control parameters according to previous encoding results. However, there is no priori-knowledge available when the first frame of a video sequence is encoded or scene changes occur. Consequently, it is challenging to choose appropriate rate control parameters in such cases. In order to address this issue, we investigated deep learning oriented methods and proposed a Convolutional Neural Network (CNN)-based rate control scheme for HEVC intra-coding. As the CNN has the advantage of local perception and the Coding Tree Unit's (CTU's) Quantisation Parameter (QP) value is determined during the CTU level rate control process, we applied the CNN at the CTU level as well to achieve an accurate QP prediction. An improved QP determination model (R-QP model) involving only two model coefficients (µ and v) was suggested to simplify the QP calculation process. A CNN was used to predict the model coefficients, namely µ and v. Our CNN has four convolution layers, two pooling layers and three fully connected layers. Each of the convolution layers contains a Rectified Linear Unit (ReLU). The last fully connected layer outputs the predicted values of µ and v. The images from the UCID dataset and the RAISE dataset were used to train the CNN. In order to obtain a universal model, none of the frames in the HEVC common test sequences were employed as training images. In order to achieve a reasonable bit budget allocation, a CNN-based framework was used to predict the bit consumption for each CTU according to the entire picture content that it contains. At the training stage, the network took the original images and the QP values as inputs, and the corresponding actual bit consumptions were used as the labels. Once the CNN coefficients have been obtained through training, the bit consumption for each CTU under different QP values can be directly predicted from the original images. The predicted bit consumption was subsequently used to readjust the bit budget for each CTU to achieve a more reasonable bit allocation. We implemented the proposed CNN-based rate control scheme in the HEVC reference software HM 16.9. As the priori-knowledge of the previous encoding results had not been considered in the proposed algorithm, only the first frame of each video sequence was encoded. The experimental results showed that our proposed scheme performs better than the default rate control implementation in the HEVC reference software, namely the BDBR is reduced by 1.33% on average while maintaining the same reconstructed picture quality. Compared with the state-of-the-art CNN-based rate control algorithm proposed by Li, our schemes achieved better coding efficiency. It can be concluded that the proposed R-QP model is effective in describing the rate-distortion relationship in HEVC, and the CNN-based bit allocation scheme is appropriate for ensuring that the best use of each bit is made.

The convolutional layers of standard convolutional neural networks (CNNs) are equivariant to translation. However, the convolution and fully-connected layers are not equivariant or invariant to other affine geometric transformations. Recently, a new class of CNNs is proposed in which the conventional layers of CNNs are replaced with equivariant convolution, pooling, and batch-normalization layers. The final classification layer in equivariant neural networks is invariant to different affine geometric transformations such as rotation, reflection and translation, and the scalar value is obtained by either eliminating the spatial dimensions of filter responses using convolution and down-sampling throughout the network or average is taken over the filter responses. In this work, we propose to integrate the orthogonal moments which gives the high-order statistics of the function as an effective means for encoding global invariance with respect to rotation, reflection and translation in fully-connected layers. As a result, the intermediate layers of the network become equivariant while the classification layer becomes invariant. The most widely used Zernike, pseudo-Zernike and orthogonal Fourier-Mellin moments are considered for this purpose. The effectiveness of the proposed work is evaluated by integrating the invariant transition and fully-connected layer in the architecture of group-equivariant CNNs (G-CNNs) on rotated MNIST and CIFAR10 datasets.

Detection of brain tumor is very challenging task in today’s medical world. Nowadays, many doctors prefer ready-made methods to diagnose the tumor from given magnetic resonance imaging (MRI) images. Accurate and less time-consuming methods are used frequently to identify it. This paper introduces new techniques for finding and differentiating brain tumors. The new methods include support vector machine (SVM) and convolution neural network (CNN) with Softmax classifier. The SVM uses histogram of oriented gradients (HOGs) as a feature to label the given dataset. Further, the same feature of the test image is verified against labeled sets and classified. The SVM gives accuracy of 87.33%. In CNN, multilayer structure is used. It contains a convolution layer followed by the pooling layer and finally fully connected layer. In CNN, specifically, Alexnet is preferred for classification. In Alexnet, rectified linear unit (ReLU) is used as an activation function. At the output of it, Softmax is used as activation to classify the images. The CNN with Softmax classifier gives improved accuracy of 98.68%. In addition, the performance measures are also found out such as specificity, sensitivity, and precision. The sensitivity with SVM is 93.18%, and with CNN, it increases up to 100%. Comparing both methods with the obtained results, the CNN with Softmax classifier gives better results. Proposed method with CNN produces only one misclassified image as an advantage over the existing method, while SVM gives nine misclassified images. The methods are tested on 253 MRI images which are detected and classified correctly with Matlab.KeywordsSVMCNNHOGMRI

This study investigates the classification of skin cancer lesions utilizing Convolutional Neural Networks (CNNs) on the HAM10000 dataset. The collection includes photos of seven unique categories of skin lesions: melanocytic nevi, melanoma, benign keratosis-like lesions, basal cell carcinoma, actinic keratoses, vascular lesions, and dermatofibroma. Our main goals were to examine diagnostics efficacy over several lesion types and assess CNN performance in precisely categorizing dermatoscopic pictures. Label encoding and data balancing were used to ensure class representation. For regularization, we built sequential CNN models with convolutional, pooling, and dense layers and dropout and batch normalization. Transfer learning and Adam optimization were used in training. Our classification accuracy averages above 73.8%, demonstrating solid performance across lesion types. We tested the models' generalization ability on new data and found consistent performance. Confusion matrix analysis showed accurate categorization with low misclassification. This research improves early identification and intervention, improving patient outcomes and healthcare efficiency.

Human movement detection based on millimeter-wave radar sensors is a technology of interest in various areas such as for smart surveillance, security, behavioral biometrics, biomedical systems, robotics, etc. This paper shows the feasibility and effectiveness of using a compact 24 GHz Doppler radar with a built-in low-noise microwave amplifier (LNA) for detecting and extracting signals coming from human motion. Reliability and accuracy is assessed based on a comprehensive theoretical analysis, and on simulation results followed by experimental investigations. A continuous wavelet transform (CWT) is used to decompose in-phase and quadrature ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${I/Q}$ </tex-math></inline-formula> ) baseband signals to extract information about the dynamics of the system. The dataset consists of 1000 recordings in 8 motion classes (standing, walking, sitting, etc.). We propose to apply a two-channel convolutional neural network (CNN), which is composed of two CNN channels, for learning high-level features from time-domain signals and CWT spectrograms. One channel has four one-dimensional (1D) convolutional and pooling layers, and the other channel is made of three two-dimensional (2D) convolutional and pooling layers. In addition, the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${I/Q}$ </tex-math></inline-formula> signals are denoised by using Savitzky-Golay filtering, and both noisy and denoised signals are used as input signals for deep learning data augmentation purpose. We achieved an overall classification accuracy rate of 98.85% in motion classification for a two-branch CNN architecture, and an accuracy rate of 95.3% for a one-branch 2D-CNN. Our results show that a dual-channel CNN model can greatly increase the classification capabilities of human motion recognition and classification, and the proposed method can be effectively used with various radar signal classifications.

Signa1 modulation recognition (SMR) is an essential and challenging topic in orthogonal frequency-division multiplexing (OFDM) systems, and also it is the fundamental technique for signal detection and recovery. However, traditional feature extraction based SMR methods cannot effectively acquire the characteristics of the OFDM signals. Hence, the modulated OFD-M signal cannot be reliably identified. In this paper, we propose a deep learning (DL) based SMR method for recognizing OFDM signals, which is combined with a convolutional neural network (CNN) trained on in-phase and quadrature (IQ) samples. In the network model, the batch normalization (BN) layer and dropout layer are used to speed up model training and prevent overfitting, respectively. Three convolution layers with different convolution kernels perform well than traditional feature extraction methods in obtaining intrinsic properties of OFDM signals. The same number of multiple modulated signals are mixed and sent to the trained model for identification. Experiments are conducted to show that the method we proposed performs better than the traditional methods, mainly reflected in a higher probability of correct classification (PCC) and better consistency.

This paper presents a novel hybrid approach combining Gramian Angular Summation Field (GASF) method with a convolutional neural network (CNN) to classify power quality disturbances. Firstly, a 1-D Power quality disturbance signal is transformed into a 2-D image file using GASF. Subsequently, CNN is implemented for features extraction and image classification. In this work, the synthetic power quality (PQ) disturbances are considered including nine single disturbances and five mixed disturbances. Further, to capture multi-scale aspects of power quality disturbances problem and reduce overfitting, a unit is designed using 2-D convolutional, pooling, and batch-normalization layers. The classification study is further supported by experimental signals obtained on a prototype setup of PV system. The obtained results demonstrate the efficiency and reliability of the proposed method. The proposed method is compared with the other advanced CNNs and other conventional methods to illustrate its effectiveness.