Journal of Signal Processing Systems for Signal Image and Video Technology最新文献

The paper summarizes the design and implementation of a passenger traffic prediction model, based on Gaussian Process Regression (GPR). Passenger traffic analysis is the present day requirement for proper bus scheduling and traffic management to improve the efficiency and passenger comfort. Bayesian analysis uses statistical modelling to recursively estimate new data from existing data. GPR is a fully Bayesian process model, which is developed using PyMC3 with Theano as backend. The passenger data is modelled as a Poisson process so that the prior for designing the GP regression model is a Gamma distributed function. It is observed that the proposed GP based regression method outperforms the existing methods like Student-t process model and Kernel Ridge Regression (KRR) process.

The SARS-CoV-2 virus causes a respiratory disease in humans, known as COVID-19. The confirmatory diagnostic of this disease occurs through the real-time reverse transcription and polymerase chain reaction test (RT-qPCR). However, the period of obtaining the results limits the application of the mass test. Thus, chest X-ray computed tomography (CT) images are analyzed to help diagnose the disease. However, during an outbreak of a disease that causes respiratory problems, radiologists may be overwhelmed with analyzing medical images. In the literature, some studies used feature extraction techniques based on CNNs, with classification models to identify COVID-19 and non-COVID-19. This work compare the performance of applying pre-trained CNNs in conjunction with classification methods based on machine learning algorithms. The main objective is to analyze the impact of the features extracted by CNNs, in the construction of models to classify COVID-19 and non-COVID-19. A SARS-CoV-2 CT data-set is used in experimental tests. The CNNs implemented are visual geometry group (VGG-16 and VGG-19), inception V3 (IV3), and EfficientNet-B0 (EB0). The classification methods were k-nearest neighbor (KNN), support vector machine (SVM), and explainable deep neural networks (xDNN). In the experiments, the best results were obtained by the EfficientNet model used to extract data and the SVM with an RBF kernel. This approach achieved an average performance of 0.9856 in the precision macro, 0.9853 in the sensitivity macro, 0.9853 in the specificity macro, and 0.9853 in the F1 score macro.

6G networks have the burden to provide not only higher performance compared to 5G, but also to enable new service domains as well as to open the door over a new paradigm of mobile communication. This paper presents an overview on the role and key challenges of signal processing (SP) in future 6G systems and networks from the conditioning of the signal at transmission to MIMO precoding and detection, from channel coding to channel estimation, from multicarrier and non-orthogonal multiple access (NOMA) to optical wireless communications and physical layer security (PLS). We describe also the core future research challenges on technologies including machine learning based 6G design, integrated communications and sensing (ISAC), and the internet of bio-nano-things.

The paper reports a combination of the deep learning technique and bayesian filtering to effectively predict the passenger traffic. The architecture of the model integrates the particle filter with the LSTM network. The time series sequential prediction is best achieved using LSTM network while Markovian behaviour is well extracted using Bayesian (Particle Filter) filters. The temporal and spatial features of the traffic data are analyzed. Three relevant temporal variations viz., morning, noon and post noon patterns are identified after the histogram analysis. These patterns are statistically modelled and the integrated model is used to accurately predict the passenger flow for the next thirty days, facilitating, the bus scheduling for that period. The experimental results proved that the proposed integrated model with coefficient of determination ( $R^2$ ) value of 0.88 is functional in predicting the passenger traffic even when the training data set size is small.

Accurate and precise identification of adeno-associated virus (AAV) vectors play an important role in dose-dependent gene therapy. Although solid-state nanopore techniques can potentially be used to characterize AAV vectors by capturing ionic current, the existing data analysis techniques fall short of identifying them from their ionic current profiles. Recently introduced machine learning methods such as deep convolutional neural network (CNN), developed for image identification tasks, can be applied for such classification. However, with smaller data set for the problem in hand, it is not possible to train a deep neural network from scratch for accurate classification of AAV vectors. To circumvent this, we applied a pre-trained deep CNN (GoogleNet) model to capture the basic features from ionic current signals and subsequently used fine-tuning-based transfer learning to classify AAV vectors. The proposed method is very generic as it requires minimal preprocessing and does not require any handcrafted features. Our results indicate that fine-tuning-based transfer learning can achieve an average classification accuracy between 90 and 99% in three realizations with a very small standard deviation. Results also indicate that the classification accuracy depends on the applied electric field (across nanopore) and the time frame used for data segmentation. We also found that the fine-tuning of the deep network outperforms feature extraction-based classification for the resistive pulse dataset. To expand the usefulness of the fine-tuning-based transfer learning, we have tested two other pre-trained deep networks (ResNet50 and InceptionV3) for the classification of AAVs. Overall, the fine-tuning-based transfer learning from pre-trained deep networks is very effective for classification, though deep networks such as ResNet50 and InceptionV3 take significantly longer training time than GoogleNet.

The emergence of the new video coding standard, Versatile Video Coding (VVC), has resulted in a 40-50% coding gain over its predecessor HEVC for the same visual quality. However, this is accompanied by a sharp increase in computational complexity. The emergence of the VVC standard and the increase in video resolution have exceeded the capacity of single-core architectures. This fact has led researchers to use multicore architectures for the implementation of video standards and to use the parallelism of these architectures for real-time applications. With the strong growth in both areas, video coding and multicore architecture, there is a great need for a design methodology that facilitates the exploration of heterogeneous multicore architectures, which automatically generates optimized code for these architectures in order to reduce time to market. In this context, this paper aims to use the methodology based on data flow modeling associated with the PREESM software. This paper shows how the software has been used to model a complete standard VVC video decoder using Parameterized and Interfaced Synchronous Dataflow (PiSDF) model. The proposed model takes advantage of the parallelism strategies of the OpenVVC decoder and in particular the tile-based parallelism. Experimental results show that the speed of the VVC decoder in PiSDF is slightly higher than the OpenVVC decoder handwritten in C/C++ languages, by up to 11% speedup on a 24-core processor. Thus, the proposed decoder outperforms the state-of-the-art dataflow decoders based on the RVC-CAL model.

A real-time 3D visualization (RT3DV) system using a multiview RGB camera array is presented. RT3DV can process multiple synchronized video streams to produce a stereo video of a dynamic scene from a chosen view angle. Its design objective is to facilitate 3D visualization at the video frame rate with good viewing quality. To facilitate 3D vision, RT3DV estimates and updates a surface mesh model formed directly from a set of sparse key points. The 3D coordinates of these key points are estimated from matching 2D key points across multiview video streams with the aid of epipolar geometry and trifocal tensor. To capture the scene dynamics, 2D key points in individual video streams are tracked between successive frames. We implemented a proof of concept RT3DV system tasked to process five synchronous video streams acquired by an RGB camera array. It achieves a processing speed of 44 milliseconds per frame and a peak signal to noise ratio (PSNR) of 15.9 dB from a viewpoint coinciding with a reference view. As a comparison, an image-based MVS algorithm utilizing a dense point cloud model and frame by frame feature detection and matching will require 7 seconds to render a frame and yield a reference view PSNR of 16.3 dB.

The world is witnessing a rising number of preterm infants who are at significant risk of medical conditions. These infants require continuous care in Neonatal Intensive Care Units (NICU). Medical parameters are continuously monitored in premature infants in the NICU using a set of wired, sticky electrodes attached to the body. Medical adhesives used on the electrodes can be harmful to the baby, causing skin injuries, discomfort, and irritation. In addition, respiration rate (RR) monitoring in the NICU faces challenges of accuracy and clinical quality because RR is extracted from electrocardiogram (ECG). This research paper presents a design and validation of a smart textile pressure sensor system that addresses the existing challenges of medical monitoring in NICU. We designed two e-textile, piezoresistive pressure sensors made of Velostat for noninvasive RR monitoring; one was hand-stitched on a mattress topper material, and the other was embroidered on a denim fabric using an industrial embroidery machine. We developed a data acquisition system for validation experiments conducted on a high-fidelity, programmable NICU baby mannequin. We designed a signal processing pipeline to convert raw time-series signals into parameters including RR, rise and fall time, and comparison metrics. The results of the experiments showed that the relative accuracies of hand-stitched sensors were 98.68 (top sensor) and 98.07 (bottom sensor), while the accuracies of embroidered sensors were 99.37 (left sensor) and 99.39 (right sensor) for the 60 BrPM test case. The presented prototype system shows promising results and demands more research on textile design, human factors, and human experimentation.

The recent COVID-19 outbreak highlighted the requirement for a more sophisticated healthcare system and real-time data analytics in the pandemic mitigation process. Moreover, real-time data plays a crucial role in the detection and alerting process. Combining smart healthcare systems with accurate real-time information about medical service availability, vaccination, and how the pandemic is spreading can directly affect the quality of life and economy. The existing architecture models are become inadequate in handling the pandemic mitigation process using real-time data. The present models are server-centric and controlled by a single party, where the management of confidentiality, integrity, and availability (CIA) of data is doubtful. Therefore, a decentralised user-centric model is necessary, where the CIA of user data is assured. In this paper, we have suggested a decentralized blockchain-based pandemic detection and assistance system (iBlock). The iBlock uses robust technologies like hybrid computing and IPFS to support system functionality. A pseudo-anonymous personal identity is introduced using H-PCS and cryptography for anonymous data sharing. The distributed data management module guarantees data CIA, security, and privacy using cryptography mechanisms. Furthermore, it delivers useful intelligent information in the form of suggestions and alerts to assist the users. Finally, the iBlock reduces stress on healthcare infrastructure and workers by providing accurate predictions and early warnings using AI/ML.