Array最新文献

Pan/Tilt/Zoom (PTZ) cameras play an important role in traffic scenes due to their wide monitoring fields and high flexibility. However, since the focal length and angle of PTZ cameras change irregularly with the monitoring needs, it is difficult to obtain accurate physical information about the real world from the image information of PTZ cameras. Aiming to address the need for real-time risk assessment of road vehicles in traffic monitoring scenarios, a vehicle position and velocity measurement scheme based on camera inverse perspective transformation is proposed, along with a method for real-time risk assessment based on the position and velocity. Specifically, Firstly, the vehicle target in the video is detected and tracked by deep learning YOLO detection algorithm and optical flow tracking algorithm. According to the obtained trajectory set, the vanishing points in the road direction are calculated by Cascade Hough Transform and the road marking lines are detected. Then, according to the vanishing point and marking line, the camera calibration task is accomplished via exploratory focal length. After camera calibration, the camera-to-road inverse perspective transformation is applied to project the image plane onto the road surface and obtain, the actual position information of vehicles. Finally, the vehicle speed measurement and real-time road risk assessment are achieved by calculating the average of instantaneous velocities across multiple frames. Simulation experiment results in a traffic monitoring scenario demonstrate that this perspective-based method for real-time road vehicle risk assessment achieves good stability and practicality, which meets the requirements for vehicle speed measurement and real-time road risk assessment.

The recent pandemic has refocused the medical world’s attention on the diagnostic techniques associated with cardiovascular disease. Heart rate provides a real-time snapshot of cardiovascular health. A more precise heart rate reading enables a better understanding of cardiac muscle activity. Although many existing diagnostic techniques are approaching the limits of perfection, there remains potential for further development. In this paper, we propose MIBINET, a novel multifaceted approach for real-time proctoring of heart rate from Millimeter wave (mm-wave) radar ballistocardiography signals via inter-beat-interval (IBI) using a convolutional neural NETwork (CNN). The central theme of our approach is to synergize the feature extraction capabilities of CNN with novel signal processing techniques, resulting in enhanced estimation accuracy while simultaneously reducing computational complexity. This proposed network can be used in hospitals, homes, and passenger vehicles due to its lightweight and contactless properties. It employs classical signal processing prior to fitting the data into the network. Although MIBINET is primarily designed to work on mm-wave signals, it is found equally effective on signals of various modalities such as PCG, ECG, and PPG. Our approach outperforms state-of-the-art techniques by more than 5% in inter-beat-interval (IBI) estimation accuracy. The architecture achieves a 98.73% correlation coefficient and a 20.69 ms Root-Mean-Square Error (RMSE) over 11 different test subjects. The paper contributes by being the first to apply CNN-based feature extraction in concert with unique signal processing strategies to mm-wave radar data for heart rate monitoring. Our methodology also introduces a synthetic IBI augmentation technique, custom loss function, and novel post-processing methods, all contributing to the robust performance of the model in various settings and modalities.

Cloud data is increasing significantly recently because of the advancement of technology which can contain individuals’ sensitive information, such as medical diagnostics reports. While deriving knowledge from such sensitive data, different third party can get their hands on this sensitive information. Therefore, privacy preservation of such sensitive data has become a vital issue. Data perturbation is one of the most often used data mining approaches for safeguarding privacy. A significant challenge in data perturbation is balancing the privacy and utility of data. Securing an individual’s privacy often entails the forfeiture of the data utility, and the contrary is true. Though there exist several approaches to deal with the trade-off between privacy and utility, researchers are always looking for new approaches. In order to address this critical issue, this paper proposes two data perturbation approaches namely NOS2R and NOS2R2. The proposed perturbation techniques are experimented with over ten benchmark UCI data set for analyzing privacy protection, information entropy, attack resistance, data utility, and classification error. The proposed approaches are compared with two existing approaches 3DRT and NRoReM. The thorough experimental analysis exhibits that the best-performing approach NOS2R2 offers 15.48% higher entropy and 15.53% more resistance against ICA attack compared to the best existing approach NRoReM. Furthermore, in terms of utility, the accuracy, f1-score, precision and recall of NOS2R2 perturbed data are 42.32%, 31.22%, 30.77% and 16.15% more close to the original data respectively than the NRoReM perturbed data.

Neuromorphic event-driven systems emulate the computational mechanisms of the brain through the utilization of spiking neural networks (SNN). Neuromorphic systems serve two primary application domains: simulating neural information processing in neuroscience and acting as accelerators for cognitive computing in engineering applications. A distinguishing characteristic of neuromorphic systems is their asynchronous or event-driven nature, but even event-driven systems require some synchronous time management of the neuron populations to guarantee sufficient time for the proper delivery of spiking messages. In this study, we assess three distinct algorithms proposed for adding a synchronization capability to asynchronous event-driven compute systems. We run these algorithms on POETS (Partially Ordered Event-Triggered Systems), a custom-built FPGA-based hardware platform, as a neuromorphic architecture. This study presents the simulation speed of SNNs of various sizes. We explore essential aspects of event-driven neuromorphic system design that contribute to efficient computation and communication. These aspects include varying degrees of connectivity, routing methods, mapping techniques onto hardware components, and firing rates. The hardware mapping and simulation of up to eight million neurons, where each neuron is connected to up to one thousand other neurons, are presented in this work using 3072 reconfigurable processing cores, each of which has 16 hardware threads. Using the best synchronization and communication methods, our architecture design demonstrates 20-fold and 16-fold speedups over the Brian simulator and one 48-chip SpiNNaker node, respectively. We conclude with a brief comparison between our platform and existing large-scale neuromorphic systems in terms of synchronization, routing, and communication methods, to guide the development of future event-driven neuromorphic systems.

The advancement of computer technology has led to an overwhelming amount of textual information, hindering the efficiency of knowledge intake. To address this issue, various text summarization techniques have been developed, including statistics, graph sorting, machine learning, and deep learning. However, the rich semantic features of text often interfere with the abstract effects and lack effective processing of redundant information. In this paper, we propose the Multi-Features Maximal Marginal Relevance BERT (MFMMR-BertSum) model for Extractive Summarization, which utilizes the pre-trained model BERT to tackle the text summarization task. The model incorporates a classification layer for extractive summarization. Additionally, the Maximal Marginal Relevance (MMR) component is utilized to remove information redundancy and optimize the summary results. The proposed method outperforms other sentence-level extractive summarization baseline methods on the CNN/DailyMail dataset, thus verifying its effectiveness.

This study proposes a method for developing equipment lifespan estimators that combine physical information and numerical data, both of which may be incomplete. Physical information may not have a uniform fit to all experimental data, and health information may only be available at the initial and final periods. To address these issues, a procedure is defined to adjust the model to different subsets of available data, constrained by feasible trajectories in the health status space. Additionally, a new health model for rechargeable lithium batteries is proposed, and a use case is presented to demonstrate its efficacy. The optimistic (max–max) strategy is found to be the most suitable for diagnosing battery lifetime, based on the results.

In some sensitive domains where data imperfections are present, standard classification techniques reach their limits. To avoid misclassifications that have serious consequences, recent works propose cautious classification algorithms to handle this problem. Despite of the presence of uncertainty and/or imprecision, a point prediction classifier is forced to bet on a single class. While a cautious classifier proposes the appropriate subset of candidate classes that can be assigned to the sample in the presence of imperfect information. On the other hand, cautiousness should not be at the expense of precision and a trade-off has to be made between these two criteria. Among the existing cautious classifiers, two classifiers propose to manage this trade-off in the decision step by the mean of a parametrized objective function. The first one is the non-deterministic classifier (ndc) proposed within the framework of probability theory and the second one is “evidential classifier based on imprecise relabelling” (eclair) proposed within the framework of belief functions. The theoretical aim of the mentioned hyper-parameters is to control the size of predictions for both classifiers. This paper proposes to study this hyper-parameter in order to select the “best” value in a classification task. First the utility for each candidate subset is studied related to the values of the hyper-parameter and some thresholds are proposed to control the size of the predictions. Then two illustrations are proposed where a method to choose this hyper-parameters based on the calibration data is proposed. The first illustration concerns randomly generated data and the second one concerns the images data of fashion mnist. These illustrations show how to control the size of the predictions and give a comparison between the performances of the two classifiers for a tuning based on our proposition and the one based on grid search method.

Semi-supervised clustering is a machine learning technique that was introduced to boost clustering performance when labeled data is available. Indeed, some labeled data are usually available in real use cases, and can be used to initialize the clustering process to guide it and to make it more efficient. Fuzzy ART is a clustering technique that is proved to be efficient in several real cases, but as an unsupervised algorithm, it cannot use available labeled data. This paper introduces a semi-supervised variant of the FuzzyART clustering algorithm (SSFuzzyART). The proposed solution uses the available labeled data to initialize clusters centers. In another hand, to deeply evaluate the characteristics of the proposed algorithm, a clustered binary data generation algorithm with controlled partitioning is also introduced in this paper. Indeed, the controlled generated clusters allows studying the characteristics of the proposed SSFuzzyART. Furthermore, a set of experiments is carried out on some available benchmarks. SSFuzzyART demonstrated better clustering prediction results than its classic counterpart.

The speed difference between high-performance CPUs and energy-efficient CPUs, which are found in asymmetric performance multicore processors, affects the current form of Amdahl’s law equation. This paper proposes two updates to that equation based on the performance evaluation results of a simple parallel pi program written with OpenCilk. Performance evaluation was done by measuring execution time and instructions per cycle (IPC). The performance evaluation of the parallel program executed on the Intel Core i5 1240P processor did not indicate decreased performance due to asymmetric performance. Instead, the program with efficient work-stealing advantages from OpenCilk performed well. In the case of using the execution time of the P-CPU as a reference to obtain speedup, the evaluation results in a sublinear speedup. Conversely, in the case of using the execution time of the E-CPU as a reference, the evaluation results in a superlinear speedup. This paper proposes two updates to Amdahl’s law equation based on these two evaluation results.

Electroencephalography (EEG) signals are used to evaluate the activities of the brain. For the accidents occurring on the road, one of the primary reasons is driver fatigueness and it can be easily identified by the EEG. In this work, five efficient and robust approaches for the EEG-based driving fatigue detection and classification are proposed. In the first proposed strategy, the concept of Multi-Dimensional Scaling (MDS) and Singular Value Decomposition (SVD) are merged and then the Fuzzy C Means based Support Vector Regression (FCM-SVR) classification module is utilized to get the output. In the second proposed strategy, the Marginal Fisher Analysis (MFA) is implemented and the concepts of conditional feature mapping and cross domain transfer learning are implemented and classified with machine learning classifiers. In the third proposed strategy, the concepts of Flexible Analytic Wavelet Transform (FAWT) and Tunable Q Wavelet Transform (TQWT) are implemented and merged and then it is classified with Extreme Learning Machine (ELM), Kernel ELM and Adaptive Neuro Fuzzy Inference System (ANFIS) classifiers. In the fourth proposed strategy, the concepts of Correntropy spectral density and Lyapunov exponent with Rosenstein algorithm is implemented and then the multi distance signal level difference is computed followed by the calculation of the Geodesic minimum distance to the Riemannian means and finally tangent space mapping is implemented to it before feeding it to classification. In the fifth or final proposed strategy, the Hilbert Huang Transform (HHT) is implemented and then the Hilbert marginal spectrum is computed. Then using the Blackhole optimization algorithm, the features are selected and finally it is classified with Cascade Adaboost classifier. The proposed techniques are applied on publicly available EEG datasets and the best result of 99.13% is obtained when the proposed Correntropy spectral density and Lyapunov exponent with Rosenstein algorithm is implemented with the multi distance signal level difference followed by the calculation of the Geodesic minimum distance to the Riemannian means and finally tangent space mapping is implemented with Support Vector Machine (SVM) classifier.