Array最新文献

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.

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.

Early diagnosis and treatment of tomato leaf diseases increase a plant's production volume, efficiency, and quality. Misdiagnosis of disease by farmers can lead to an inadequate treatment strategy that hurts the tomato plants and agroecosystem. Therefore, it is crucial to detect the disease precisely. Finding a rapid, accurate approach to take care of the issue of misdiagnosis and early disease identification will be advantageous to the farmers. This study proposed a lightweight custom convolutional neural network (CNN) model and utilized transfer learning (TL)-based models VGG-16 and VGG-19 to classify tomato leaf diseases. In this study, eleven classes, one of which is healthy, are used to simulate various tomato leaf diseases. In addition, an ablation study has been performed in order to find the optimal parameters for the proposed model. Furthermore, evaluation metrics have been used to analyze and compare the performance of the proposed model with the TL-based model. The proposed model, by applying data augmentation techniques, has achieved the highest accuracy and recall of 95.00% among all the models. Finally, the best-performing model has been utilized in order to construct a Web-based and Android-based end-to-end (E2E) system for tomato cultivators to classify tomato leaf disease.

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.

Fast-growing smart city applications, such as smart delivery, smart community, and smart health, are generating big data that are widely distributed on the internet. IoT (Internet of Things) systems are at the centre of smart city applications, as traditional cloud computing is insufficient for satisfying the critical requirements of smart IoT systems. Due to the nature of smart city applications, massive IoT data may contain sensitive information; hence, various privacy-preserving methods, such as anonymity, federated learning, and homomorphic encryption, have been utilised over the years. Furthermore, limited concern has been given to the resource consumption for data privacy-preserving in edge computing environments, which are resource-constrained when compared with cloud data centres. In particular, differential privacy (DP) has been an effective privacy-preserving method in the edge computing environment. However, there is no dedicated study on DP technology with a focus on smart city applications in the edge computing environment.

To fill this gap, this paper provides a comprehensive study on DP in edge computing-based smart city applications, covering various aspects, such as privacy models, research methods, mechanisms, and applications. Our study focuses on five areas of data privacy, including data transmitting privacy, data processing privacy, data model training privacy, data publishing privacy, and location privacy. In addition, we investigate many potential applications of DP in smart city application scenarios. Finally, future directions of DP in edge computing are envisaged. We hope this study can be a useful roadmap for researchers and practitioners in edge computing enable smart city applications.

Recommender systems are widely-adopted by numerous popular e-commerce sites, such as Amazon and E-bay, to help users find products that they might like. Although much has been achieved in the area, most recommender systems are designed to work on top of centralized platforms that are traditionally supported by fixed infrastructure like the Internet. Hence, additional work is warranted to examine the applicability and performance of recommender systems in challenging environments that are characterized by dynamic network topology and variable transmission delays. This study deals with the design of a recommender system that is compatible in a delay-tolerant network where communication is supported by opportunistic encounters between participating nodes. The proposed approach combines collaborative filtering and content-based filtering techniques to generate rating predictions for users. To make the system more tolerant against interruptions, each node maintains a local recommender that generates predictions using user profiles that are obtained through opportunistic exchanges over a clustered topology. Simulation results indicate that the proposed approach is able to improve coverage while alleviating the cold-start problem.

Due to the emergence of social networking sites and social media platforms, there is faster information dissemination to the public. Unverified information is widely disseminated across social media platforms without any apprehension about the accuracy of the information. The propagation of false news has imposed significant challenges on governments and society and has several adverse effects on many aspects of human life. Fake News is inaccurate information deliberately created and spread to the public. Accurate detection of fake news from cyber propagation is thus a significant and challenging issue that can be addressed through deep learning techniques. It is impossible to manually annotate large volumes of social media-generated data. In this research, a hybrid approach is proposed to detect fake news, novel weakly supervised learning is applied to provide labels to the unlabeled data, and detection of fake news is performed using Bi- GRU and Bi-LSTM deep learning techniques. Feature extraction was performed by utilizing TF-IDF and Count Vectorizers techniques. Bi-LSTM and Bi-GRU deep learning techniques with Weakly supervised SVM techniques provided an accuracy of 90% in detecting fake news. This approach of labeling large amounts of unlabeled data with weakly supervised learning and deep learning techniques for the detection of fake and real news is highly effective and efficient when there exist no labels to the data.