查看更多>>摘要：Autonomous vehicles will be a reality in the next decade, transforming mobility, turning vehicles into software-driven products. This article presents the hardware and software architecture of the embedded systems of an autonomous vehicle developed in the Autonomous Mobility Laboratory at UNICAMP. This vehicle aims to enable the testing of cooperative strategies between the driver and the automated system. The proposal has been tested, allowing the integration of an automotive embedded system's reliability with the flexibility and capacity of distributed Linux and robotic operating system (ROS) based on PC-based computing systems. The article's main contribution is to include discussing how the automation and real-time systems should cooperate with the driver, which is an essential step for level 3 of SAE (J3016) automation of the vehicles.
查看更多>>摘要：Analysing the suitability of a particular anomaly detection algorithm in a real-time scenario is a challenging task since the benchmark studies are either restricted to a specific application or limited to characterisation study of outliers from a statistical point of view. This study makes an effort to design a system that performs characterisation study of anomaly detection algorithms based on data and anomaly statistics. Comparison of different anomaly detection algorithms was done by conducting an experimental study on a generated dataset that follows various data distributions and has distinct types and percentages of anomalies. Using this simulation model an application framework is proposed which is applicable to multiple industrial domains. Validation of the system is done using the case analysis that guides the users to utilise the recommender system for their application. Output of the recommender system suggests a suitable algorithm for their specific application.
查看更多>>摘要：The environment of the flotation plant is harsh, and the noise pollution of the collected froth images is severe. It is challenging to obtain real-time and high-quality froth images by common denoising methods. A spatial-temporal joint denoising method based on bubble dynamic features is proposed. This method first analyses the dynamic features of the bubble and detects the stability of each reference image sub-blocks; then selects the corresponding filtering to denoising according to the different states of the froth sub-blocks; and finally obtains a weighted average result of temporal filtering and spatial filtering. This method uses a modified and noise-robust cross-correlation method to estimate the sub-blocks' motion, which improves the denoising performance of time-domain filtering. The experiments show that the method can obtain a high signal-to-noise ratio and strong structural similarity result for non-static background images. It has also been well verified in the application of zinc flotation froth images.
查看更多>>摘要：Renewable energy (RE) is effectively used by many CSPs to build next-generation computing systems. However, it is highly unpredictable and not accessible 24 x 7. Recent studies have suggested that both NRE and RE sources can be used by CSPs to fulfil the demands/ requests of the users. In this paper, we propose a multi-objective renewable energy-based scheduling algorithm to make a fusion between energy cost and availability of NRE and RE resources. The primary objective is to map and distribute the requests to the resources, such that the energy cost is minimised and the usage of RE resources is maximised. The proposed algorithm is simulated using MATLAB and compared with the existing FABEF, SCA, RR, HAREF, MB and WF algorithms using four different datasets and two different metrics. The simulation results demonstrate the efficiency of the proposed algorithm in comparison with the existing algorithms.
查看更多>>摘要：With the increasing number of open APIs on the internet, reusing them to develop value-added new applications has received enormous attention. Mashup is the most popular technique for combining APIs into new applications. Against this background, the API-mashup ecosystem composed of APIs and mashups is emerging. This paper focuses on the API-mashup ecosystem of ProgrammableWeb.com , which is the largest web API portal. Although a few studies have investigated this API-mashup ecosystem, the understandings to it are still limited. In addition, the features of the API-mashup ecosystem may change due to its continuous evolvement. Therefore, this paper reinvestigates the API-mashup ecosystem of ProgrammableWeb by exploiting the latest data. We first conduct a statistical analysis to the current API-mashup ecosystem, and then explore the relationships between APIs or API providers to build cooperation networks of them. Finally, we analyse the derived cooperation networks and uncover some important features.
查看更多>>摘要：Research related to the authentication schemes in vehicular ad hoc networks (VANETs) still becomes a hot issue to discuss. In 2019, Cui and Tu proposed an efficient authentication scheme for vehicular ad hoc networks (VANETs) with batch verification using bilinear pairings. Their scheme was designed to improve the utilisation of the double-secret key in the identity-based batch signature (IBS) scheme published by Jianhong et al. and Bayat et al. Unfortunately, we found that Cui and Tu's identity-based conditional privacy-preserving authentication (IBCPPA) scheme is also insecure against non-repudiation attack. By those defects, a malicious user can broadcast some wrong messages to mislead the roadside unit (RSU) and deny its behaviour when a trusted authority (TA) traces it. In this article, we address the issue and give our improvement to withstand the above security threat.
查看更多>>摘要：Seismic waves are signals that may be generated by earthquakes. These waves are happening after a strong release of energy. Seismic waves may cause vibrations on the surface of the earth detected and recorded by a seismograph. We cannot directly predict where a high magnitude vibration will happen from recorded observations but with a hidden Markov model, we can predict an earthquake with a high magnitude, HMM will be implemented from earthquake historical data. An earthquake query system (EQS) is implemented to check the probability of specific state sequence. The proposed system can predict professionally if the next state will be an earthquake with 'strong' magnitude or not. Results showed that EQS can be used by governments for early warning and evacuations.
查看更多>>摘要：In this paper we propose a two-stage credit risk scoring approach that can estimate the probability of default (PD) and profit of the loan, stage 1 is credit scoring and stage 2 is profit scoring. In stage 1, the stacked generalisation (stacking) approach is used to train the model. In stage 2, select the loans that are predicted to be non-default in the stage 1, generate a new data set, build a profit prediction model using the stacking algorithm, and introduce internal rate of return (IRR) as the measure of profitability. Finally, the profitability performance of the loan portfolio is studied based on the predicted value of profit. The experimental results show that the predictive performance of the two-stage credit risk modelling approach proposed in this study overcomes the existing methods, and can help investors choose the most profitable loans on the P2P platform.
查看更多>>摘要：Because more and more applications need high performance yet large capacity storages, solid state drives (SSD) based on triple level cell (TLC) flash memory have been playing an essential role in the storage systems. Although significantly increasing storage capacity, TLC flash memory severely degrades the raw reliability and thus drastically decreases lifetime. However, after evaluating real flash chips, the researchers have shown that worn-out blocks can be reused in flash lifespan. This paper suggests a novel flash translation layer (FTL) called graceful degradation flash translation layer (GD-FTL) by downgrading worn-out TLC blocks to SLC blocks to extend lifetime and improve performance of SSDs. We further propose to store hot data on SLC-mode blocks and proactively conduct mode transitions to meet predefined service level objects. Four real workloads are used to evaluate the proposed GD-FLT. Experiment results show that GD-FLT can improve the performance and reduce write amplification of solid state drives.
NSTL