Reidentification (Re-id) of vehicles in a multicamera system is an essential process for traffic control automation. Previously, there have been efforts to reidentify vehicles based on shots of images with identity (id) labels, where the model training relies on the quality and quantity of the labels. However, labeling vehicle ids is a labor-intensive procedure. Instead of relying on expensive labels, we propose to exploit camera and tracklet ids that are automatically obtainable during a Re-id dataset construction. In this article, we present weakly supervised contrastive learning (WSCL) and domain adaptation (DA) techniques using camera and tracklet ids for unsupervised vehicle Re-id. We define each camera id as a subdomain and tracklet id as a label of a vehicle within each subdomain, i.e., weak label in the Re-id scenario. Within each subdomain, contrastive learning using tracklet ids is applied to learn a representation of vehicles. Then, DA is performed to match vehicle ids across the subdomains. We demonstrate the effectiveness of our method for unsupervised vehicle Re-id using various benchmarks. Experimental results show that the proposed method outperforms the recent state-of-the-art unsupervised Re-id methods. The source code is publicly available on https://github.com/andreYoo/WSCL_VeReid.

The performance of road defect segmentation (a.k.a. pixel-level road defect detection) has been improved alongside with remarkable achievement of deep learning. Those improvements need a large-scale and well-constructed dataset. However, road surface materials or designs vary from country to country, and the patterns of defects are hard to pre-define. In this paper, we propose a novel multi-source domain adaptation method to boost the performance of road defect segmentation on an unlabelled dataset. The proposed method generates multi-source ensembled labels using transferred information from models trained with multiple labelled source domains, which are utilised as supervisory signals for the unlabelled target domain. Furthermore, to reduce the domain gap between each source domain and a target domain, these domains are re-aligned with outlier repositioning to improve the defect segmentation performance. We demonstrate the effectiveness of our proposed method on Cracktree200, CRACK500, CFD, and Crack360 datasets. Experimental results show that the proposed method outperforms the existing unsupervised road defect segmentation methods and achieves competitive performance compared with recent supervised methods. The source code is publicly available on https://github.com/andreYoo/MSDA_RDS.git.

With the widespread of electric vehicles (EV), the necessity of installing EV charging facility has rapidly increased. Since operating EV charging facility are costly and complex, choosing a proper power operation scheme is critical in implementing a cost-effective charging service. Therefore, this article proposes an efficient power operation scheme for EV charging facility by jointly analyzing not only monetary issues with various power rate policies and battery wear-out costs of the energy storage system (ESS) but also the uncertainty issues caused by EV users' behavior under different charging requirements. By considering the issues, this article analyzes and formulates the problem with robust optimization techniques. By using the real-world EV operation datasets, the effectiveness of the proposed scheme is analyzed in terms of daily peak power and total cost. In addition, by applying the proposed scheme in an actual power system, it is shown that the proposed scheme is able to reduce the overall cost by 20.5% and reduce peak power by 17.3% compared to other benchmark models.

Recently, vehicle re-identification methods based on deep learning constitute remarkable achievement. However, this achievement requires large-scale and well-annotated datasets. In constructing the dataset, assigning globally available identities (Ids) to vehicles captured from a great number of cameras is labour-intensive, because it needs to consider their subtle appearance differences or viewpoint variations. In this paper, we propose camera-tracklet-aware contrastive learning (CTACL) using the multi-camera tracklet information without vehicle identity labels. The proposed CTACL divides an unlabelled domain, i.e., entire vehicle images, into multiple camera-level subdomains and conducts contrastive learning within and beyond the subdomains. The positive and negative samples for contrastive learning are defined using tracklet Ids of each camera. Additionally, the domain adaptation across camera networks is introduced to improve the generalisation performance of learnt representations and alleviate the performance degradation resulted from the domain gap between the subdomains. We demonstrate the effectiveness of our approach on video-based and image-based vehicle Re-ID datasets. Experimental results show that the proposed method outperforms the recent state-of-the-art unsupervised vehicle Re-ID methods. The source code for this paper is publicly available on https://github.com/andreYoo/CTAM-CTACL-VVReID.git.

With the evolutionary development of the Internet of Things (IoT), the demand for delay-sensitive applications has increased. In this manner, mobile-edge computing (MEC) has emerged as a promising technology to run these applications on mobile devices. Several studies have been conducted on pricing schemes in the MEC environment, and they have focused on the amount of offloaded data in pricing. However, under the previously proposed pricing policy, the server resource usage of users is not properly reflected in the payment, so users only try to occupy the server resources as much as possible without any consideration. To solve this problem, this article newly proposes a differential pricing scheme in which the unit price per second is determined based on the user’s usage of server computational resources. Also, it suggests the user’s optimal offloading strategy and server’s equilibrium pricing strategy by formulating Stackelberg game based on the proposed pricing scheme and execution delay. Several numerical results show that the proposed pricing scheme and strategies can solve the problems and can increase the efficiency of edge server’s computational resources.

Detecting unusual behaviors of insiders on enterprise resource planning (ERP) systems is one of the essential parts to reduce the risks of threatening and abusing enterprise resources by insiders. Many approaches to detect the behaviors based on rule-based systems and stochastic processes are currently limited to empirical monitoring using manually established algorithms or probabilistic boundaries. Those approaches need prior knowledge such as user permission guideline and process data characteristics. Unfortunately, obtaining prior knowledge is hard in practice, and these are not appropriate to detect atypical unusual behavior which can not be clearly defined using heuristic rules. Therefore, in this article, we propose a novel framework for unusual insider behavior detection (UIBD) for ERP systems. The proposed framework initially derives a discriminative model for normal behavior samples, and UIBD is conducted by computing an error using the model. Since the model is compiled using normal samples only, the error of unusual samples would be larger than normal ones. To derive a robust normal behavior model, we present adversarial recurrent autoencoder (ARAE). To demonstrate the efficiency of the proposed framework based on ARAE, we conduct experiments using a dataset composed of insider behaviors defined by sequences of security audit logs of ERP systems operating in real-world enterprises. The experimental results show that the proposed framework with ARAE can successfully detect unusual insider behaviors and outperform other methods to detect unusual insider behavior or threatening.

The key challenge of unsupervised vehicle re-identification (Re-ID) is learning discriminative features from unlabelled vehicle images. Numerous methods using domain adaptation have achieved outstanding performance, but those methods still need a labelled dataset as a source domain. This paper addresses an unsupervised vehicle Re-ID method, which no need any types of a labelled dataset, through a Self-supervised Metric Learning (SSML) based on a feature dictionary. Our method initially extracts features from vehicle images and stores them in a dictionary. Thereafter, based on the dictionary, the proposed method conducts dictionary-based positive label mining (DPLM) to search for positive labels. Pair-wise similarity, relative-rank consistency, and adjacent feature distribution similarity are jointly considered to find images that may belong to the same vehicle of a given probe image. The results of DPLM are applied to dictionary-based triplet loss (DTL) to improve the discriminativeness of learnt features and to refine the quality of the results of DPLM progressively. The iterative process with DPLM and DTL boosts the performance of unsupervised vehicle Re-ID. Experimental results demonstrate the effectiveness of the proposed method by producing promising vehicle Re-ID performance without a pre-labelled dataset. The source code for this paper is publicly available on https://github.com/andreYoo/VeRI_SSML_FD.git.

With the widespread of Internet-of-Things (IoT) environment, a big data concept has emerged to handle a large number of data generated by IoT devices. Moreover, since data-driven approaches now become important for business, IoT data markets have emerged, and IoT big data are exploited by major stakeholders, such as data brokers and data service providers. Since many services and applications utilize data analytic methods with collected data from IoT devices, the conflict issues between privacy and data exploitation are raised, and the markets are mainly categorized as privacy protection markets and privacy valuation markets, respectively. Since these kinds of data value chains (which are mainly considered by business stakeholders) are revealed, data providers are interested in proper incentives in exchange for their privacy (i.e., privacy valuation) under their agreement. Therefore, this article proposes a competitive data trading model that consists of data providers who weigh the value between privacy protection and valuation as well as other business stakeholders. Each data broker considers the willingness-to-sell of data providers, and a single data service provider considers the willingness-to-pay of service consumers. At the same time, multiple data brokers compete to sell their data set to the data service provider as a noncooperative game model. Based on the Nash equilibrium analysis (NE) of the game, the feasibility is shown that the proposed model has the unique NE that maximizes the profits of business stakeholders while satisfying all market participants.

The number of wireless access points (APs) have increased rapidly in recent years to support increasing demands of wireless local area network. However, some of the research findings show that many of these APs are actually idle mainly during off-peak hours, i.e., there is no active user to support within their coverage areas during that time. Nevertheless, to identify availability of users, all APs are remained powered-on always regardless the presence or absence of any active user inside their coverage areas. To save energy during off-peak hours in idle APs, sleep mechanism could be applied. In this paper, we propose a novel sleep mechanism for IEEE 802.11 wireless local area network APs. In our solution, an AP moves into sleep mode to maximize its energy efficiency (EE) while not harming traffic delay requirements. To decide length of sleep interval of an AP, we propose a dynamic sleep boundary decision algorithm which dynamically sets upper and lower bound of sleep duration considering traffic arrival rate and traffic delay requirements at a given time. Numerical results show the proposed scheme can improve EE of an AP significantly compared to the existing schemes without violating traffic delay requirements.

The Smart u-Learning System is designed to provide an interactive and social learning environment that accommodates emerging devices. This demonstration will show how teachers and students can use its interactivity and social features in live lecture situations.