arXiv subjects

Kien Nguyen

Publications and source records attributed to Kien Nguyen.

49 records · Page 3Linked to original sources

arXiv2019

A Privacy-Preserving, Accountable and Spam-Resilient Geo-Marketplace

Mobile devices with rich features can record videos, traffic parameters or air quality readings along user trajectories. Although such data may be valuable, users are seldom rewarded for collecting them. Emerging digital marketplaces allow owners to advertise their data to interested buyers. We focus on geo-marketplaces, where buyers search data based on geo-tags. Such marketplaces present significant challenges. First, if owners upload data with revealed geo-tags, they expose themselves to serious privacy risks. Second, owners must be accountable for advertised data, and must not be allowed to subsequently alter geo-tags. Third, such a system may be vulnerable to intensive spam activities, where dishonest owners flood the system with fake advertisements. We propose a geo-marketplace that addresses all these concerns. We employ searchable encryption, digital commitments, and blockchain to protect the location privacy of owners while at the same time incorporating accountability and spam-resilience mechanisms. We implement a prototype with two alternative designs that obtain distinct trade-offs between trust assumptions and performance. Our experiments on real location data show that one can achieve the above design goals with practical performance and reasonable financial overhead.

cs.CR↗

arXiv2019

Los Angeles Metro Bus Data Analysis Using GPS Trajectory and Schedule Data (Demo Paper)

With the widespread installation of location-enabled devices on public transportation, public vehicles are generating massive amounts of trajectory data in real time. However, using these trajectory data for meaningful analysis requires careful considerations in storing, managing, processing, and visualizing the data. Using the location data of the Los Angeles Metro bus system, along with publicly available bus schedule data, we conduct a data processing and analyses study to measure the performance of the public transportation system in Los Angeles utilizing a number of metrics including travel-time reliability, on-time performance, bus bunching, and travel-time estimation. We demonstrate the visualization of the data analysis results through an interactive web-based application. The developed algorithms and system provide powerful tools to detect issues and improve the efficiency of public transportation systems.

cs.DB↗

arXiv2019

Differentially Private Publication of Location Entropy

Location entropy (LE) is a popular metric for measuring the popularity of various locations (e.g., points-of-interest). Unlike other metrics computed from only the number of (unique) visits to a location, namely frequency, LE also captures the diversity of the users' visits, and is thus more accurate than other metrics. Current solutions for computing LE require full access to the past visits of users to locations, which poses privacy threats. This paper discusses, for the first time, the problem of perturbing location entropy for a set of locations according to differential privacy. The problem is challenging because removing a single user from the dataset will impact multiple records of the database; i.e., all the visits made by that user to various locations. Towards this end, we first derive non-trivial, tight bounds for both local and global sensitivity of LE, and show that to satisfy $ε$-differential privacy, a large amount of noise must be introduced, rendering the published results useless. Hence, we propose a thresholding technique to limit the number of users' visits, which significantly reduces the perturbation error but introduces an approximation error. To achieve better utility, we extend the technique by adopting two weaker notions of privacy: smooth sensitivity (slightly weaker) and crowd-blending (strictly weaker). Extensive experiments on synthetic and real-world datasets show that our proposed techniques preserve original data distribution without compromising location privacy.

cs.CR↗

arXiv2019

Constrained Design of Deep Iris Networks

Despite the promise of recent deep neural networks in the iris recognition setting, there are vital properties of the classic IrisCode which are almost unable to be achieved with current deep iris networks: the compactness of model and the small number of computing operations (FLOPs). This paper re-models the iris network design process as a constrained optimization problem which takes model size and computation into account as learning criteria. On one hand, this allows us to fully automate the network design process to search for the best iris network confined to the computation and model compactness constraints. On the other hand, it allows us to investigate the optimality of the classic IrisCode and recent iris networks. It also allows us to learn an optimal iris network and demonstrate state-of-the-art performance with less computation and memory requirements.

cs.CV↗

arXiv2018

Sparse Over-complete Patch Matching

Image patch matching, which is the process of identifying corresponding patches across images, has been used as a subroutine for many computer vision and image processing tasks. State -of-the-art patch matching techniques take image patches as input to a convolutional neural network to extract the patch features and evaluate their similarity. Our aim in this paper is to improve on the state of the art patch matching techniques by observing the fact that a sparse-overcomplete representation of an image posses statistical properties of natural visual scenes which can be exploited for patch matching. We propose a new paradigm which encodes image patch details by encoding the patch and subsequently using this sparse representation as input to a neural network to compare the patches. As sparse coding is based on a generative model of natural image patches, it can represent the patch in terms of the fundamental visual components from which it has been composed of, leading to similar sparse codes for patches which are built from similar components. Once the sparse coded features are extracted, we employ a fully-connected neural network, which captures the non-linear relationships between features, for comparison. We have evaluated our approach using the Liberty and Notredame subsets of the popular UBC patch dataset and set a new benchmark outperforming all state-of-the-art patch matching techniques for these datasets.

cs.CV↗

arXiv2018

Semantic Correspondence: A Hierarchical Approach

Establishing semantic correspondence across images when the objects in the images have undergone complex deformations remains a challenging task in the field of computer vision. In this paper, we propose a hierarchical method to tackle this problem by first semantically targeting the foreground objects to localize the search space and then looking deeply into multiple levels of the feature representation to search for point-level correspondence. In contrast to existing approaches, which typically penalize large discrepancies, our approach allows for significant displacements, with the aim to accommodate large deformations of the objects in scene. Localizing the search space by semantically matching object-level correspondence, our method robustly handles large deformations of objects. Representing the target region by concatenated hypercolumn features which take into account the hierarchical levels of the surrounding context, helps to clear the ambiguity to further improve the accuracy. By conducting multiple experiments across scenes with non-rigid objects, we validate the proposed approach, and show that it outperforms the state of the art methods for semantic correspondence establishment.

cs.CV↗

arXiv2018

Meta Transfer Learning for Facial Emotion Recognition

The use of deep learning techniques for automatic facial expression recognition has recently attracted great interest but developed models are still unable to generalize well due to the lack of large emotion datasets for deep learning. To overcome this problem, in this paper, we propose utilizing a novel transfer learning approach relying on PathNet and investigate how knowledge can be accumulated within a given dataset and how the knowledge captured from one emotion dataset can be transferred into another in order to improve the overall performance. To evaluate the robustness of our system, we have conducted various sets of experiments on two emotion datasets: SAVEE and eNTERFACE. The experimental results demonstrate that our proposed system leads to improvement in performance of emotion recognition and performs significantly better than the recent state-of-the-art schemes adopting fine-\ tuning/pre-trained approaches.

cs.CV↗

arXiv2018

SDN for End-Nodes: Scenario Analysis and Architectural Guidelines

The advent of SDN has brought a plethora of new architectures and controller designs for many use-cases and scenarios. Existing SDN deployments focus on campus, datacenter and WAN networks. However, little research efforts have been devoted to the scenario of effectively controlling a full deployment of end-nodes (e.g. smartphones) that are transient and scattered across the Internet. In this paper, we present a rigorous analysis of the challenges associated with an SDN architecture for end-nodes, show that such challenges are not found in existing SDN scenarios, and provide practical design guidelines to address them. Then, and following these guidelines we present a reference architecture based on a decentralized, distributed and symmetric controller with a connectionless pull-oriented southbound and an intent-driven northbound. Finally, we measure a proof-of-concept deployment to assess the validity of the analysis as well as the architecture.

cs.NI↗

arXiv2018

Big Data Analytics, Machine Learning and Artificial Intelligence in Next-Generation Wireless Networks

The next-generation wireless networks are evolving into very complex systems because of the very diversified service requirements, heterogeneity in applications, devices, and networks. The mobile network operators (MNOs) need to make the best use of the available resources, for example, power, spectrum, as well as infrastructures. Traditional networking approaches, i.e., reactive, centrally-managed, one-size-fits-all approaches and conventional data analysis tools that have limited capability (space and time) are not competent anymore and cannot satisfy and serve that future complex networks in terms of operation and optimization in a cost-effective way. A novel paradigm of proactive, self-aware, self- adaptive and predictive networking is much needed. The MNOs have access to large amounts of data, especially from the network and the subscribers. Systematic exploitation of the big data greatly helps in making the network smart, intelligent and facilitates cost-effective operation and optimization. In view of this, we consider a data-driven next-generation wireless network model, where the MNOs employ advanced data analytics for their networks. We discuss the data sources and strong drivers for the adoption of the data analytics and the role of machine learning, artificial intelligence in making the network intelligent in terms of being self-aware, self-adaptive, proactive and prescriptive. A set of network design and optimization schemes are presented with respect to data analytics. The paper is concluded with a discussion of challenges and benefits of adopting big data analytics and artificial intelligence in the next-generation communication system.

cs.IT↗

arXiv2018

Next Generation New Radio Small Cell Enhancement: Architectural Options, Functionality and Performance Aspects

The 3rd generation partnership project (3GPP) has been engaged in further advancing the evolved universal mobile telecommunications system (UMTS) terrestrial radio access network (E-UTRAN) and UTRAN based radio access network technologies. New radio (NR) is the 3rd generation partnership project (3GPP) endeavor for outlining and standardization of the 5th generation (5G) advanced radio access technology. 3GPP has released the first set of 5G NR standards, i.e., the non-standalone 5G radio specifications. As long-term evolution (LTE) technology is massively deployed and broadly accepted, the transition from LTE to 5G is very critical, and it is of maximal importance that the backward compatibility of 5G with LTE is considered. 3GPP has identified several architecture options for 5G. This article gives an overview of the NR architecture options, their deployment scenarios, and the key migration paths. The LTE-NR dual connectivity (DC) is presented. This DC scenario is unique in the sense that DC is being endowed for two different generations of 3GPP radio access technologies. We, further, present the integration of multipath transmission control protocol (MPTCP) with LTE-NR DC and DC-like aggregation, i.e., 3GPP-non-3GPP interworking to bring in the advantages of MPTCP in terms of link robustness, reliability and dynamic mapping between the traffic flows and the available paths. Finally, we discuss the future research and standardization directions of the next-generation networks.

cs.IT↗

arXiv2018

Deep Classification of Epileptic Signals

Electrophysiological observation plays a major role in epilepsy evaluation. However, human interpretation of brain signals is subjective and prone to misdiagnosis. Automating this process, especially seizure detection relying on scalp-based Electroencephalography (EEG) and intracranial EEG, has been the focus of research over recent decades. Nevertheless, its numerous challenges have inhibited a definitive solution. Inspired by recent advances in deep learning, we propose a new classification approach for EEG time series based on Recurrent Neural Networks (RNNs) via the use of Long-Short Term Memory (LSTM) networks. The proposed deep network effectively learns and models discriminative temporal patterns from EEG sequential data. Especially, the features are automatically discovered from the raw EEG data without any pre-processing step, eliminating humans from laborious feature design task. We also show that, in the epilepsy scenario, simple architectures can achieve competitive performance. Using simple architectures significantly benefits in the practical scenario considering their low computation complexity and reduced requirement for large training datasets. Using a public dataset, a multi-fold cross-validation scheme exhibited an average validation accuracy of 95.54\% and an average AUC of 0.9582 of the ROC curve among all sets defined in the experiment. This work reinforces the benefits of deep learning to be further attended in clinical applications and neuroscientific research.

cs.LG↗

arXiv2017

Shared Spectrum Access Communications: A Neutral Host Micro Operator Approach

In this paper, we conceive an advanced neutral host micro operator (NH-μO) network approach providing venues with services tailored to their specialized/specific requirements and/or local context related services that the mobile network operators (MNOs) are poorly-suited to providing it, as well as mobile broadband experience to the users from MNOs in a venue where only a single infrastructure is mandated under shared spectrum access framework. A radio access network slicing concept is conceived to support and optimize both the slice instance (SI) use cases independently and efficiently by running all network implementations in parallel, simultaneously on a common physical network infrastructure. We devise a common shared architecture for the NH-μO small cell base stations and dynamic spectrum assignment control unit, and their required functionalities supporting coexistence of different SIs as well as multiple MNOs in shared spectrum access communications. We devise both inter-SI and intra- SI dynamic spectrum allocation policies considering time-varying requirements of different SIs. The policies are capable of taking care of application level priority, -i.e., mixture of guaranteed quality of service and best-effort service users served by each SI while ensuring a healthy competition. Our proposed framework serves two-fold advantages, such as it gives the venue owner its own managed wireless networks tailored to its very specific requirements, and it also brings out cost savings and coverage extension for MNOs and efficiency of resources that arise from sharing wireless networks, and delivering the network capacity into high density venues.

cs.IT↗

arXiv2017

Outage Analysis of Offloading in Heterogeneous Networks: Composite Fading Channels

Small cells deployment is one of the most significant long-term strategic policies of the mobile network operators. In heterogeneous networks (HetNets), small cells serve as offloading spots in the radio access network to offload macro users (MUs) and their associated traffic from congested macrocells. In this paper, we perform analytical analysis and investigate how the radio propagation effects such as multipath and shadowing and small cell base station density affect MUs' offloading to small cell network (SCN). In particular, we exploit composite fading channels in our evaluation when an MU is offloaded to SCN with varying small and macro cell densities in the stochastic HetNets framework. We derive the expressions for outage probability (equivalently success probability) of the MU in macro network and SCN for two different cases, viz.: i) Nakagami-lognormal channel fading; ii) time-shared (combined) shadowed/unshadowed channel fading. We propose efficient approximations for the probability density functions of the channel fading (power) for the above-mentioned fading distributions that do not have closed-form expressions employing Gauss-Hermite integration and finite exponential series, respectively. Finally, the outage probability performance of MU with and without offloading options/services is analyzed for various settings of fading channels.

cs.NI↗