Details of a Researcher

Papers - Chen, Yin

Division display 1 - 20 of about 44 ／ All the affair displays >>

Time–frequency fusion for enhancement of deep learning-based physical layer identification

Zeng S., Chen Y., Li X., Zhu J., Shen Y., Shiratori N.

Ad Hoc Networks (Ad Hoc Networks) 142 2023.04

ISSN 15708705

Existing studies on deep learning-based physical layer identification have mainly exploited raw in-phase/ quadrature (IQ) samples or power spectral density (PSD) samples as inputs independently. The raw IQ and PSD samples represent the information in the time and frequency domains, respectively. It has been observed from the results of existing studies that identification using raw IQ samples outperforms that using PSD in low signal-to-noise ratio (SNR) regimes, and that identification using PSD outperforms that using raw IQ in high SNR regimes. In this paper, we propose to use the fusion of raw IQ and PSD samples to enhance deep learning-based physical layer identification. In particular, we design three general fusion frameworks, i.e., input, feature, and decision fusions, and integrate them with three typical deep neural network architectures of fully connected neural network, convolutional neural network, and recurrent neural network to form fusion identification schemes. We conduct experiments using 50 off-the-shelf Wi-Fi devices to validate the concerned fusion schemes and investigate their performance gains in identification and model training. Our experimental results verify that the proposed fusion identification schemes can achieve comparable or superior identification performances to the state-of-the-art schemes in the entire SNR regime. Moreover, for the considered fusion schemes, we further investigate the impacts of fusion strategies, deep-learning networks, and SNR conditions on the identification performance and training time.

Access to Document (DOI)

Fractal Dimension of DSSS Frame Preamble: Radiometric Feature for Wireless Device Identification

Li X., Chen Y., Zhu J., Zeng S., Shen Y., Jiang X., Zhang D.

IEEE Transactions on Mobile Computing (IEEE Transactions on Mobile Computing) 2023

ISSN 15361233

This paper demonstrates that the <italic>fractal dimension of frame preamble</italic> serves as a new radiometric feature that can be used together with other known radiometric features to enhance the identification accuracy in wireless device identification. We first propose a fractal dimension estimation scheme for direct-sequence spread spectrum (DSSS) frame preamble, then provide theoretical analysis to reveal how the fractal dimension is primarily determined by the device hardware imperfections, and thus prove that the fractal dimension serves as an intrinsic radiometric feature. We further show simulation results to verify our theoretical modeling of the fractal dimension and also numerically evaluate the effects of device hardware imperfections and wireless channels on the fractal dimension. Finally, by jointly applying the fractal dimension and the five features reported in the literature, we conduct extensive experiments to demonstrate that the fractal dimension can lead to a further improvement of the state-of-the-art result in the radiometric feature-based device identification.

Access to Document (DOI)

3D Spatial Sensing and Analysis Model of Closed Space CO2 Concentration

Goto D., Tsuge A., Huang W., Kawasaki T., Chen Y., Okoshi T., Nakazawa J.

2023 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events, PerCom Workshops 2023 (2023 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events, PerCom Workshops 2023) 408 - 411 2023

Access to Document (DOI)

Bus Crowdedness Sensing System Based on Carbon Dioxide Concentration

Huang W., Tsuge A., Chen Y., Okoshi T., Nakazawa J.

SenSys 2022 - Proceedings of the 20th ACM Conference on Embedded Networked Sensor Systems (SenSys 2022 - Proceedings of the 20th ACM Conference on Embedded Networked Sensor Systems) 806 - 807 2022.11

Crowdedness sensing of buses is playing an important role in the disease control of COVID-19 and bus resource scheduling. This research analyzes the relationship between carbon dioxide concentration, bus environment and the number of passengers by linear regression. Our prototype system collects the data of bus environment and carbon dioxide concentration to estimate the number of passengers in real time. By collecting the sensing data from a shuttle bus of university campus, we experimentally evaluate the feasibility and sensing performance of the crowdedness estimation model.

Access to Document (DOI)

A Bus Crowdedness Sensing System Using Deep-Learning Based Object Detection

Huang W., Tsuge A., Chen Y., Okoshi T., Nakazawa J.

IEICE Transactions on Information and Systems (IEICE Transactions on Information and Systems) E105D ( 10 ) 1712 - 1720 2022.10

ISSN 09168532

Crowdedness of buses is playing an increasingly important role in the disease control of COVID-19. The lack of a practical approach to sensing the crowdedness of buses is a major problem. This paper proposes a bus crowdedness sensing system which exploits deep learningbased object detection to count the numbers of passengers getting on and off a bus and thus estimate the crowdedness of buses in real time. In our prototype system, we combine YOLOv5s object detection model with Kalman Filter object tracking algorithm to implement a sensing algorithm running on a Jetson nano-based vehicular device mounted on a bus. By using the driving recorder video data taken from real bus, we experimentally evaluate the performance of the proposed sensing system to verify that our proposed system system improves counting accuracy and achieves real-time processing at the Jetson Nano platform.

Access to Document (DOI)

Visibility graph entropy based radiometric feature for physical layer identification

Zeng S., Chen Y., Li X., Zhu J., Shen Y., Shiratori N.

Ad Hoc Networks (Elsevier) 127 2022.03

Research paper (scientific journal), Joint Work, Accepted, ISSN 15708705

Emerging physical layer identification methods have demonstrated the capability to complement and enhance the device authentication of Internet of Things networks by exploiting the uncontrollable, unclonable, and unforgeable radiometric features resulted from randomly generated hardware imperfection in wireless devices. Multiple feature-based identification has proven an efficient and feasible approach to improving identification performance. At the same time, the lack of radiometric features effective for device identification is a major problem. Most of the existing features are derived from the view of the time, frequency, or phase domain. In this study, we explore the graph domain of wireless frame's preambles and propose a new radiometric feature called normalized horizontal visibility graph Shannon entropy (HVGE). At first, we introduce a preprocessing consisting of sample truncation and downsampling to enable the adjustment between the computational time of visibility graph (VG) conversion and the identification performance. Secondly, we propose the calculation method of the new HVGE feature from the VG representation. Finally, an experimental study using 50 off-the-shelf wireless devices was conducted to investigate the impact of the preprocessing parameters and the effect of noise and feature combinations on the identification performance gain.

Access to Document (DOI)

On the Performance Supremum of CFO Based Physical Layer Identification

Zeng S., Chen Y., Li X., Shen Y., Zhao D., Zhu J., Shiratori N.

Wireless Communications and Mobile Computing (Wireless Communications and Mobile Computing) 2022 2022

ISSN 15308669

Physical layer identification is an emerging technique that exploits physical layer features to identify wireless devices. The identification accuracy and the device quantity that can be identified at most are significant for the identification scheme. Existing works primarily focus on the feature correlation analysis for multifeature selection without investigating the least upper bound (supremum) of the performance of a single feature. The supremum indicates the limit of the performance, which is another sight for evaluating the quality of features and improving the performance of the identification scheme. Therefore, this paper first investigates the supremum of the performance of the most commonly used physical layer feature, i.e., carrier frequency offset (CFO). Specifically, we offer a rigorous mathematical analysis and derive the closed-form expression of the supremum of identification accuracy based on the max-min distance analysis (MMDA) criterion. And then, the supremum of the number of distinguishable devices is also analyzed. Finally, we conducted a simulation study to verify the theoretical analysis result.

Access to Document (DOI)

Rppuf: An ultra-lightweight reconfigurable pico-physically unclonable function for resource-constrained iot devices

Huang Z., Li L., Chen Y., Li Z., Wang Q., Jiang X.

Electronics (Switzerland) (MDPI) 10 ( 23 ) 2021.12

Research paper (scientific journal), Joint Work, Accepted

With the advancement of the Internet of Things (IoTs) technology, security issues have received an increasing amount of attention. Since IoT devices are typically resource-limited, con-ventional security solutions, such as classical cryptography, are no longer applicable. A physically unclonable function (PUF) is a hardware-based, low-cost alternative solution to provide security for IoT devices. It utilizes the inherent nature of hardware to generate a random and unpredictable fingerprint to uniquely identify an IoT device. However, despite existing PUFs having exhibited a good performance, they are not suitable for effective application on resource-constrained IoT devices due to the limited number of challenge-response pairs (CRPs) generated per unit area and the large hardware resources overhead. To solve these problems, this article presents an ultra-lightweight reconfigurable PUF solution, which is named RPPUF. Our method is built on pico-PUF (PPUF). By incorporating configurable logics, one single RPPUF can be instantiated into multiple samples through configurable information K. We implement and verify our design on the Xilinx Spartan-6 field programmable gate array (FPGA) microboards. The experimental results demonstrate that, compared to previous work, our method increases the uniqueness, reliability and uniformity by up to 4.13%, 16.98% and 10.5%, respectively, while dramatically reducing the hardware resource overhead by 98.16% when a 128-bit PUF response is generated. Moreover, the bit per cost (BPC) metric of our proposed RPPUF increased by up to 28.5 and 53.37 times than that of PPUF and the improved butterfly PUF, respectively. This confirms that the proposed RPPUF is ultra-lightweight with a good performance, making it more appropriate and efficient to apply in FPGA-based IoT devices with constrained resources.

Access to Document (DOI)

QoE-Aware Traffic Aggregation Using Preference Logic for Edge Intelligence

Tang P., Dong Y., Chen Y., Mao S., Halgamuge S.

IEEE Transactions on Wireless Communications (IEEE) 20 ( 9 ) 6093 - 6106 2021.09

Research paper (scientific journal), Joint Work, Accepted, ISSN 15361276

Traffic flows with different requirements of quality of service (QoS requirements) are aggregated into different QoS classes to provide differentiated services (Diffserv) and better quality of experience (QoE) for users. The existing aggregation approaches/QoS mapping methods are based on quantitative QoS requirements and static QoS classes. However, they are typically qualitative and time-varying at the edge of the beyond fifth generation (B5G) networks. Therefore, the artificial intelligence technology of preference logic is applied in this paper to achieve an intelligent method for edge computing, called the preference logic based aggregation model (PLM), which effectively groups flows with qualitative requirements into dynamic classes. First, PLM uses preferences to describe QoS requirements of flows, and thus can deal with both quantitative and qualitative cases. Next, the potential conflicts in these preferences are eliminated. According to the preferences, traffic flows are finally mapped into dynamic QoS classes by logic reasoning. The experimental results show that PLM presents better performance in terms of QoE satisfaction compared with the existing aggregation methods. Utilizing preference logic to group flows, PLM implements a novel way of edge intelligence to deal with dynamic classes and improves the Diffserv for massive B5G traffic with quantitative and qualitative requirements.

Access to Document (DOI)

A Development Method for Safe Node-RED Systems using Discrete Controller Synthesis

Yamauchi T., Hirano T., Li J., Kawasaki T., Chen Y., Tsuge A., Okoshi T., Nakazawa J., Yoshioka N., Palaiokrassas G., Litke A., Tei K.

Proceedings - IEEE Congress on Cybermatics: 2021 IEEE International Conferences on Internet of Things, iThings 2021, IEEE Green Computing and Communications, GreenCom 2021, IEEE Cyber, Physical and Social Computing, CPSCom 2021 and IEEE Smart Data, SmartData 2021 (Proceedings - IEEE Congress on Cybermatics: 2021 IEEE International Conferences on Internet of Things, iThings 2021, IEEE Green Computing and Communications, GreenCom 2021, IEEE Cyber, Physical and Social Computing, CPSCom 2021 and IEEE Smart Data, SmartData 2021) 130 - 137 2021

We present a controller to Node-RED translator (CNT), a tool for developing Node-RED systems that are safe and easy to update continuously. CNT introduces the discrete controller synthesis to conventional Node- Redsystems to provide a guarantee of flow correctness (safety). Flow correctness, which essentially means that the nodes fire at the timing intended by the designer, is crucial in smart city systems that require frequent application updates with no room for design errors. In this work, we propose a method for developing a Node- Redsystem using CNT along with its accompanying algorithm. We also report the results of experiments that demonstrate the usefulness of the proposed method.

Access to Document (DOI)

A HT Detection and Diagnosis Method for Gate-level Netlists based on Machine Learning

Du M., Huang Z., Chen Y., Li L., Wang Q., Liu J.

2021 6th International Conference on Signal and Image Processing, ICSIP 2021 (2021 6th International Conference on Signal and Image Processing, ICSIP 2021) 1070 - 1074 2021

The risk of hardware Trojan (HT) attack in the design step of the integrated circuit (IC) development process has become a 'hot spot' in hardware security. Despite some solutions presented in the literature, there are still limitations such as high time complexity, low HT detection accuracy, and the inability to locating HTs. This paper presents a novel HT detection and diagnosis method based on machine learning (ML) to identify the HT-related gates/nets maliciously inserted into the IC gate-level netlists at design stage. We partition the circuit into n sectors and extract five HT-related features from the netlists of each sector to construct a five-dimensional vector of that sector. Then, these n five-dimensional feature vectors are trained using support vector machine (SVM) to obtain the learned model. We have evaluated our method on the ISCAS'85 benchmark circuits. The experimental results show that our method can achieve 100% true positive rate (TPR), more than 90% true negative rate (TNR), complete 95% average precision and F-measure, average accuracy exceeds 80%. Moreover, it can also report the possible implantation location of a Trojan instance.

Access to Document (DOI)

A PUF-based Scheme for Identify Trusted Mobile Phone Accessories

Li L., Huang Z., Chen Y., Du M., Wang Q., Liu J.

Proceedings - 2020 International Conference on Networking and Network Applications, NaNA 2020 459 - 463 2020.12

Research paper (international conference proceedings), Joint Work, Accepted, ISSN 9781728189543

The rapid diffusion of mobile communication technology and smart phone devices has raised the concerns about the security problems of mobile phone accessories. Despite a few effort has been made in this aspect, there are still some deficiencies such as poor compatibility and limited application scope. This article presents a trusted mobile phone accessory identification scheme. Our method uses physically unclonable function (PUF) as hardware security primitives which are embedded in mobile phone accessories to generate digital signatures, so that they can be applied to identify authorized mobile phone accessories. We finally implement the proposed scheme on a field programmable gate array (FPGA) platform. Experimental results show that our solution can effectively identify trusted mobile phone accessories.

Access to Document (DOI)

DeepCounter: Collecting Garbage Disposal Data with Deep Learning

三上量弘, 陳寅, 中澤仁

報処理学会論文誌 61 ( 1 ) 36 - 48 2020.01

Research paper (scientific journal), Joint Work, Accepted

A Survey on Machine Learning against Hardware Trojan Attacks: Recent Advances and Challenges

Huang Z., Wang Q., Chen Y., Jiang X.

IEEE Access (IEEE) 8 10796 - 10826 2020

Research paper (scientific journal), Joint Work, Accepted

© 2013 IEEE. The remarkable success of machine learning (ML) in a variety of research domains has inspired academic and industrial communities to explore its potential to address hardware Trojan (HT) attacks. While numerous works have been published over the past decade, few survey papers, to the best of our knowledge, have systematically reviewed the achievements and analyzed the remaining challenges in this area. To fill this gap, this article surveys ML-based approaches against HT attacks available in the literature. In particular, we first provide a classification of all possible HT attacks and then review recent developments from four perspectives, i.e., HT detection, design-for-security (DFS), bus security, and secure architecture. Based on the review, we further discuss the lessons learned in and challenges arising from previous studies. Despite current work focusing more on chip-layer HT problems, it is notable that novel HT threats are constantly emerging and have evolved beyond chips and to the component, device, and even behavior layers, therein compromising the security and trustworthiness of the overall hardware ecosystem. Therefore, we divide the HT threats into four layers and propose a hardware Trojan defense (HTD) reference model from the perspective of the overall hardware ecosystem, therein categorizing the security threats and requirements in each layer to provide a guideline for future research in this direction.

Access to Document (DOI)

OmimamoriNet: An Outdoor Positioning System Based on Wi-SUN FAN Network

Chen Y., Sakamura M., Nakazawa J., Yonezawa T., Tsuge A., Hamada Y.

2018 11th International Conference on Mobile Computing and Ubiquitous Network, ICMU 2018 2019.02

Research paper (international conference proceedings), Joint Work, Accepted, ISSN 9784907626341

© 2018 IPSJ. We propose in this paper an outdoor positioning system based on Wi-SUN FAN network, the goal of which is to protect the elderly, young children and even pets via estimating their locations in a city. In order to achieve long-term portability and network-side positioning, the system does not directly rely on GPS receiver mounted on terminals but use machine learning for location estimation via the received signal strength indication (RSSI) measurements. In particular, the system consists of Wi-SUN beacons, Wi-SUN base-stations and vehicular devices. A beacon, attached to the one to be positioned, broadcasts wireless signal periodically so that its location can be estimated using machine learning algorithms from the RSSIs measured at multiple base-stations that are densely deployed over a city to construct an ad hoc network. Using the mobility of vehicles that roam over a city routinely, such like garbage collection trucks, buses and taxies. Vehicular devices containing both a Wi-SUN beacon and a GPS are used to collect RSSIs and the corresponding GPS coordinates to train the estimation models. We develop a prototype system consisting of 9 base-stations and deploy it to our university campus to conduct a field experiment to validate the proposed approach. Offline analysis on the data collected from the experiment showed that a RandomForest learner performs best among four selected learning algorithms using the default parameters of Weka 3.8, which achieves a mean absolute error of 35.43m and a root mean squared error of 44.21m, respectively. Evaluation on network performance is also conducted.

Access to Document (DOI)

DeepCounter: Using deep learning to count garbage bags

Mikami K., Chen Y., Nakazawa J., Iida Y., Kishimoto Y., Oya Y.

Proceedings - 2018 IEEE 24th International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2018 (IEEE ) 1 - 10 2019.01

Research paper (international conference proceedings), Joint Work, Accepted, ISSN 9781538677599

© 2018 IEEE. This paper proposes DeepCounter, an automotive sensing system where deep learning based image processing technology is used to automatically count the number of collected garbage bags from the video taken by a camera mounted on the rear of a garbage truck in order to sense a fine-grain spatio-temporal distribution on the amount of disposed garbage in cities that is envisioned to be helpful to develop novel applications related to garbage collection there. A prototype system is implemented on a GPU-integrated signal-board computer. A detection-tracking-counting (DTC) algorithm is developed and implemented based on the single shot multibox detector (SSD), a well-known real-time object detection algorithm. Experimental evaluation validates the feasibility of the proposed approach using video of realistic garbage collection in Fujisawa city, Japan.

Access to Document (DOI)

End-to-End Physical Layer Authentication for Dual-Hop Wireless Networks

Zhang P., Zhu J., Chen Y., Jiang X.

IEEE Access (IEEE) 7 38322 - 38336 2019

Research paper (scientific journal), Joint Work, Accepted

© 2013 IEEE. End-to-end (E2E) physical layer authentication for multi-hop wireless networks is still not well-explored by now. Like one step forward in this direction, this paper focuses on the E2E physical layer authentication in a dual-hop wireless network with an untrusted relay and proposes a corresponding physical layer authentication scheme. The scheme fully utilizes the location-specific features of both channel amplitude and delay interval of cascaded channels and adopts the artificial jamming technique, so that it is not only resistant to the impersonate attack from an unauthorized transmitter but also resilient to the replay attack from the untrusted relay. Theoretical analysis is further conducted to derive the expressions for the probabilities of false alarm and missed detection, which are two fundamental metrics of authentication performance. Finally, the numerical and simulation results are provided to illustrate both the efficiency of these theoretical results and the E2E authentication performance of dual-hop wireless networks under the proposed scheme.

Access to Document (DOI)

Poster abstract: Using deep learning to count garbage bags

Mikami K., Chen Y., Nakazawa J.

SenSys 2018 - Proceedings of the 16th Conference on Embedded Networked Sensor Systems (ACM) 329 - 330 2018.11

Research paper (international conference proceedings), Joint Work, Accepted, ISSN 9781450359528

This poster introduces DeepCounter, an automotive sensing system to providing a fine-grained spatio-temporal distribution on the amount of disposed garbage bags. In the system, deep learning based image processing is used to automatically count the number of collected garbage bags from the video taken by a camera mounted on the rear of a garbage truck. A prototype system is implemented and experimental evaluation validates the feasibility of our proposal using realistic garbage collection videos in Fujisawa city, Japan.

Access to Document (DOI)

SOXFire: XMPPに基づく都市センサ情報流通基盤

米澤拓郎，伊藤友隆，陳寅，中澤仁

情報処理学会MBL研究会第88回研究会 2018.08

Research paper (conference, symposium, etc.), Joint Work

Counting garbage bags from garbage collecting video using deep learning

Kazuhiro Mikami, Makoto Kawano, Yin Chen, Jin Nakazawa

the 32nd Annual Conference of JSAI 2018.06

Research paper (conference, symposium, etc.), Joint Work, Accepted

　 Previous page - Next page 　