Dong Yang

Georgia Institute of Technology | GT · School of Mechanical Engineering

Deep neural network (DNN) inference task offloading is an essential problem of edge intelligence, which faces the challenges of limited computing resources shortage of edge devices and the dynamics of edge networks. In this article, the DNN inference task offloading problem in queue‐based multi‐device and multi‐server collaborative edge computing i...

Time-sensitive networking (TSN) can help standardize deterministic Ethernet across industrial automation. The deterministic guarantee of TSN is based on network resource scheduling in the unit of flow. However, the state-of-the-art TSN single flow scheduling scheme cannot meet the coordinated scheduling requirements of multiple data flows in advanc...

More data and information is being captured from systems, machines, and devices and made available to industrial IT (information technology) systems. The information is processed on-the-fly, enabling IT-based management systems to generate updated information for real-time control of the manufacturing processes. This data capturing and collection f...

With the great evolution of human society from the information era to the smart automation era, intelligent production and maintenance have become the core orientation of Industry 4.0. Data-driven intelligent predictive maintenance (IPdM) offers potential solutions to satisfy the urgent demand of predicting impending failures and mitigating unplann...

In this paper, we aim to make the best joint decision of device selection and computing and spectrum resource allocation for optimizing federated learning (FL) performance in distributed industrial Internet of Things (IIoT) networks. To implement efficient FL over geographically dispersed data, we introduce a three-layer collaborative FL architectu...

Performing deep neural network (DNN) inference in real time requires excessive network resources, which poses a great challenge to the resource-limited industrial Internet of things (IIoT) networks. To address the challenge, in this paper, we introduce an end-edge-cloud orchestration architecture, in which the inference task assignment and DNN mode...

Research about online failure prediction of rail vehicle core components (such as wheels, bearings, and bogies) based on big data and artificial intelligence (AI) has become popular in view of its role of improving rail vehicle operation safety. The recent vibration energy harvesting sensor network relieves sensor nodes' dependence on wired power,...

Due to the time-varying characteristics of energy harvesting sources, it is a challenge for energy harvesting to provide stable energy output. In this paper, the time fair energy allocation (TFEA) problem is investigated, and an utility maximization framework is proposed to guarantee both time fairness and energy efficiency of energy allocation. Th...

With the rapid development of artificial intelligence and industrial Internet of things (IIoT) technologies, intelligent predictive maintenance (IPdM) has received considerable attention. To efficiently predict impending failures and mitigate unexpected downtime, while satisfying the instant maintenance demands of industrial facilities is very impo...

Ultrawideband (UWB) wireless communication is a promising spread-spectrum technology for accurate localization among devices characterized by a low transmission power, a high rate and immunity to multipath propagation. The accurately of the clock synchronization algorithm and the time-difference-of-arrival (TDOA) localization algorithm provide prec...

Accurate and real-time perception of the operating status of rolling bearings, which constitute a key component of rotating machinery, is of vital significance. However, most existing solutions not only require substantial expertise to conduct feature engineering, but also seldom consider the temporal correlation of sensor sequences, ultimately lea...

With recent adoption of Wireless Sensor-Actuator Networks (WSANs) in industrial automation, wireless control systems have emerged as a frontier of industrial networks. Hence, it has been shown that existing standards and researches concentrate on the reliability and real-time performance of WSANs. The multipath retransmission scheme with multiple c...

In 2016, the IEEE task group ah (TGah) released a new standard called IEEE 802.11ah, and industrial Internet of Things (IoT) is one of its typical use cases. The restricted access window (RAW) is one of the core MAC mechanisms of IEEE 802.11ah, which aims to address the collision problem in the dense wireless networks. However, in each RAW period,...

With the tremendous revival of artificial intelligence, predictive maintenance (PdM) based on data-driven methods has become the most effective solution to address smart manufacturing and industrial big data, especially for performing health perception (e.g., fault diagnosis and remaining life assessment). Moreover, because the existing PdM researc...

As a key component of rotating machinery, the health perception of bearings is essential to ensure the safe and reliable operation of industrial equipment. In recent years, research on equipment health perception based on data-driven methods has received extensive attention. Overall, most studies focus on several public datasets to verify the effec...

In recent years, wireless communication has been widely adopted in the field of industrial systems. Compared with traditional wired control and monitoring systems, wireless control and monitoring systems are cost-effective and easy to deploy. On the other hand, IEEE 802.11-based wireless technology is widely applied in many areas due to its popular...

Wireless sensor and actuator network (WSAN) is increasingly recognized as an important technology in the realization of the future Internet of Things (IoT). The ability to cater to the demands of real-time, reliable and resource-constraint communication in industrial areas is highly dependent on efficient scheduling of communication links. Harsh in...

Industrial wireless sensor networks (IWSNs) have mainly been used to monitor applications, but recently an interest in control and safety applications has emerged. Functional safety and communication in open transmission systems have been laid down in the IEC 61784-3-3 standard. The standard is based on a cyclic polling mechanism, which consumes a...

Wireless control systems for industrial automation have been gaining popularity in recent years owing to the low cost of their components and their ease of deployment. Wireless Local Area Network (WLAN) is a good candidate for industrial wireless applications, especially for soft real-time control systems. However, unbalanced traffic loads in areas...

With the prevalence of low-power wireless devices in industrial applications, concerns about timeliness and reliability are bound to continue despite the best efforts of researchers to design Industrial Wireless Sensor Networks (IWSNs) to improve the performance of monitoring and control systems. As mobile devices have a major role to play in indus...

Despite the fact that a number of research efforts in the area of Industrial Wireless Sensor Networks (IWSNs) exist, there is a lack of really practical IWSN implementations, deployments, and in-field applications. This paper presents the design and implementation of an IWSN for welder machine systems, called WirelessCAN which is based on WirelessH...

Industrial wireless sensor networks (IWSNs) have the potential to contribute significantly in areas such as cable replacement, mobility, flexibility, and cost reduction. Nevertheless, the industrial environment that the IWSNs operate in is very challenging because of dust, heat, water, electromagnetic interference, and interference from other wirel...

SUMMARY Cloud computing is rapidly expanding as an alternative service deployment platform today. This brings forth many new challenges in migrating enterprise applications into cloud. To enable enterprises to benefit from migration while achieving cost-efficiency and keeping sensitive user data confidential against untrusted servers, planning whic...

Most applications of industrial wireless sensor networks (IWSNs) should converge process data generated by each node to the central manager. The data collection operation results in an important communication primitive referred to as convergecast. Convergecast is a many-to-one communication paradigm as a critical functionality deployed for industri...

Despite lots of research efforts in the area of Industrial Wireless Sensor Networks (IWSNs), there is a lack of really practical IWSN implementations, deployments and in-field experiments. This demo presents the design and implementation of an IWSN for welder machine systems based on the first IWSN standard WirelessHART. The goal of this work is to...

Developing, deploying, or reprogramming an application in a short time and at a low cost is necessary in wireless vehicular sensor and vehicular ad hoc networks. However, the existing technologies, which usually take a long time or require a high cost, cannot support a system and common solution. In this paper, we propose an application-customized...

Lots of traditional distributed ride-sharing services match vehicles with drivers and passengers geographic information only. When urban road congestion situation is particularly serious, such as Beijing's rush hour, the waiting time for the passengers is too long which affects the quality of the service. So we propose a distributed ride-sharing se...

In recent years, trust-aware routing protocol plays a vital role in security of wireless sensor networks (WSNs), which is one of the most popular network technologies for smart city. However, several key issues in conventional trust-aware routing protocols still remain to be solved, such as the compatibility of trust metric with QoS metrics and the...

Industrial Wireless Sensor Networks (IWSNs) consist of a central manager, gateways and field devices with sensing, signal processing and wireless communication capabilities. Convergecast is a many-to-one industrial communication paradigm which is used for process measurement and control applications. Convergecast scheduling in IWSNs is to determine...

Virtual machine (VM) live migration, the key problem of modern virtualized data centers, is a challenging task since 1) Frequent traffic across data center between coupling VMs limits the efficiency of current methods. 2) Most existing approaches suffered from poor scalability issues as multi-objective optimization is still an open question in thes...

A growing trend in the automation industry is to use wireless technologies to reduce cable costs and deployment time, unlock stranded information in deployed devices and enable wireless control applications. The WirelessHART protocol is the first open and interoperable industrial wireless sensor network standard, which proposes a combination of tim...

In this paper, the product configuration problems that are characterized by cardinality-based configuration rules are dealt with. Novel configuration rules including FI and EI rules are presented to clarify the semantics of inclusion rules when cardinalities and hierarchies of products are encountered. Then, a configuration graph is proposed to vis...

Recent research in the designing of an elegant mapping service to map identifiers onto locators in networks with locator/identifier separation, focuses on solving practical issues related to mapping system. However, how to provide entire secure support in separation networks is still an open issue. In this paper, we present the design and evaluatio...

Research studies on smart cities have been conducted, which will enable a better management of the available resources. Industrial wireless sensor networks (IWSNs) are important part of smart city. IWSNs are used for process measurement and control applications in harsh and noisy industrial environments. As substitutes for traditional wired industr...

The energy efficiency of modern data centers has become a practical concern and has attracted significant attention in recent years. In contract to existing solutions that primarily focuses on only one specific aspect of management to reduce energy consumption, this paper explores the balance between server energy consumption and network energy con...

With the success of wireless technologies and the number of wireless devices increasing, the wireless coverage footprint expands and removes the needs of wired networks for industrial applications. Wireless industrial sensor networks (WISNs) are a type of wireless sensor networks (WSNs), which dedicate to industrial applications. The WISNs bring se...

Product configuration is an essential means for selecting various components to constitute a customized product with the aim of meeting the individualized requirements of a customer. Nevertheless, configuration conflicts may occur when too strict requirements of the customer are given and thus any configuration cannot be found to satisfy the custom...

While locator/identifier split makes Internet routing more scalable, the promise of a mapping system that resolves a service to corresponding location is yet to be realized. Part of the challenge is due to most current approaches only focusing on how to find the location of a host, not the location of a service, which make these systems rely on ext...

TDMA has been resumed for industrial wireless sensor network (IWSN) like WirelessHART and ISA 100.11a recently, because TDMA is suitable for periodic traffic which is predictable to pre-assign. However, for random traffic TDMA degenerates to inefficient slotted ALOHA. In our previous work, we propose a new medium access control (MAC) scheme called...

Image semantic annotation can be viewed as a multi-class classification problem, which maps image features to semantic class labels, through the procedures of image modeling and image semantic mapping. Bayesian classifier is usually adopted for image semantic annotation which classifies image features into class labels. In order to improve the accu...

The singular points of fingerprints, namely core and delta, play an important role in fingerprint recognition and classification systems. Several traditional methods have been proposed; however, these methods cannot achieve the reliable and accurate detection of poor-quality fingerprints. In this paper, an algorithm is proposed which combines impro...

The goal of service composition is to create value-added services which automatically composed of exiting services based on dynamic user requirements. Most research on service composition is based on logical reasoning, and do not consider dynamic services requirements and network status. In this paper we present a novel resource-oriented algorithm....

With the development of mass customization (MC) paradigm, service product/package configuration is getting crucial to service industry. Aiming to extend the achievements of product configuration in manufacturing industry to service industry and considering ontology’s reusability, an ontology-based service product modeling approach for configuration...

All modern indoor swimming pools have a large volume, the water temperature control system is the serious delay and serious inertia nonlinear system. The traditional PLC control system based on PID controller can not meet the control requirements. This paper presents an integrated control system composed of a fuzzy automatic optimization algorithm...

In the design of satellite assembly, it is a new task that a full-scale digital mockup is generated using full concurrent engineering environment based on network. In this paper, the top-down technical basis, method of defining satellite model, the progress of satellite design are introduced to implement the application of concurrent engineering en...

As more and more wireless devices use the 2.4 GHz radio spectrum, the coexistence of 2.4 GHz wireless devices operating in one place has become a hot topic. With low transmit power, the widely deployed IEEE 802.15.4-based networks are easily interfered with by other 2.4 GHz wireless networks, such as IEEE 802.11. IEEE 802.15.4-based wireless networ...

Process capability indices measure the ability of a production process to produce items within specification limits. The calculation of process capability indices has been focusing on using traditional frequency approach, which requires a large sample size for an accurate estimation. In order to eliminate this defect of traditional frequency approa...

In an image semantic annotation system, it often encounters the large-scale and high dimensional feature datasets problem, which leads to a slow learning process and degrading image semantic annotation accuracy. In order to reduce the high time complexity caused by redundancy information of image feature dataset, we adopt an improved affinity propa...

Web service composition is very important in web service technology. Domain Ontology is used for semantic web service match and automatic web service composition. When a web service is registered,it will be related to the concepts in the domain ontology with its output concepts. To start a semantic match or composition starts, only the related web...

In order to obtain the better analysis of the multiple reentrant manufacturing systems (MRMSs), their modeling and analysis from both micro- and macroperspectives are considered. First, this paper presents the discrete event simulation models for MRMS and the corresponding algorithms are developed. In order to describe MRMS more accurately, then a...

Service composition system in wireless sensor networks treats software components provided by sensors as services. Most research into prolongation of uptime of sensor networks is based on adaptive mechanism at the MAC layer and physical layer to minimize the energy consumption and do not consider integration of services requirement and energy of se...

The identifier split is a design principle for new Internet architectures such as Universal Network, Lisp, which make Internet more scalable, reliable and security. One important form of identifier split in Universal Network is connection identifier/access identifier (CID/AID) split which is introduced to improve security isolation during communica...

Wireless networks based on IEEE 802.15.4 have paid great attention to the coexistence problem between themselves and with other non-IEEE 802.15.4 wireless networks. This problem has been further emphasized by two new industry wireless standards, WirelessHART and ISA100 that are set to meet special industry requirements. In this paper, we firstly re...

This paper proposes a new hybrid method for machine transliteration Our method is based on combining a newly proposed two step conditional random field (CRF) method and the well known joint source channel model (JSCM) The contributions of this paper are as follows (1) A two step CRF model for machine transliteration is proposed The first CRF segmen...

The project was one of the most important projects of PRC Land & Resources Ministry in 2001. Land-using Dynamic RS Monitoring was significant components of PRC Land & Resources Ministry new overall investigation of land and resources. The implementation of this project was very important to strengthen land management, ensure the realization of dyna...

The Internet has evolved from its original design. (1)The user cares about what they are looking for, not which machine provides the data or the service. The host-to-host Internet tends to become a data-oriented network. (2) In the pressures of commerce and security, the middleboxes, such as network address translators (NATs), firewalls and caching...

Based on the organizational learning theory and social exchange theory, this article builds theoretical model to describe how different types of strategic orientations affect the knowledge acquisition; and the moderating effects of both informal control and formal control on the relationship between the EO, MO LO and knowledge acquisition of local...

In the early days of the Internet layered design, the information between layers did not exchange in large amount frequently. With the rapid growth of the Internet, the emergence of many technologies such as service data partition, multi-connection and multi-path has made it possible to frequently exchange complex information between layers. With r...

Based on the analysis of the nonlinearity of ferrite material under high power condition, this paper proposes some effective measures to reduce the nonlinearity and the intermodulation distortion of the system. These measures include selecting appropriate materials, correctly designing inner conductor and using of heat conductive body in the extern...

The project adopted GPS to plate conjunction, gaining the three-dimensional coordinates of photograph control points, obtaining ground features in spatial point locations and attribute information throughput photo annotation. Indoor work used digital photography system DPS, firstly to scan 1:4000 scale aerial photography film by UltraScan 5000 scan...

Navigation electronic map, one of the electronic maps or databases which contain spatial position geographical coordinates can be combined with spatial positioning system and guide man or means of transportation accurately to arrive from place of departure to place of destination with spatial information service function of location-based services...

The project constituted Jinan City E-class GPS control network, 5"-class GPS control network and the fourth-order level network, providing high-precision geodetic datum; field work laid the aerial photography ground signs, adopting GPS to plate conjunction, gaining the three-dimensional coordinates of photograph control points, obtaining ground fea...

Churn is one of the main problems faced by all P2P networks. This paper surveys the existing theories and methods about Churn. On the basis of the generation mechanism of Churn, this study summarizes the major steps of the Churn problem solution: precise measurement of Churn, analysis of the impact of Churn on P2P performance, and provision of spec...

Do the simultaneous pursuit of exploitative and explorative activities will add to or detract from innovation performance? We develop a model of firms as essentially ambidextrous, i.e. as engaging in both exploitative and explorative behavior. According to dynamic capabilities, we find that firms with ambidextrous capabilities - those that both use...

In the field of product modular design, it is desirable to have a methodology leading to a dynamic product design responding to the changing market. In this article, an option-pricing method is proposed for the module introduction decision making. At each stage of the module introduction processes, the decision maker can decide to add, reject and m...

This paper presents a joint optimization method of a two-step conditional random field (CRF) model for machine transliteration and a fast decoding algorithm for the proposed method. Our method lies in the category of direct orthographical mapping (DOM) between two languages without using any intermediate phonemic mapping. In the two-step CRF model,...

A new chelating matrix has been prepared by immobilising sulfanilamide (SA) on silica gel (SG) surface modified with 3-chloropropyltrimethoxysilane as a sorbent for the solid-phase extraction (SPE) Cu(II), Zn(II) and Ni(II). The determination of metal ions in aqueous solutions was carried out by inductively coupled plasma optical emission spectrome...

Semantic image annotation can be viewed as a classification problem, which maps image features to semantic labels, through the procedures of image modeling and image-semantic mapping. In order to improve the performance of image modeling, we propose a novel method which is based on affinity propagation (AP) algorithm. For a given image, low-level i...

Services in the next generation Internet, Uni- versal Network, is distinct from that in the current network. The reason is that the former has QoS (quality of sevice) grading. In the universal network, different services have different QoS; therefore, service discovery in the Universal Network is quite distinct from that of the present network. In...

Considering some reasonable and simplified hypothesis, this paper presents a short-circuit current model based on the circuit theory. Power receiving capability on the limitation of short-circuit current is analyzed according to this model. The example of Jinan power grid in China is computed to verify the applicability of this short-circuit curren...

Fingerprint ridge distance is a very useful parameter in AFIS (automatic fingerprint identification system), it can be used for fingerprint enhancement, identification or classification. In this paper, a new ridge distance estimation method based on the ridge search is presented. Firstly, we use the IPL(initial points line) to select the initial-po...

The dynamics of peers, namely Churn, is an inherent property of peer-to-peer (P2P) systems and is critical to their design and evaluation. Although every excellent P2P protocol has some solution to this issue, studies on Churn are still seldom. This paper studies various factors related to Churn, and uses them to analyze and evaluate P2P protocols....

This paper describes our system for "NEWS 2009 Machine Transliteration Shared Task" (NEWS 2009). We only par- ticipated in the standard run, which is a direct orthographical mapping (DOP) be- tween two languages without using any intermediate phonemic mapping. We propose a new two-step conditional ran- dom field (CRF) model for DOP machine translit...

Low-lying and high-spin states of 124Cs are studied through the 116 Sn(11 B,3n)124 Cs reaction at a beam energy of 45 MeV. Several new linking transitions are observed, including three transitions between the yrast and πh11/2 ⊗ νd3/2 bands and two transitions between the yrast and πh11/2 ⊗ ν(d5/2, g7/2) bands. These transitions fix the excitation e...

In large-scale cluster systems, the failure rate of network connection is non-negligibly high. A cluster file system must have the ability to handle network failures in order to provide high-available data accesses service. Traditionally, network failure handling is only guaranteed by network protocol, or implemented within the file system semantic...

In this paper, a novel framework and methodology based on hidden semi-Markov models (HSMMs) for high PM2.5 concentration value prediction is presented. Due to lack of explicit time structure and its short-term memory of past history, a standard hidden Markov model (HMM) has limited power in modeling the temporal structures of the prediction problem...

Effective and efficient development of product configuration systems, including the modeling of product configuration knowledge and the development of inference systems, is a key successful factor to implement mass customization paradigm. Ontology-based method for knowledge representation offers a means for the reuse and sharing of knowledge unambi...