Researches

*Note: IEEE, SPIE and other institutions hold the copyrights on many papers listed here. Reproduction and distribution of these documents may be governed by those copyrights. To get softcopies of our published papers, please contact the publishers.

In the last few years, we are interested in the research topics related to embedded system, real-time systems, sensor information systems, and database systems. Although one may find we have broad research topics, the core of our research is resource allocation optimization. This technique can be applied to several application domains. In the past five years, we have done researches in the following four areas: (1) Component Design for SISARL Services and Devices, (2) System Software for Heterogeneous Multicore Plat- forms, (3) Workflow-Based Framework for User-Centric Cyber-Physical Systems and Services, and (4) self-X middle-ware for machine-to machine networks. The full list of our publication can be found another page.

2014 Research Summary: ResearchSummary2014

Research Activities:

[tab name=’SISARL’] Component Design for SISARL Services and Devices

The acronym SISARL stands for Sensor Information Systems (Services) for Active Retirees and Assisted Living. It refers broadly to con- sumer electronic and assistive appliances, as well as services, designed to enrich the quality of life of elderly individuals and to help them live actively and independently. Examples are object loca- tors that help us to find household and personal items; smart storage pantries that inventory grocery supplies and notify designated suppliers for just-in-time replenishment; medicine dispensers that help to ensure correctness and enforce compliance of medication schedules; monitors that record and process vital sign signals, detect irregularities, and send appropriate notifications; and robotic helpers that enhance dexterity and accessibility and minimize the effects of functional limitations.

The thrusts of our work are on technologies for the design, production, and quality assurance of easy-to-use, dependable SISARL appliances and services with state-of-art and future capabilities. These appliances and services are not only needed to improve the well-being of an increasingly larger segment of the global population, but they also present to the ICT (Information and Communication Technologies) industry a tremendous new business opportunity. We want to help the industry to shorten the time and lower the cost required to bring families of high-quality SISARL products and services to market. Problems to be solved include how to partition diverse SISARL appliances and services into common components; how to configure and integrate the compo- nents in a systematic, verifiable way to build diverse appliances and services; how to design and implement the appliances for compositional and incremental verification, validation and certifica- tion; how to make the appliances easily customizable to users’ needs, preferences, and available support infrastructures; how to ease the incorporation of future extensions and advancements into existing SISARL; and how to effectively exploit application/platform co-design, software/hardware co-design and SoC (system-on-a-chip) technologies.

Our research aims to fill voids in the science and technology needed to strengthen the foundation of component-based design, integration and quality assurance for SISARL. We are also developing a general architectural framework, supported by a repository of user scenarios, SISARL application components, integration platforms and middleware, as well as verification and validation methods 1 and tools, with which one can evaluate tradeoffs and carry out system integration, quality assurance and certification. The framework will provide an environment for experimentation with and eval- uation of SISARL products and the methodologies and tools used to produce them. Parts of our research results have been published on numerous prestigious international conference and journals. In 2006, we presented the study on medication scheduling algorithm on IEEE Real-Time Systems Symposiums [1], the design and implementation for medication authoring tool and prescription algebra for medication use on IEEE International Conference on Systems, Mans, and Cybernetics 2006 [2], [3]. In 2007, we presented the design and implementation for the integration framework for medication-use process on IEEE International Conference on Systems, Mans, and Cybernetics 2007 [4]. In 2008, we presented the design and implementation of a software services composed by web services on IEEE International Conference on Systems, Mans, and Cybernetics 2008 [5]. In 2009, we present the design and implementation of embedded workflow framework on IEEE RTAS 2009 [6] and intelligent nurse cart on International Conference on Biomedical Engineering and Informatics [7]. We also published our results on IFIP SEUS 2010 [8], IEEE HealthCom 2010 [9], IEEE Systems Journal [10], and Foundations of Computing and Decision Science [11].

[/tab]

[tab name=’Multicore’]  System Software for Heterogeneous Multicore Platforms

Heterogeneous multicore systems have become the trend for the embedded market due to its advantage of power/performance over traditional designs and are widely accepted for high performance multimedia embedded systems. In 2008, we started a project on developing system software for heterogeneous multicore platforms. Hence, the applications on such platform can take advantage of the heterogeneous multicore to meet their performance requirement including throughput, energy constraints, and timing constraints.

One example application is to process stream data with high throughput. Although pipeline techniques can enhance performance for the multi-core platforms, data dependencies for process- ing compressed multimedia data makes it difficult, if not impossible, to automate pipelined design. In this work, we targeted on multimedia streaming applications on heterogeneous multi-core platforms and develop the Tile Piecing Algorithm for pipelined schedule synthesis within the targeted applications and platforms. The algorithm gives an efficient way to construct a pipelined schedule. The performance evaluation result shows that the algorithm performs as well as the optimal algo- rithm to utilize the computation resource. On the other hand, the algorithm only takes hundreds of milliseconds to complete, which is less than one tenth of the running time for optimal algorithm. Last, the synthesized schedule is well packed. The short execution time and schedule make-span makes the algorithm more practical to be used during the run-time. Parts of this work was published on Congerence for Design, Automation, and Test in Europe (DATE) 2011 [12].

Another example system software is the performance monitoring tool. However, monitoring the workload, scheduling the tasks, and managing the energy consumption to enable energy-efficient, real-time applications are increasingly challenging on such systems as both the applications and systems become complex. In this work, we introduce a comprehensive approach to address the key problems and accelerate the design of a heterogeneous multicore embedded system by providing a suite of energy-aware system software with tightly coupled real-time support and perfor- mance/power modeling facilities. We start with a rapid full system modeling/simulation framework to characterize the application workload, design energy-saving algorithms, and verify if performance requirements are met by hardware specifications during the early design stage.

With special considerations on today’s multicore embedded systems, we developed several key components and integrated them as a system software suite: a portable, efficient library to support inter-core communications and multicore programming, a lightweight kernel for dynamically mon- itoring and sharing the workload among the processor cores, and a dynamic voltage and frequency scaling scheme to adjust the setting of the processors to save energy. The system software has been implemented on the PAC Duo system as a case study, with experimental results to demonstrate the effectiveness of the proposed approach. This work discusses the novel techniques included in this system software and shares the lessons that we have learned from this work. Parts of this work were published on the 2011 Research in Applied Computation Symposium (RACS 2011) [13], which won the Best Paper Award, and the eighth IEEE/ACM/IFIP international conference on Hardware/software codesign and system synthesis [14].

Parts of our results were published on Journal of Real-Time Systems [15], and Journal of Signal Processing Systems [16], Congerence for Design, Automation, and Test in Europe (DATE) 2011 [12], 2010 22nd Euromicro Conference on RealTime Systems [17], the 2011 Research in Applied Computation Symposium (RACS 2011) [13], 17th Asia and South Pacific Design Automation Con- ference [18], and the eighth IEEE/ACM/IFIP international conference on Hardware/software code- sign and system synthesis [14], the 2012 Research in Applied Computation Symposium (RACS 2012)[19], and the 28th Symposium On Applied Computing (SAC 2013) [20].

[/tab]

[tab name=’Workflow’] Workflow-Based Framework for User-Centric Cyber-Physical Systems and Services

The research focus of this project was on a framework as an architectural foundation for flexible, safe- and-sound 21st century cyber-physical systems and services (CPS). The proposed middleware pro- totype made effective use of the results of our research on CPS workflow management and open real-time systems abstractions and embody the results in a ready for use form. The novel middle- ware is called Distributed, Real-Time Workflow Framework (DiReWF). By providing a flexible, workflow-based framework for integration of cyber-physical system and application components, together with tools for defining the components and their integration, DiReWF made the try-and- true workflow approach that has been widely used for business process automation applicable for automation of CPS processes. Thus, it can help to reduce the levels of expertise and efforts required to design, implement and maintain flexible 21-century services in general, automation and assistive services in particular. By incorporating effective algorithms and mechanisms for end-to-end re- source and quality of service management in open environments, it supports appropriate real-time systems abstractions needed by time critical services. By providing extensible libraries of cyber-physical system and applications components, device models, service models, user models and user behavior models, DiReWF is able to support simulation and evaluation of a wide spectrum of 21st century cyber-physical services and use scenarios.

Parts of research results were published in 2011 IEEE International Conference on Technolo- gies for Homeland Security (HST) [21], 2011 IEEE International Conference on Service-Oriented Computing and Applications (SOCA)[22], IEEE ICC2012 Workshop on Re-think ICT infrastruc- ture designs and operations[23], the 15th International Symposium on Wireless Personal Multime- dia Communication[19], and IEEE Computer Magazine[24].

[/tab]

[tab name=’WuKong’] Self-X Middleware for machine-to-machine networks

Many existing wireless sensor network (WSN) research projects have focused on low-level algorithms such as routing, MAC layers, and data aggregation. At a higher level, a significant number of single-purpose WSN applications have been developed and deployed. In between, however, the gap between the low level HW/network support and the mission of high-level applications, has received significantly less study. Most WSN implementation projects show that building a complete, working WSN is still very hard, not to mention making them dynamically adaptable or capable of evolving with new missions, new sensors, and/or new target environments. Except for the low level building blocks, there is very little software reuse from one WSN to another WSN.

WSNs have historically been built with a strong coupling among applications and the underly- ing network infrastructure. Many WSN applications are built directly on top of the hardware or on some minimum operating system, such as TinyOS, which is very hard to work with. This results in applications being programmed from the individual node’s perspective, telling a node what to do, rather than allowing the application to express globally what it really wants from the sensor network. Furthermore, since most WSN applications are specifically designed to particular scenar- ios and unique target environments, most behavior is hardcoded, resulting in rigid networks that are typically not very flexible at adjusting their behavior to faults or changing external conditions. A more high level vision on how large-scale machine-to-machine (M2M) or networks of sensors should be programmed, deployed, and configured is still missing.

Indeed, we are far from conducting Rapid Application Development (RAD) for M2M. This project, from 2011 to 2013, aims to fill the gap, by developing a flexible and self-organizing mid- dleware support for M2M deployment and management in the envisioned ubiquitous M2M of the near future. The middleware will pursue intelligent capabilities to detect, identify, configure, de- ploy, and if necessary, repair, reload and redeploy an M2M application. The intelligent capabili- ties have similar goals to autonomic computing, including Self-Configuration, Self-Healing, Self- Optimization, and Self-Protection. But our research project will be specifically for M2M where much of computing, network, energy and memory resources may be under severe constraints. We design the middleware architecture as configurable modules so that different subsets of the ’self-X’ capabilities may be selected and embedded in a WSN middleware instance for a specific sensor node, in order to best meet the needs of the node itself and the M2M application. The grand vi- sion for our research is that future M2M should have ”zero-cost” deployment where users of an M2M application do not need to be concerned on how and where to deploy sensors. The built-in intelligence from the proposed M2M support can automatically perform the optimal sensor node configuration, bandwidth allocation, fault management, and re-configuration in response to new missions and new device deployment. Much like the past transition from low-level assembly codes to high-level programming using general purpose OS and compiler support, M2M programming may be as platform-independent as possible while keep only the most essential system primitives to allow automatic performance optimization.

The goal of our research is to build flexible middleware support so that developers and users of an M2M system do not need to be constrained by which and how sensors have been deployed in a target environment. The built-in intelligence from the middleware can dynamically perform sensor detection, device configuration, bandwidth allocation, software upgrade, and system re- configuration. Like the transition from low-level coding to high-level programming with the sup- port of a general purpose OS and a optimising compiler, we would like to make M2M programming as platform-independent as possible using simple, high-level primitives instead of the traditional node-centric programming. To achieve our goals for flexible M2M management, we define three orthogonal frameworks:

  • Sensor profile framework: to enable the handling of heterogeneous sensor nodes, and for high-level, logical abstraction of sensor operations.
  • User policy framework: to allow user-friendly specification of application execution objec- tives, and context-dependent management of system performance.
  • System progression framework: to facilitate in-situ software upgrade for dynamically, pro- gressive reconfiguration.

The part of our middleware running on the nodes, called NanoKong, will provide platform independent access at two different levels. First, the profile framework allows the resources, including sensors and software functions, in the network to be discovered by the Master and to communicate with each other through a well defined protocol where the underlying implementation is hidden from the client. Second, NanoKong includes a small Java virtual machine, which will allow us to add application specific behaviour to the functionality already present on the device. Parts of our results are published in the workshop of Large Scale Cyber-Physical Systems (LCPS) 2011 [22], and 2nd International Conference on Sensor Networks [25].

[/tab]

[tab name=’Papers’] Parts of Publications from 2007 to 2012.

  1. P. Tsai, H. Yeh, C. Yu, P. Hsiu, C. Shih, and J. Liu, “Compliance Enforcement of Temporal and Dosage Con- straints,” English, in 2006 27th IEEE International Real-Time Systems Symposium (RTSS’06), IEEE, Dec. 2006, pp. 359–368, isbn: 0-7695-2761-2. doi: 10.1109/RTSS.2006.14. [Online]. Available: http: //ieeexplore.ieee.org/xpls/abs%5C_all.jsp?arnumber=4032363’%20escapeXml= ‘false’/%3E.
  2. H.-C. Yeh, P.-C. Hsiu, C.-S. Shih, P.-H. Tsai, and J. W. S. Liu, “APAMAT: A Prescription Algebra for Medi- cation Authoring Tool,” in 2006 IEEE International Conference on Systems Man and Cybernetics, Ieee, 2006, pp. 4284–4291, isbn: 1424400996. doi: 10.1109/ICSMC.2006.384807. [Online]. Available: http: //ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=4274572.
  3. C. F. Hsu, H. Y. M. Liao, P. C. Hsiu, Y. S. Lin, C. S. Shih, T. W. Kuo, and J. W. S. Liu, “Smart Pantries for Homes,” English, in 2006 IEEE International Conference on Systems, Man and Cybernetics, vol. 5, IEEE, Oct. 2006, pp. 4276–4283, isbn: 1-4244-0099-6. doi: 10.1109/ICSMC.2006.384806. [Online]. Avail- able: http://ieeexplore.ieee.org/xpls/abs%5C_all.jsp?arnumber=4274571′ %20escapeXml=’false’/%3E.
  4. H.-C. Yeh, C.-S. Shih, and J. W.-S. Liu, “Integration framework for medication-use process,” English, in 2007 IEEE International Conference on Systems, Man and Cybernetics, IEEE, 2007, pp. 3676–3681, isbn: 978-1- 4244-0990-7. doi: 10.1109/ICSMC.2007.4414158. [Online]. Available: http://ieeexplore. ieee.org/xpls/abs%5C_all.jsp?arnumber=4414158’%20escapeXml=’false’/%3E.
  5. W.-H. Chang, C.-S. Shih, and J. Liu, “Component interface design for flexible user-centric automation and assistive devices,” English, in 2008 IEEE International Conference on Systems, Man and Cybernetics, IEEE, Oct. 2008, pp. 2276–2284, isbn: 978-1-4244-2383-5. doi: 10.1109/ICSMC.2008.4811632.
  6. T. Chou, S. Chang, Y. Lu, Y. Wang, M. Ouyang, C. Shih, T. Kuo, J. S. Hu, and J. Liu, “EMWF for Flexible Automation and Assistive Devices,” English, in 2009 15th IEEE Real-Time and Embedded Technology and Applications Symposium, IEEE, Apr. 2009, pp. 243–252, isbn: 978-0-7695-3636-1. doi: 10.1109/RTAS. 2009.21. [Online]. Available: http://ieeexplore.ieee.org/xpls/abs%5C_all.jsp? arnumber=4840585’%20escapeXml=’false’/%3E.
  7. P. H. Tsai, Y. T. Chuang, T. S. Chou, J. W. S. Liu, and C. S. Shih, “iNuC: An Intelligent Mobile Nursing Cart,” English, in 2009 2nd International Conference on Biomedical Engineering and Informatics, IEEE, 2009, pp. 1–6, isbn: 978-1-4244-4132-7. doi: 10.1109/BMEI.2009.5305225. [Online]. Available: http: //ieeexplore.ieee.org/xpls/abs%5C_all.jsp?arnumber=5305225’%20escapeXml= ‘false’/%3E.
  8. T. Y. Chen, P.-H. Tsai, T. S. Chou, C.-S. Shih, T.-W. Kuo, J. W. S. Liu, and A. Thamizhmani, “Component Model and Architecture of Smart Devices for Elderly,” in Seventh Working IEEE IFIP Conference on Software Architecture WICSA 2008, Ieee, 2008, pp. 51–60, isbn: 9780769530925. doi: 10.1109/WICSA.2008. 11. [Online]. Available: http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm? arnumber=4459143.
  9. P. H. Tsai, C. Y. Yu, M. Y. Wang, J. K. Zao, H. C. Yeh, C. S. Shih, and J. W. S. Liu, “iMAT: Intelligent medication administration tools,” English, in The 12th IEEE International Conference on e-Health Network- ing, Applications and Services, IEEE, Jul. 2010, pp. 308–315, isbn: 978-1-4244-6374-9. doi: 10.1109/ HEALTH.2010.5556551. [Online]. Available: http://ieeexplore.ieee.org/xpls/abs%5C_ all.jsp?arnumber=5556551’%20escapeXml=’false’/%3E.
  10. P.-H. Tsai, T.-Y. Chen, C.-R. Yu, C.-S. Shih, and J. W. S. Liu, “Smart Medication Dispenser: Design, Architec- ture and Implementation,” English, IEEE Systems Journal, vol. 5, no. 1, pp. 99–110, Mar. 2011, issn: 1932- 8184. doi: 10.1109/JSYST.2010.2070970. [Online]. Available: http://ieeexplore.ieee. org/xpls/abs%5C_all.jsp?arnumber=5585838’%20escapeXml=’false’/%3E. 6
  11. P.-H. Tsai, J. W. S. Liu, and C.-S. Shih, “Algorithms for Scheduling Interactive Medications,” Foundations of Computing and Decision Science, vol. 34, no. 4, pp. 307–331, 2009. [Online]. Available: http://baztech. icm.edu.pl/baztech/cgi-bin/btgetdoc.cgi?BPP2-0014-0055.
  12. Y.-S. Chiu, C.-S. Shih, and S.-H. Hung, “Pipeline Schedule Synthesis for Real-Time Streaming Tasks with Inter/Intra-instance Precedence,” in Congerence for Design, Automation, and Test in Europe (DATE), 2011, pp. 1–6. [Online]. Available: http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber= 05763212.
  13. S.-H. Hung, P.-H. Chiu, and C.-S. Shih, “Building a Scalable and Portable Message-Passing Library for Em- bedded Multicore Systems,” in The 2011 Research in Applied Computation Symposium (RACS 2011), 2011.
  14. S.-H. Hung, C.-S. Shih, T.-W. Kuo, C.-H. Tu, and C.-W. Chang, “A real-time, energy-efficient system software suite for heterogeneous multicore platforms,” in Proceedings of the eighth IEEE/ACM/IFIP international con- ference on Hardware/software codesign and system synthesis, ser. CODES+ISSS ’12, ACM, 2012, pp. 23–32. doi: 10.1145/2380445.2380456.
  15. Y.-S. Chen, C.-S. Shih, and T.-W. Kuo, “Processing element allocation and dynamic scheduling codesign for multi-function SoCs,” Real-Time Systems, vol. 44, no. 1-3, pp. 72–104, 2010. doi: 10.1007/s11241-009- 9090-9. [Online]. Available: http://www.springerlink.com/index/3434K78766384623. pdf.
  16. Y. Y.-H. Lee, J.-J. Chen, and C.-S. Shih, “Energy-Efficient Considerations on a Variable-Bitrate PCI-Express Device,” Journal of Signal Processing Systems, vol. 59, no. 1, pp. 57–69, 2008, issn: 19398018. doi: 10. 1007/s11265-008-0280-9. [Online]. Available: http://www.springerlink.com/index/ L663160806R005Q2.pdf%20http://www.springerlink.com/index/10.1007/s11265- 008-0280-9.
  17. Y.-C. Lin, C.-Y. Yang, C.-W. Chang, Y.-H. Chang, T.-W. Kuo, and C.-S. Shih, “Energy-Efficient Mapping Technique for Virtual Cores,” in 2010 22nd Euromicro Conference on RealTime Systems, IEEE, 2010, pp. 66–75, isbn: 9781424475469. doi: 10.1109/ECRTS.2010.22. [Online]. Available: http://ieeexplore. ieee.org/lpdocs/epic03/wrapper.htm?arnumber=5562900.
  18. S.-H. Hung, T.-W. Kuo, C.-S. Shih, and C.-H. Tu, “System-wide profiling and optimization with virtual ma- chines,” English, in 17th Asia and South Pacific Design Automation Conference, IEEE, Jan. 2012, pp. 395– 400, isbn: 978-1-4673-0772-7. doi: 10.1109/ASPDAC.2012.6164980. [Online]. Available: http: //ieeexplore.ieee.org/articleDetails.jsp?arnumber=6164980%5C&contentType= Conference+Publications.
  19. C.-S. Shih, J.-W. Wei, S.-H. Hung, N. Chang, and J. Chen, “A VM-aware Fairness Scheduler on Heterogonous Multi-Core Platforms,” in The 2012 Research in Applied Computation Symposium (RACS 2012), 2012, pp. 409– 418.
  20. C.-S. Shih and H.-Y. Lai, “nμKernel: MicroKernel for multi-core DSP SoCs with load sharing and priority interrupts,” in The 28th Symposium On Applied Computing (SAC 2013), 2013.
  21. L.-J. Chen, C.-W. Li, Y.-T. Huang, and C.-S. Shih, “A rapid method for detecting geographically disconnected areas after disasters,” in 2011 IEEE International Conference on Technologies for Homeland Security (HST), IEEE, Nov. 2011, pp. 501–506, isbn: 978-1-4577-1376-7. doi: 10.1109/THS.2011.6107919. [Online]. Available: http://ieeexplore.ieee.org/articleDetails.jsp?arnumber=6107919%5C& contentType=Conference+Publications.
  22. N. Reijers, Y.-C. Wang, C.-S. Shih, J. Y. Hsu, and K.-J. Lin, “Building intelligent middleware for large scale CPS systems,” in 2011 IEEE International Conference on Service-Oriented Computing and Applications (SOCA), IEEE, Dec. 2011, pp. 1–4, isbn: 978-1-4673-0319-4. doi: 10.1109/SOCA.2011.6166238. [Online]. Available: http://ieeexplore.ieee.org/articleDetails.jsp?arnumber=6166238%5C& contentType=Conference+Publications.
  23. C.-S. Shih, L.-J. Chen, K. C.-J. Lin, and W.-H. Chung, “Open Information Gateway for Disaster Management,” in IEEE ICC2012 Workshop on Re-think ICT infrastructure designs and operations, 2012.
  24. J. Liu, C.-S. Shih, and E. Chu, “Cyber-physical elements of disaster prepared smart environment,” IEEE Com- puter Magazine, Feb. 2013.
  25. N. Reijers, K.-J. Lin, Y.-C. Wang, C.-S. Shih, and J. Y. Hsu, “Design of an Intelligent Middleware for Flexible Sensor Configuration in M2M Systems,” in the 2nd International Conference on Sensor Networks (SENSOR- NETS 2013), IEEE, Dec. 2013, pp. 1–6. 7

[/tab]

 

[end_tabset]

Advertisements