| 1. |
- Christalin, B., et al.
(författare)
-
Synthesis of reactive control protocols for switch electrical power systems for commercial application with safety specifications
- 2017
-
Ingår i: 2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016. - : IEEE. - 9781509042401
-
Konferensbidrag (refereegranskat)abstract
- This paper presents a method for the reactive synthesis of fault-tolerant optimal control protocols for a finite deterministic discrete event system subject to safety specifications. A Deterministic Finite State Machine (DFSM) and Behavior Tree (BT) were used to model the system. The synthesis procedure involves formulating the policy problem as a shortest path dynamic programming problem. The procedure evaluates all possible states when applied to the DFSM, or over all possible actions when applied to the BT. The resulting strategy minimizes the number of actions performed to meet operational objectives without violating safety conditions. The effectiveness of the procedure on DFSMs and BTs is demonstrated through three examples of switched electrical power systems for commercial application and analyzed using run-time complexity analysis. The results demonstrated that for large order system BTs provided a tractable model to synthesize an optimal control policy.
|
|
| 2. |
- Miloradovic, Branko, et al.
(författare)
-
A genetic planner for mission planning of cooperative agents in an underwater environment
- 2016
-
Ingår i: The 2016 IEEE Symposium Series on Computational Intelligence SSCI'16. - 9781509042401
-
Konferensbidrag (refereegranskat)abstract
- In this paper, a Genetic Algorithm (GA) is used for solving underwater mission planning problem. The proposed genetic planner is capable of utilizing multiple Autonomous Underwater Vehicles (AUVs) and Remotely Operated Vehicles (ROVs) in a mission plan, as well as running multiple tasks in parallel on the agent’s level. The problem is described using STRIPS modeling language. The proposed planner shows high robustness regarding initial population set, which is randomly generated. Chromosomes have variable length, consisting of active and inactive genes. Various genetic operators are used in order to improve convergence of the algorithm. Although genetic planner presented in this work is for underwater missions, this planning approach is universal, and it is not domain dependent. Results for a realistic case study with five AUVs and almost 30 tasks show that this approach can be used successfully for solving complex mission planning problems.
|
|
| 3. |
- Pham, Tuan D.
(författare)
-
Entropy rates of physiological aging on microscopy
- 2016
-
Ingår i: Proceedings of 2016 IEEE Symposium Series on Computational Intelligence. - : Institute of Electrical and Electronics Engineers (IEEE). - 9781509042401 - 9781509042418
-
Konferensbidrag (refereegranskat)abstract
- This paper presents a method for computing entropy rates of images by modeling a stationary Markov chain constructed from a weighted graph. The proposed method was applied to the quantification of the complex behavior of the growing rates of physiological aging of Caenorhabditis elegans (C. elegans) on microscopic images, which has been considered as one of the most challenging problems in the search for metrics that can be used for identifying differences among stages in high- throughput and high-content images of physiological aging.
|
|
| 4. |
- van Breda, Ward, et al.
(författare)
-
A feature representation learning method for temporal datasets
- 2016
-
Ingår i: PROCEEDINGS OF 2016 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (SSCI). - : IEEE. - 9781509042401
-
Konferensbidrag (refereegranskat)abstract
- Predictive modeling of future health states can greatly contribute to more effective health care. Healthcare professionals can for example act in a more proactive way or predictions can drive more automated ways of therapy. However, the task is very challenging. Future developments likely depend on observations in the (recent) past, but how can we capture this history in features to generate accurate predictive models? And what length of history should we consider? We propose a framework that is able to generate patient tailored features from observations of the recent history that maximize predictive performance. For a case study in the domain of depression we find that using this method new data representations can be generated that increase the predictive performance significantly.
|
|
