Action Selection Under Uncertainty and Risk Involving High Consequence Rare Events

Author(s):  
Galina L. Rogova ◽  
Roman Ilin
Keyword(s):  
2020 ◽  
Vol 39 (6) ◽  
pp. 8463-8475
Author(s):  
Palanivel Srinivasan ◽  
Manivannan Doraipandian

Rare event detections are performed using spatial domain and frequency domain-based procedures. Omnipresent surveillance camera footages are increasing exponentially due course the time. Monitoring all the events manually is an insignificant and more time-consuming process. Therefore, an automated rare event detection contrivance is required to make this process manageable. In this work, a Context-Free Grammar (CFG) is developed for detecting rare events from a video stream and Artificial Neural Network (ANN) is used to train CFG. A set of dedicated algorithms are used to perform frame split process, edge detection, background subtraction and convert the processed data into CFG. The developed CFG is converted into nodes and edges to form a graph. The graph is given to the input layer of an ANN to classify normal and rare event classes. Graph derived from CFG using input video stream is used to train ANN Further the performance of developed Artificial Neural Network Based Context-Free Grammar – Rare Event Detection (ACFG-RED) is compared with other existing techniques and performance metrics such as accuracy, precision, sensitivity, recall, average processing time and average processing power are used for performance estimation and analyzed. Better performance metrics values have been observed for the ANN-CFG model compared with other techniques. The developed model will provide a better solution in detecting rare events using video streams.


Author(s):  
Lidia K Simanjuntak ◽  
Tessa Y M Sihite ◽  
Mesran Mesran ◽  
Nuning Kurniasih ◽  
Yuhandri Yuhandri

All colleges each year organize the selection of new admissions. Acceptance of prospective students in universities as education providers is done by selecting prospective students based on achievement in school and college entrance selection. To select the best student candidates based on predetermined criteria, then use Multi-Criteria Decision Making (MCDM) or commonly called decision support system. One method in MCDM is the Elimination Et Choix Traduisant la Reality (ELECTRE). The ELECTRE method is the best method of action selection. The ELECTRE method to obtain the best alternative by eliminating alternative that do not fit the criteria and can be applied to the decision SNMPTN invitation path.


Author(s):  
Bernhard Hommel

AbstractCommonsense and theorizing about action control agree in assuming that human behavior is (mainly) driven by goals, but no mechanistic theory of what goals are, where they come from, and how they impact action selection is available. Here I develop such a theory that is based on the assumption that GOALs guide Intentional Actions THrough criteria (GOALIATH). The theory is intended to be minimalist and parsimonious with respect to its assumptions, as transparent and mechanistic as possible, and it is based on representational assumptions provided by the Theory of Event Coding (TEC). It holds that goal-directed behavior is guided by selection criteria that activate and create competition between event files that contain action-effect codes matching one or more of the criteria—a competition that eventually settles into a solution favoring the best-matching event file. The criteria are associated with various sources, including biological drives, acquired needs (e.g., of achievement, power, or affiliation), and short-term, sometimes arbitrary, instructed aims. Action selection is, thus, a compromise that tries to satisfy various criteria related to different driving forces, which are also likely to vary in strength over time. Hence, what looks like goal-directed action emerges from, and represents an attempt to satisfy multiple constraints with different origins, purposes, operational characteristics, and timescales—which among other things does not guarantee a high degree of coherence or rationality of the eventual outcome. GOALIATH calls for a radical break with conventional theorizing about the control of goal-directed behavior, as it among other things questions existing cognitive-control theories and dual-route models of action control.


ACS Omega ◽  
2020 ◽  
Vol 5 (49) ◽  
pp. 31608-31623
Author(s):  
Samuel D. Lotz ◽  
Alex Dickson

Sign in / Sign up

Export Citation Format

Share Document