Explore chapters and articles related to this topic
Unsupervised Brain Tumor Segmentation Using Knowledge-Based Fuzzy Techniques
Published in Horia-Nicolai Teodorescu, Abraham Kandel, Lakhmi C. Jain, FUZZY and NEURO-FUZZY SYSTEMS in MEDICINE, 2017
Matthew C. Clark, Lawrence O. Hall, Dimitry B. Goldgof, Robert Velthuizen, Reed Murtagh, Martin S. Silbiger
The slices processed here were first determined to contain enhancing pathology during “pre-processing” (pathology detection) in [6], [8]. Knowledge gained during pre-processing allows removal of extra-cranial tissues (air, skin, fat, etc.) from a segmentation created by a fuzzy c-means clustering algorithm [5], [23]. The remaining pixels (really voxels, since they have thickness) form an intra-cranial mask. An expert system uses information from multi-spectral, local statistical analysis and fuzzy edge-detection to iteratively segment the enhancing tumor from the intra-cranial mask. A rule-based expert system shell, CLIPS [20], [46] is used to organize the system. Low level modules for image processing and high level modules for image analysis are all written in the C language and called as actions from the right-hand sides of the rules.
From natural language text to rules: knowledge acquisition from formal documents for aircraft assembly
Published in Journal of Engineering Design, 2019
N. Madhusudanan, Balan Gurumoorthy, Amaresh Chakrabarti
It was desirable to perform validation of the entire knowledge acquisition pipeline with the smart manufacturing system shown in Figure 1. The purpose of the knowledge acquisition system is to enable the smart manufacturing system to reuse expert knowledge along with data from sensors embedded in the manufacturing system. This combination, it is hoped, will lead to informed decision making. Hence, validation of the knowledge base, strictly speaking, is not possible until the implementation of the entire smart manufacturing system. Thus, the rule-writing component was validated manually by the researchers themselves, and not with subjects. For this, the syntax and correctness of parameters of rules, as used by the CLIPS expert system, was verified. Also, the syntax of CLIPS rules were directly mapped to the relations/parameters identified in the cause dissection component. Thus, component (3) mentioned in Section 3 is tightly linked to rule writing – component (4). Due to these reasons, though the knowledge acquisition method was implemented till component (4), its validation was performed only until component 2: of extraction of causes-issues. This is because the extent to which the relations and parameters are correctly identified were able to be seen only in the rules that are ultimately run.
Backward chaining inference as a database stored procedure – the experiments on real-world knowledge bases
Published in Journal of Information and Telecommunication, 2018
Tomasz Xie¸ski, Roman Simiński
Knowledge-based systems are still popular and practically used tools for solving ill-structured problems. Rules are among the most popular forms of representing knowledge in the field of intelligent information systems, regardless of the development of different knowledge representations. Forward and backward chaining inference algorithms are also popular in the real-world applications (Akerkar & Sajja, 2010). The number of applications which utilize rule bases and methods of inference grows, but unfortunately the number of tools for building knowledge-based systems increases much more slowly (Sajja & Akerkar, 2010). The well-known systems, such as JESS (2016), CLIPS (2016), DROOLS (2016) or EXSYS (2016), are usually described as the tools for implementing domain knowledge-based systems. What is more, commercial expert system development tools have been extended to offer web-based development capabilities.
Shake-Table Seismic Performance Evaluation of Direct- and Indirect-Hung Suspended Ceiling Systems
Published in Journal of Earthquake Engineering, 2022
Su-Chan Jun, Cheol-Ho Lee, Chang-Jun Bae, Kyung-Joo Lee
In Korea, as well as in other countries, several types of suspended ceiling systems are commonly used apart from the direct-hung suspended ceiling system. The major differences lie in the hanger members and the details of the connection of the ceiling grids to the floor above. Figure 3b shows one of such suspended ceiling systems. In this system, the main T-beams in the ceiling grids are attached to additional C-section members, often called a carrying channel, using C/T clips. Instead of hanger wires, hanger bolts are used to connect the grid system to the floor slab. Because the entire ceiling grid is hung through the carrying channel, it is also classified as an indirect-hung suspended ceiling system.