Masoud Yazdani

Bio: Masoud Yazdani is an academic researcher. The author has contributed to research in topics: Artificial general intelligence & Symbolic artificial intelligence. The author has an hindex of 1, co-authored 1 publications receiving 59 citations.

Artificial Intelligence: Principles and Applications

Abstract: Part 1. Principles of artificial intelligence, John Campbell. Part 2 Tools and techniques: artificial intelligence programming environments and the POPLOG system, John Gibson LISP, lists and pattern-matching, Tony Hasemer. Part 3 Applications: computer processing of natural languages, Alan Ramsay levels of representation in computer speech synthesis and recognition, Stephen Isard computer vision, David Hogg artificial intelligence and robotics, Michael Brady the anatomy of expert systems, Richard Forsyth. Part 4 Frontiers: machine learning, Richard Forsyth memory models of man and machine, Ajit Narayanan. Part 5 Implications: why artificial intelligence needs an empirical foundation, Noel E Sharkey and Gordan D A Brown breaking out of the chinese room, Steve Torrance social implications of artificial intelligence, Derek Partridge.

Artificial Intelligence and Administrative Discretion: Implications for Public Administration

Abstract: Advances in the field of artificial intelligence (AI) are leading to a new level of computing in which systems will have the capability to act as autonomous agents and learn to learn independently,...

Investigation of Seam Pucker in Lightweight Synthetic Fabrics as an Aesthetic Property Part I: A Cognitive Model for the Measurement of Seam Pucker

Abstract: Seam pucker is an area which is now receiving particular attention especially with the development of microfibre fabrics which are inherently prone to deformations during garment manufacture. Although fabric properties can be related to seam pucker, the aesthetic judgement is still left to subjective assessment which is based upon ranking the stitched fabric samples by judges having compared them with photographic ‘standards’. The shortcomings of this procedure are obvious; judges do not always agree, they need to be trained, the procedure is time consuming and non standardised. This paper reports upon the development of a new measuring procedure which is based on the use of a computer and a camera, ie computer ‘vision’. This procedure is objective and is focused on the aesthetic property of the seam assembly, by ‘modelling’ the cognitive process involved in seam pucker assessment The results are organised in two parts: Part I reports on the development of a cognitive ‘model’ for the measurement of seam p...

An improved genetic algorithm for optimal feature subset selection from multi-character feature set

Abstract: This paper presents an improved genetic algorithm (IGA) by which the optimal feature subset can be selected effectively and efficiently from a multi-character feature set (MCFS). IGA adopts segmented chromosome management scheme to implement local management of chromosome. This scheme encodes a solution with an entire binary chromosome; but logically, it divides the chromosome into several segments according to the number of feature groups in MCFS for local management. A segmented crossover operator and a segmented mutation operator are employed to operate on these segments to avoid invalid chromosomes. The probability of crossover and mutation are adjusted dynamically according to the generation number and the fitness value. As a result, IGA obtains strong searching ability at the beginning of the evolution and achieves accelerated convergence along the evolution. IGA is tested using features extracted from cotton foreign fiber objects, and compared with the Simple Genetic Algorithm (SGA) under the same condition. The results show that IGA receives improved searching ability and convergence speed compared with SGA. The optimal feature subset selected by the IGA has much smaller size than that of the SGA. This is very important for the online classification of foreign fibers.