A new feature selection from lidar data and digital aerial images acquired for an urban/c environment using an ANFIS-based classification and a fuzzy rough set method

In this article, a new fuzzy rough set (FRS) method was proposed for extracting rules from an adaptive neuro-fuzzy inference system (ANFIS)-based classification procedure in order to select the optimum features. The proposed methodology was used to classify lidar data and digital aerial images acquired for an urban environment to detect four classes, including trees, buildings, roads, and natural grounds. In this regard, 16 potentially primary features were produced for classification using the lidar data and the digital aerial images. The training and checking inputs of the proposed ANFIS were collected from the generated features for further training and evaluation processes. Also, the fuzzy c-mean clustering algorithm was used to initialize the fuzzy inference system of the proposed ANFIS-based classification method. By considering all states of fuzzy rules for each training input, the fuzzy rule with the maximum firing value was selected. Accordingly, these fuzzy rules were used as the inputs of the Rough Set Theory. Accordingly, the optimum features were acquired by the basic minimal covering algorithm as the rule induction method. To validate our proposed methodology, the procedure of classification was repeated by the achieved optimum features. The results showed that the classification using the optimum features has reached better overall accuracy than those achieved by using the 16 potentially primary features. Also, comparing the results of our proposed methodology with the other well-known genetic-algorithm-based feature selection methods indicated the significance of the proposed FRS method to select optimum features with high accuracy in a short running time.     

Coupled eagle strategy and differential evolution for unconstrained and constrained global optimization

The performance of an optimization tool is largely determined by the efficiency of the search algorithm used in the process. The fundamental nature of a search algorithm will essentially determine its search efficiency and thus the types of problems it can solve. Modern metaheuristic algorithms are generally more suitable for global optimization. This paper carries out extensive global optimization of unconstrained and constrained problems using the recently developed eagle strategy by Yang and Deb in combination with the efficient differential evolution. After a detailed formulation and explanation of its implementation, the proposed algorithm is first verified using twenty unconstrained optimization problems or benchmarks. For the validation against constrained problems, this algorithm is subsequently applied to thirteen classical benchmarks and three benchmark engineering problems reported in the engineering literature. The performance of the proposed algorithm is further compared with various, state-of-the-art algorithms in the area. The optimal solutions obtained in this study are better than the best solutions obtained by the existing methods. The unique search features used in the proposed algorithm are analyzed, and their implications for future research are also discussed in detail.     

Computing with words for hierarchical competency based selection of personnel in construction companies

As part of human resource management policies and practices, construction firms need to define competency requirements for project staff, and recruit the necessary team for completion of project assignments. Traditionally, potential candidates are interviewed and the most qualified are selected. Applicable methodologies that could take various candidate competencies and inherent uncertainties of human evaluation into consideration and then pinpoint the most qualified person with a high degree of reliability would be beneficial. In the last decade, computing with words (CWW) has been the center of attention of many researchers for its intrinsic capability of dealing with linguistic, vague, interdependent, and imprecise information under uncertain environments. This paper presents a CWW approach, based on the specific architecture of Perceptual Computer (Per-C) and the Linguistic Weighted Average (LWA), for competency based selection of human resources in construction firms. First, human resources are classified into two types of main personnel: project manager and engineer. Then, a hierarchical criteria structure for competency based evaluation of each main personnel category is established upon the available literature and survey. Finally, the perceptual computer approach is utilized to develop a practical model for competency based selection of personnel in construction companies. We believe that the proposed approach provides a useful tool to handle personnel selection problem in a more reliable and intelligent manner.     

Comparison of multiwavelet, wavelet, Haralick, and shape features for microcalcification classification in mammograms

We present an evaluation and comparison of the performance of four different texture and shape feature extraction methods for classification of benign and malignant microcalcifications in mammograms. For 103 regions containing microcalcification clusters, texture and shape features were extracted using four approaches: conventional shape quantifiers; co-occurrence-based method of Haralick; wavelet transformations; and multi-wavelet transformations. For each set of features, most discriminating features and their optimal weights were found using real-valued and binary genetic algorithms (GA) utilizing a k-nearest-neighbor classifier and a malignancy criterion for generating ROC curves for measuring the performance. The best set of features generated areas under the ROC curve ranging from 0.84 to 0.89 when using real-valued GA and from 0.83 to 0.88 when using binary GA. The multi-wavelet method outperformed the other three methods, and the conventional shape features were superior to the wavelet and Haralick features.     

A new approach to investigate relationships between certain instrumentally measured appearance parameters and their visually perceived equivalents in the automotive industry

Appearance control has continuously been a major challenge to the automotive industry. In order to implement a consistent control on the appearance of automotive finishes, objective measurement of various appearance attributes such as gloss, distinctness of image, orange peel, etc., is indispensable to the automotive manufacturers. In the present study, attempts were made to find the correlation between visually perceived and instrumentally measured appearance of achromatic automotive finishes. To this end, three physical scales of appearance attributes, namely specular gloss, distinctness of image, and orange peel were prepared using a series of metallic black, metallic gray, metallic silver, and solid white automotive finishes. The samples were visually evaluated by a panel of 16 observers, by utilizing an also prepared lightness scale, in a light cabinet having a 45/0 illumination/observation geometry. The innovative use of a common lightness scale in the present study showed that there is a surprisingly good correlation between instrumentally measured specular gloss, distinctness of image, and Wave scan LW and Wd parameters, and the corresponding visually evaluated data at the four investigated achromatic levels.     

Scale-up studies for stable,long-term indoor and outdoor production of hydrogen by immobilized Rhodobacter capsulatus

Photofermentative hydrogen production by immobilized Rhodobacter capsulatus YO3 was carried out in a novel photobioreactor in sequential batch mode under indoor and outdoor conditions. Long-term H₂ production was realized in a 1.4 L photobioreactor for 64 days using Rhodobacter capsulatus YO3 immobilized with 4% (w/v) agar on 5 mM sucrose and 4 mM glutamate. The highest hydrogen yield (19 mol H₂/mol sucrose) and hydrogen productivity (0.73 mmol H₂ L^?1 h^?1) were achieved indoors on 5 mM sucrose. The effect of initial sucrose concentration (5 mM, 10 mM, and 20 mM) on hydrogen production was also investigated. Sustained hydrogen production was carried out under natural, outdoor conditions as well. For the outdoor experiments, the highest hydrogen productivity and yield were obtained as 0.87 ± 0.06 mmol H₂ L^?1 h^?1 and 6.1 ± 0.2 mol H₂/mol sucrose, respectively on 10 mM sucrose. Furthermore, this system prevented sudden pH drops and fluctuations caused by the utilization of sucrose throughout the process. These results demonstrate that a proper immobilization setup can lead to long-term efficient and robust hydrogen production even under naturally varying conditions.     

Model-driven development platform selection: four industry case studies

Software and Systems Modeling - Model-driven development platforms shift the focus of software development activity from coding to modeling for enterprises. A significant number of such platforms...     

Chaotic imperialist competitive algorithm for optimum design of truss structures

The imperialist competitive algorithm is a new socio-politically motivated optimization algorithm which recently is applied for structural problems. This paper utilizes the idea of using chaotic systems instead of random processes in the imperialist competitive algorithm. The resulting method is called chaotic imperialist competitive algorithm (CICA) in which chaotic maps are utilized to improve the movement step of the algorithm. Some well-studied truss structures are chosen to evaluate the efficiency of the new algorithm.