Search

This paper illustrates the application of Adaptive Neuro-Fuzzy Inference System (ANFIS) to model Jordan transport energy demand. The ANFIS model has been developed using socio-economic and transport related indicators based on annual number of vehicles, vehicle owner level, income level, and fuel prices in Jordan. The model has been validated using testing data and has showed very accurate results of 97%. It is expected that the results of this study will be helpful in developing highly applicable and productive planning for future transport energy policies. [ABSTRACT FROM AUTHOR]

The main purpose of this paper is to introduce a complete design of a novel system for adaptive intelligent learning system (SAIL), and to innovate on both technical and conceptual fronts by addressing relevant barriers. This research was focused on actualizing a human centered approach through the guidance of experts in the learning and psychological fields. System intelligence was sought through the utilization of automated machine learning technologies to classify learners as well as through information processing at a semantic level. Adaptively was achieved through the constant monitoring of learners' behavior and psychophysiological status, feedback and performance to draw actionable conclusions for both the learners and the system itself. SAIL uses intelligent and interactive technologies in processing individual learner perceptions, preferences and cognitive profiles. In addition, it focuses on a highly configurable architecture to provide a system that can be used in varying training scenarios, so as to produce a tailor-made learning experience, suiting both the needs of the individual learners and the goals of the organizations, thus, improving the professional training process outcomes. Evaluation of both content and the learning system itself were conducted in a sound and statistically relevant way, under the supervision of learning and cognitive experts. SAIL industrial "added value" are quantified and measured, as the industry needs to see a clear connection between competence gaining of employees, business goals, resources and organizational performance. Emphasis is also given on producing fully-reusable system architecture for varying training purposes in the future. [ABSTRACT FROM AUTHOR]

The aim of this study was to employ whey proteins isolate (WPI) and carboxymethylcelulose (CMC) as stabilizers in beverage production and to evaluate viscosity of the products. Three beverages were formulated using 6% WPI combined with three different concentrations of CMC (0.1, 0.5, and 1%). The combination of 6% WPI/1.0% CMC was selected and added to three different ratios of pure orange juice (50:50 "T1," 40:60 "T2," and 15:85 "T3"). The apparent viscosity decreased as shear rate and temperature increased. Additionally, the apparent viscosity for the same treatment at certain shear rate/same temperature increased after storage. In addition, an adaptive neuro-fuzzy inference system (ANFIS) was used to model and identify the viscosity of the resulted beverages. Experimental validation runs were conducted to compare the measured values and the predicted ones. ANFIS models achieved an average prediction error of viscosity of only 9%. It is believed that this approach can be applied to predict many other parameters and properties in beverage industry. [ABSTRACT FROM AUTHOR]

Abrasive surface finishing processes are complex, highly non-linear and time variable systems that can have many variables affecting the desired surface roughness. In this study, an adaptive neuro-fuzzy inference system (ANFIS) was used to identify the surface roughness after the edge grinding process. The specific application involves the grinding of the edges of steel blanks with a pneumatic gantry robot. Two grinding parameters that have a major impact on the surface roughness, including grinding force and feed rate, were analyzed. The design of experiment (DOE) and analysis of variance (ANOVA) were applied to screen and validate the experimental data points. The predicted surface roughness values derived by ANFIS were compared with the experimental data for validation purposes. The comparison indicates that the adoption of (Pi) fuzzy membership function in ANFIS achieved a very satisfactory accuracy of 96%. [ABSTRACT FROM AUTHOR]

An on-line monitoring and prediction of surface roughness in grinding is introduced with experimental verification. An adaptive neuro-fuzzy inference system (ANFIS) is used to monitor and identify the surface roughness online. The system uses a piezoelectric accelerometer to generate a signal related to grinding features and surface finish. The power spectral density (PSD) of this signal is used as an input to ANFIS, which in turn outputs a value for the on-line predicted surface roughness. Different neuro-fuzzy parameters were adopted during the training process of ANFIS in order to improve the on-line monitoring and prediction accuracy of surface roughness. Experimental validation runs were conducted to compare the measured surface roughness values with the online-predicted ones. The comparison shows that the adoption of Bell-shaped membership function in ANFIS achieved a very satisfactory on-line prediction accuracy of 91%. [ABSTRACT FROM AUTHOR]