Classification and optimization of product review information using soft computing models

A soft computing framework to classify and optimize text-based information extracted from customers' product reviews is proposed in this paper. The soft computing framework performs classification and optimization in two stages. Given a set of keywords extracted from unstructured text-based product reviews, a Support Vector Machine (SVM) is used to classify the reviews into two categories (positive and negative reviews) in the first stage. An ensemble of evolutionary algorithms is deployed to perform optimization in the second stage. Specifically, the Modified micro Genetic Algorithm (MmGA) optimizer is applied to maximize classification accuracy and minimize the number of keywords used in classification. Two Amazon product reviews databases are employed to evaluate the effectiveness of the SVM classifier and the ensemble of MmGA optimizers in classification and optimization of product related keywords. The results are analyzed and compared with those published in the literature. The outputs potentially serve as a list of impression words that contains useful information from the customers' viewpoints. These impression words can be further leveraged for product design and improvement activities in accordance with the Kansei engineering methodology.

Optimization of process parameters for the production of naringinase by Aspergillus niger MTCC 1344

Aspergillus niger MTCC 1344 was used to produce extracellular naringinase in a complex (molasses, yeast extract and salts) medium. An initial medium pH 4.5 and cultivation temperature 30 °C were optimal for enzyme production. Among various carbon and organic nitrogen sources used, molasses and peptone were the most effective for enzyme yield. The rate of enzyme production was enhanced when metal ions were added to the medium. Fermentation conditions are described which produced a higher rate of enzyme synthesis. An increase in initial sugar concentration from 6 to 10 g l⁻¹ in the fermentation medium produced decreased naringinase synthesis while cell mass growth increased with the increase of sugar concentration. At a higher sugar level (10 g l⁻¹) the production of cell mass decreased.

Optimization of medium and process parameters for the production of inulinase from a newly isolated Kluyveromyces marxianus YS-1

A newly isolated strain of Kluyveromyces marxianus YS-1 was used for the production of extra cellular inulinase in a medium containing inulin, meat extract, CaCl₂ and sodium dodecyl sulphate (SDS). Fermentation medium pH 6.5, cultivation temperature 30 °C and 5% (v/v) inoculum of 12 h-old culture were optimal for enzyme production (30.8 IU/ml) with a fermentation time of 72 h at shake flask level. Raw inulin (2%, w/v) extracted from dahlia tubers by processing at 15 kg/cm² for 10 min was optimum for bioreactor studies. Maximum enzyme production (55.4 IU/ml) was obtained at an agitation rate of 200 rpm and aeration of 0.75 vvm in a stirred tank reactor with a fermentation time of 60 h.

Optimization of MLP parameters on mineral potential mapping tasks

Mineral potential mapping is the process of combining a set of input maps, each representing a distinct geo-scientific variable, to produce a single map which ranks areas according to their potential to host deposits of a particular type. The maps are combined using a mapping function which must be either provided by an expert (knowledge-driven approach), or induced from sample data (data-driven approach). Current data-driven approaches using multilayer perceptrons (MLPs) to represent the mapping function have several inherent problems: they rely heavily on subjective judgment in selecting training data and are highly sensitive to this selection; they do not utilize the contextual information provided by unlabeled data; and, there is no objective interpretation of the values output by the MLP. This paper presents a novel approach which overcomes these three problems.

Effect of manufacturing process on the final properties of advanced high strength steels for automotive applications

The performance of multiphase steels with high strength and improved toughness or ductility, such as intercritically annealed dual-phase (DP) and transformation-induced plasticity (TRIP) steels, is of key importance to the automotive industry. In this work we have considered the entire manufacturing process and the effects of this on the final product performance. These steels are formed to produce the required final shape and then the car is paint baked. In this work we also consider the effect of cold working and bake hardening on the fatigue life of the components.

Dynamic prediction models and optimization of polyacrylonitrile (PAN) stabilization processes for production of carbon fiber

Thermal stabilization process of polyacrylonitrile (PAN) is the slowest and the most energy-consuming step in carbon fiber production. As such, in industrial production of carbonfiber, this step is considered as amajor bottleneck in the whole process. Stabilization process parameters are usually many in number and highly constrained, leading to high uncertainty. The goal of this paper is to study and analyze the carbon fiber thermal stabilization process through presenting several effective dynamic models for the prediction of the process. The key point with using dynamic models is that using an evolutionary search technique, the heat of reaction can be optimized. The employed components of the study are Levenberg–Marquardt algorithm (LMA)-neural network (LMA-NN), Gauss–Newton (GN)-curve fitting, Taylor polynomial method, and a genetic algorithm. The results show that the procedure can effectively optimize a given PAN fiber heat of reaction based on determining the proper values of heating rampand temperature

Prediction of ductile failure in CP-Titanium as criterion of SPD process design

Application of damage model in combination with finite element analysis to design and optimization of equal channel angular pressing - conform of commercially pure titanium against ductile failure is demonstrated. The properties required for precise simulation of the process and prediction of damage accumulation (equivalent stress as function of equivalent strain and temperature and low bound ductility function) are obtained in the temperature interval 20-400 °C and described in details.

Organizing forms in change management: the role of structures, process and boundaries in a longitudinal case analysis

This paper examines change management at William Angliss Institute of Technical and Further Education (TAFE) against the three organizational dimensions of structures, processes and boundaries identified by the INNFORM Study. Its experience confirms that even when an organization adopts a systemic approach and implements change across each design dimension, optimal performance benefits depend on mutually reinforcing and complementary changes. Furthermore, improvement to processes, particularly communications and human resources practices, plays a pivotal role, as complementary change across all dimensions depends ultimately on the contribution and commitment of organization members. Case findings also highlight the need for ambidextrous forms of organizing that combine 'controllability' with 'responsiveness'. The conceptual notion of organizing dualities has been employed to provide a practical interpretation of the ostensibly competing imperatives implied by ambidexterity. This case explores the dualities that can be demonstrated for the INNFORM triumvirate of structures, processes and boundaries. The dualities interpretation emphasizes an acceptance of texture and the simultaneous presence of what are conventionally viewed as incompatible organizing forms. This was considered a useful conceptual vehicle in the analysis of a case study covering nearly ten years of serious change interventions, where one theoretical view can be misleading in understanding the subtleties and complexities of the actual changes that occurred.

Cyberfraud & identity theft: the hidden costs of business process outsourcing

Offshore business process outsourcing involves additional risks, according to Anne Rouse and David Watson. Here they outline some of these with strategies for their management.

Parameter optimization of kernel-based one-class classifier on imbalance learning

Compared with conventional two-class learning schemes, one-class classification simply uses a single class in the classifier training phase. Applying one-class classification to learn from unbalanced data set is regarded as the recognition based learning and has shown to have the potential of achieving better performance. Similar to twoclass learning, parameter selection is a significant issue, especially when the classifier is sensitive to the parameters. For one-class learning scheme with the kernel function, such as one-class Support Vector Machine and Support Vector Data Description, besides the parameters involved in the kernel, there is another one-class specific parameter: the rejection rate v. In this paper, we proposed a general framework to involve the majority class in solving the parameter selection problem. In this framework, we first use the minority target class for training in the one-class classification stage; then we use both minority and majority class for estimating the generalization performance of the constructed classifier. This generalization performance is set as the optimization criteria. We employed the Grid search and Experiment Design search to attain various parameter settings. Experiments on UCI and Reuters text data show that the parameter optimized one-class classifiers outperform all the standard one-class learning schemes we examined.

Optimization of laccase production from Trametes versicolor by solid fermentation

The regulation of culture conditions, especially the optimization of substrate constituents, is crucial for laccase production by solid fermentation. To develop an inexpensive optimized substrate formulation to produce high-activity laccase, a uniform design formulation experiment was devised. The solid fermentation of Trametes versicolor was performed with natural aeration, natural substrate pH (about 6.5), environmental humidity of 60% and two different temperature stages (at 37 °C for 3 days, and then at 30 °C for the next 17 days). From the experiment, a regression equation for laccase activity, in the form of a second-degree polynomial model, was constructed using multivariate regression analysis and solved with unconstrained optimization programming. The optimized substrate formulation for laccase production was then calculated. Tween 80 was found to have a negative effect on laccase production in solid fermentation; the optimized solid substrate formulation was 10.8% glucose, 27.7% wheat bran, 9.0% (NH4)2SO4, and 52.5% water. In a scaled-up verification of solid fermentation at a 10 kg scale, laccase activity from T. versicolor in the optimized substrate formulation reached 110.9 IU/g of dry mass.

Towards optimization of a real-world robotic-sensor system of systems

The problem of threat detection in an unstructured environment is considered. Three systems, comprising of robots and sensors, are proposed to form a system of systems (SoS) to find a solution to the problem. System interactions are defined to provide a framework for formulation as an SoS optimization problem. Different cost and objective functions are introduced for optimization of local criteria. Using different weights, a linear combination of the local cost and objective functions is obtained to propose a global objective function. An algorithm is suggested to find an optimum value for the global objective function leading towards optimization of the SoS.