Search results

Opinion mining (OM), also known as “sentiment classification”, which aims to discover common patterns of user opinions from their textual statements automatically or semi-automatically, is not only useful for customers, but also for manufacturers. However, because of the complexity of natural language, there are still some problems, such as domain dependence of sentiment words, extraction of implicit features and others. The purpose of this paper is to propose an OM method based on topic maps to solve these problems.

Domain-specific knowledge is key to solve problems in feature-based OM. On the one hand, topic maps, as an ontology framework, are composed of topics, associations, occurrences and scopes, and can represent a class of knowledge representation schemes. On the other hand, compared with ontology, topic maps have many advantages. Thus, it is better to integrate domain-specific knowledge into OM based on topic maps. This method can make full use of the semantic relationships among feature words and sentiment words.

In feature-level OM, most of the existing research associate product features and opinions by their explicit co-occurrence, or use syntax parsing to judge the modification relationship between opinion words and product features within a review unit. They are mostly based on the structure of language units without considering domain knowledge. Only few methods based on ontology incorporate domain knowledge into feature-based OM, but they only use the “is-a” relation between concepts. Therefore, this paper proposes feature-based OM using topic maps. The experimental results revealed that this method can improve the accuracy of the OM. The findings of this study not only advance the state of OM research but also shed light on future research directions.

To demonstrate the “feature-based OM using topic maps” applications, this work implements a prototype that helps users to find their new washing machines.

This paper presents a new method of feature-based OM using topic maps, which can integrate domain-specific knowledge into feature-based OM effectively. This method can improve the accuracy of the OM greatly. The proposed method can be applied across various application domains, such as e-commerce and e-government.

The purpose of this paper is to explore the influence that competitors and supply chain (SC) partners have on firms’ feature-based production capabilities (FBPC). Also, it analyzes the consumers’ customization options, the operational challenges and the need for servitization as a service-operations strategy to bypass the product complexity created through features. The author assesses the impact of FBPC on performance and uses some moderators to explore the operational implications in depth.

The author tests research hypotheses through structural equation modeling using a sample of 172 manufacturing firms. The author analyzes the links existing among constructs and tests the influence of certain operational moderators within the network of relationships.

FBPC are highly dictated by competitors’ and SC partners’ decisions, while servitization is a vital prerequisite to guarantee a valuable customization option. Although operational performance is highly challenged by FBPC, only good consumer experiences with features enhance economic performance. The analysis of moderators reveals that advanced planning systems, vendor managed inventory and distribution requirement planning enable firms to better exploit their operations. Total quality management helps firms to offer higher levels of servitization while reverse logistics needs careful evaluation to balance the trade-offs between higher operational performance and supply structure changes.

This research empirically tests the influence of both competitors and suppliers when firms acquire FBPC. The author investigates consumers’ requests for features and the benefits that servitization can supply when goods become too complex. The author tests how FBPC affect operations as well as the implications for economic performance. Finally, the author searches for moderators to assess the overall economic benefits of FBPC and better appreciate the operational implications.

The purpose of this paper is to present the results on a model for manufacturing under the constraints and conditions of mass customization environment.

The proposed model is based on manufacturing features and entails the concept of modular design. That is, manufacturing features are identified and analyzed in a way that enables the generation of what is called “manufacturing core”. Manufacturing cores are semi‐finished products that have certain manufacturing features. The core can be used to manufacture a range of products after conducting certain manufacturing processes. Manufacturing cores are generated through two phases of optimization. The first phase is known as product's manufacturing features analysis which includes starting features identification. The second phase is known as manufacturing cores formation that ends with generation of manufacturing cores.

The methodology is implemented on real products (flanges) as a case study. The proposed model for mass customization is compared at make‐to‐stock and make‐to‐order policies in terms of a burden which includes the time and the cost that are required to fulfil a production order. Applying the proposed model of mass customization entails the minimum total burden required.

When the number of generic and variant features increases, an automated feature‐recognition module or sub‐system is required to facilitate the extraction of manufacturing features.

The proposed methodology is used for design of customized product through the application of integrated design for modularity and mass customization approach for production.

The proposed methodology entails development of semi‐finished products based on manufacturing features that can be used for design and manufacturing of a range of products.

The representation of Heterogeneous Object (HO) is divided into two categories: Data model (DM) and material evaluation paradigm (MEP). A hybrid methodology with geometry model and volumetric dataset to represent heterogeneous properties is proposed in this paper. Geometry model of an object can guarantee the accuracy of the final HO slices; and volumetric dataset lends the flexible manipulability and other advantages to HO representation. Two MEPs, namely distance field (DF) based and Fixed Reference Features & Active Grading Source(s) (FRF&AGS) are presented to facilitate the process of HO representation according to the designer)s input parameters. The DM can be modified interactively with users until the final satisfactory result is obtained. In this paper, a scheme of HO slicing is described. In this method, we utilize the slices contour of geometrical model as constraint to reconstruct the HO slices, which can theoretically achieve the same accuracy with the geometrical shape. Some examples of Heterogeneous object represented with our scheme are provided.

Concurrent design and manufacturing is widely accepted as essential for obtaining an economically conceivable design solution for industrial production. Nevertheless the development of a viable computer‐aided inspection planning (CAIP) using CAD as input for effective NC‐measuring data preparation has not yet been successful. This paper introduces an approach to direct integration between CAD and CAIP by developing a feature‐based computer aided design/inspection planning (FB‐CAIP) system. The FB‐CAIP system contains a computer‐internal model of a product that contains sufficient information to guide the direct generation of NC code of the inspection activity. The developed small prototype system integrates knowledge‐based inspection planning with feature‐based CAD system for an automatic CNC measuring program generation of prismatic parts.

Propoes a methodology that enables a dynamic and interactive 3‐Dvisualization model of the assembly process to be developed from the CAD files of each part in the assembly. Makes three main contributions to the research in this area. First, a taxonomy of features for assembly is presented. Second, a process model for generating interactive 3D models of the assembly process is developed and, third, a new algorithm for creating a dynamic assembly model is derived. This algorithm, called the 3D assembly visualization (3AV) algorithm, involves instantiating the motion attributes that specify the motion of each part in the assembly. This dynamic assembly model is then converted to a 3‐D renderable format for visualization. An example is presented that uses virtual reality modeling language (VRML) as the 3‐D representation language. The result is a dynamic and interactive visual representation of the assembly operation. Such visualization can be of considerable use in DFA.

This paper aims to propose an intelligent system that serves as a cost estimator when new part orders are received from customers.

The methodologies applied in this study were case-based reasoning (CBR), analytic hierarchy process, rule-based reasoning and fuzzy set theory for case retrieval. The retrieved cases were revised using parametric and feature-based cost estimation techniques. Cases were represented using an object-oriented (OO) approach to characterize them in n-dimensional Euclidean vector space.

The proposed cost estimator retrieves historical cases that have the most similar cost estimates to the current new orders. Further, it revises the retrieved cost estimates based on attribute differences between new and retrieved cases using parametric and feature-based cost estimation techniques.

The proposed system was illustrated using a numerical example by considering different lathe machine operations in a computer-based laboratory environment; however, its applicability was not validated in industrial situations.

Different intelligent methods were proposed in the past; however, the combination of fuzzy CBR, parametric and feature-oriented methods was not addressed in product cost estimation problems.

This paper aims to evaluate and compare the performance of different computer vision algorithms in the context of visual servoing for augmented robot perception and autonomy.

The authors evaluated and compared three different approaches: a feature-based approach, a hybrid approach and a machine-learning-based approach. To evaluate the performance of the approaches, experiments were conducted in a simulated environment using the PyBullet physics simulator. The experiments included different levels of complexity, including different numbers of distractors, varying lighting conditions and highly varied object geometry.

The experimental results showed that the machine-learning-based approach outperformed the other two approaches in terms of accuracy and robustness. The approach could detect and locate objects in complex scenes with high accuracy, even in the presence of distractors and varying lighting conditions. The hybrid approach showed promising results but was less robust to changes in lighting and object appearance. The feature-based approach performed well in simple scenes but struggled in more complex ones.

This paper sheds light on the superiority of a hybrid algorithm that incorporates a deep neural network in a feature detector for image-based visual servoing, which demonstrates stronger robustness in object detection and location against distractors and lighting conditions.

The purpose of this paper is to present weighted Euclidean distance for measuring whether the fitting of projective transformation matrix is more reliable in feature-based image stitching.

The hybrid model of weighted Euclidean distance criterion and intelligent chaotic genetic algorithm (CGA) is established to achieve a more accurate matrix in image stitching. Feature-based image stitching is used in this paper for it can handle non-affine situations. Scale invariant feature transform is applied to extract the key points, and the false points are excluded using random sampling consistency (RANSAC) algorithm.

This work improved GA by combination with chaos's ergodicity, so that it can be applied to search a better solution on the basis of the matrix solved by Levenberg-Marquardt. The addition of an external loop in RANSAC can help obtain more accurate matrix with large probability. Series of experimental results are presented to demonstrate the feasibility and effectiveness of the proposed approaches.

The modified feature-based method proposed in this paper can be easily applied to practice and can obtain a better image stitching performance with a good robustness.

A hybrid model of weighted Euclidean distance criterion and CGA is proposed for optimization of projective transformation matrix in image stitching. The authors introduce chaos theory into GA to modify its search strategy.

For part models with complex shape features or freeform shapes, the existing build orientation determination methods may have issues, such as difficulty in defining features and costly computation. To deal with these issues, this paper aims to introduce a new statistical method to develop fast automatic decision support tools for additive manufacturing build orientation determination.

The proposed method applies a non-supervised machine learning method, K-Means Clustering with Davies–Bouldin Criterion cluster measuring, to rapidly decompose a surface model into facet clusters and efficiently generate a set of meaningful alternative build orientations. To evaluate alternative build orientations at a generic level, a statistical approach is defined.

A group of illustrative examples and comparative case studies are presented in the paper for method validation. The proposed method can help production engineers solve decision problems related to identifying an optimal build orientation for complex and freeform CAD models, especially models from the medical and aerospace application domains with much efficiency.

The proposed method avoids the limitations of traditional feature-based methods and pure computation-based methods. It provides engineers a new efficient decision-making tool to rapidly determine the optimal build orientation for complex and freeform CAD models.