Search results

This paper aims to present a hybrid machine learning algorithm for additive manufacturing (AM) design feature recommendation during the conceptual design phase.

In the proposed hybrid machine learning algorithm, hierarchical clustering is performed on coded AM design features and target components, resulting in a dendrogram. Existing industrial application examples are used to train a supervised classifier that determines the final sub-cluster within the dendrogram containing the recommended AM design features.

Through a case study of designing additive manufactured R/C car components, the proposed hybrid machine learning method was proven useful in providing feasible conceptual design solutions for inexperienced designers by recommending appropriate AM design features.

The proposed method helps inexperienced designers who are newly exposed to AM capabilities explore and utilize AM design knowledge computationally.

The purpose of this paper is to conduct a UK-based assessment of oral history technology and to identify the most important features that should be available in any oral history search system.

A co-design approach involving interviews and focus groups was adopted. The framework approach with elements of grounded theory was used to analyse transcripts to identify themes.

The analysis found that “ethics, consent and control”, “accessibility and engagement”, “publicity and awareness”, and “innovative technologies” were the four major themes identified. It was also established that there is limited understanding of oral history in the digital age, numerous interests, ethical concerns, lack of publicity and several key attributes that those designing an oral history search system or archive should strive for. The findings also identified that further exploration into sampling selected technologies on different user groups is required in order to develop software that would benefit the field.

Participants were all recruited from one geographic region. The qualitative methodology utilised could be deemed to have elements of subjectivity.

This study has identified important features of any oral history search system and offered design recommendations for any developer of an oral history search systems.

This research has validated some previous findings for oral history search systems from more limited user studies. New issues for consideration including usability, software development and marketing have also been identified.

Describes two approaches to the evaluation of the built environment. First, discusses post‐occupancy evaluation (POE) which is a formal way of determining whether a recently occupied or remodelled building is performing as was intended in its programming and design. Bases data collection on comprehensive questionnaires in which occupants of the building are asked to report on their experience. Second, looks at the use of facilitated participatory workshops as developed in Scandinavia. Reports a case study carried out in respect of the Taubman Building of Harvard University’s School of Government, opened in 1990, which combines the two traditions. Describes the process used in the study and outlines the issues which surfaced from the study. Concludes by analysing the lessons learned.

There are many investigations in design methodologies, but there are also divergences and convergences as there are so many points of view. This study aims to evaluate to corroborate and deepen other researchers’ findings, dissipate divergences and provide directing to future work on the subject from a methodological and convergent perspective.

This study analyzes the previous reviews (about 15 reviews) and based on the consensus and the classifications provided by these authors, a significant sample of research is analyzed in the design for additive manufacturing (DFAM) theme (approximately 80 articles until June of 2017 and approximately 280–300 articles until February of 2019) through descriptive statistics, to corroborate and deepen the findings of other researchers.

Throughout this work, this paper found statistics indicating that the main areas studied are: multiple objective optimizations, execution of the design, general DFAM and DFAM for functional performance. Among the main conclusions: there is a lack of innovation in the products developed with the methodologies, there is a lack of exhaustivity in the methodologies, there are few efforts to include environmental aspects in the methodologies, many of the methods include economic and cost evaluation, but are not very explicit and broad (sustainability evaluation), it is necessary to consider a greater variety of functions, among other conclusions

The novelty in this study is the methodology. It is very objective, comprehensive and quantitative. The starting point is not the case studies nor the qualitative criteria, but the figures and quantities of methodologies. The main contribution of this review article is to guide future work on the subject from a methodological and convergent perspective and this article provides a broad database with articles containing information on many issues to make decisions: design methodology; optimization; processes, selection of parts and materials; cost and product management; mechanical, electrical and thermal properties; health and environmental impact, etc.

With the developments of e-commerce markets, novel recommendation technologies are becoming an essential part of many online retailers’ economic models to help drive online sales. Initially, the purpose of this paper is to undertake an investigation of apparel recommendations in the commercial market in order to verify the research value and significance. Then, this paper reviews apparel recommendation techniques and systems through academic research, aiming to acquaint apparel recommendation context, summarize the pros and cons of various research methods, identify research gaps and eventually propose new research solutions to benefit apparel retailing market.

This study utilizes empirical research drawing on 130 academic publications indexed from online databases. The authors introduce a three-layer descriptor for searching articles, and analyse retrieval results via distribution graphics of years, publications and keywords.

This study classified high-tech integrated apparel systems into 3D CAD systems, personalised design systems and recommendation systems. The authors’ research interest is focussed on recommendation system. Four types of models were found, namely clothes searching/retrieval, wardrobe recommendation, fashion coordination and intelligent recommendation systems. The forth type, smart systems, has raised more awareness in apparel research as it is equipped with advanced functions and application scenarios to satisfy customers. Despite various computational algorithms tested in system modelling, existing research is lacking in terms of apparel and users profiles research. Thus, from the review, the authors have identified and proposed a more complete set of key features for describing both apparel and users profiles in a recommendation system.

Based on previous studies, this is the first review paper on this topic in this subject field. The summarised work and the proposed new research will inspire future researchers with various knowledge backgrounds, especially, from a design perspective.

The roles recommendation systems play in health care have become crucial in achieving effective care and in meeting the needs of modern care giving. As a result, efforts have been geared toward using recommendation systems in the management of chronic diseases. Effectiveness of these systems is determined by evaluation following implementation and before deployment, using certain metrics and criteria. The purpose of this study is to ascertain whether consideration of criteria during the design of a recommendation system can increase acceptance and usefulness of the recommendation system.

Using survey-style requirements gathering method, the specific health and technology needs of people living with chronic diseases were gathered. The result was analyzed using quantitative method. Sets of harmonized criteria and metrics were used along with requirements gathered from stakeholders to establish relationship among the criteria and the requirements. A matching matrix was used to isolate requirements for prioritization. These requirements were used in the design of a mobile app.

Matching criteria against requirements highlights three possible matches, namely, exact, inferential and zero matches. In any of these matches, no requirement was discarded. This allows priority features of the system to be isolated and accorded high priority during the design. This study highlights the possibility of increasing the acceptance rate and usefulness of a recommendation system by using metrics and criteria as a guide during the design process of recommendation systems in health care. This approach was applied in the design of a mobile app called Recommendations Sharing Community for Aged and Chronically Ill People. The result has shown that with this method, it is possible to increase acceptance rate, robustness and usefulness of the product.

Inability to know the evaluation criteria beforehand, inability to do functional analysis of requirements, lack of well-defined requirements and often poor cooperation from people living with chronic diseases during requirements gathering for fear of stigmatization, confidentiality and privacy breaches are possible limitations to this study.

The result has shown that with this method, it is possible to isolate more important features of the system and use them during the design process, thereby speeding up the design and increasing acceptance rate, robustness and usefulness of the system. It also helps to see in advance the likely features of the system that will enhance its usefulness and acceptance, thereby increasing the confidence of the developers in their ability to deliver a system that will meet users’ needs. As a result, developers know beforehand where to concentrate their efforts during system development to ascertain the possibility of increasing usefulness and acceptance rate of a recommendation system. In addition, it will also save time and cost.

This paper demonstrates originality by highlighting and testing the possibility of using evaluation criteria and metrics during the design of a recommender system with a view to increasing acceptance and enhancing usefulness. It also shows the possibility of using the metrics and criteria in system’s development process for an exercise other than evaluation.

The big challenge in apparel recommendation system research is not the exploration of machine learning technologies in fashion, but to really understand clothes, fashion and people, and know what to learn. The purpose of this paper is to explore an advanced apparel style learning and recommendation system that can recognise deep design-associated features of clothes and learn the connotative meanings conveyed by these features relating to style and the body so that it can make recommendations as a skilled human expert.

This study first proposes a type of new clothes style training data. Second, it designs three intelligent apparel-learning models based on newly proposed training data including ATTRIBUTE, MEANING and the raw image data, and compares the models’ performances in order to identify the best learning model. For deep learning, two models are introduced to train the prediction model, one is a convolutional neural network joint with the baseline classifier support vector machine and the other is with a newly proposed classifier later kernel fusion.

The results show that the most accurate model (with average prediction rate of 88.1 per cent) is the third model that is designed with two steps, one is to predict apparel ATTRIBUTEs through the apparel images, and the other is to further predict apparel MEANINGs based on predicted ATTRIBUTEs. The results indicate that adding the proposed ATTRIBUTE data that captures the deep features of clothes design does improve the model performances (e.g. from 73.5 per cent, Model B to 86 per cent, Model C), and the new concept of apparel recommendation based on style meanings is technically applicable.

The apparel data and the design of three training models are originally introduced in this study. The proposed methodology can evaluate the pros and cons of different clothes feature extraction approaches through either images or design attributes and balance different machine learning technologies between the latest CNN and traditional SVM.

The purpose of this paper is to study the use of online recommendation systems on e‐commerce sites is which becoming more common as marketers recognize their potential to improve their own operations as well as consumers' shopping experiences. Since some consumers question the credibility of these systems, this study compares responses to such systems (classified based on their source into seller and third party systems) with responses to recommendations coming directly from other consumers. The latter may also be better suited for consumers today since many of them utilize direct information from social media on a daily basis. Past research indicates that reactions to such recommendations may depend on the types of goods they describe and therefore this study also tests whether consumer responses vary with types of goods. The study examines consumer reactions to recommendations designed for search, experience, and credence goods. Finally, this study also explores the most desired features of recommendations to help marketers come up with the most effective recommendations that help facilitate purchasing decisions.

The study surveys a convenience sample of 202 undergraduate students to test these objectives. It was a 3 (product types) by 3 (recommendation types) factorial design with multiple dependent variables and three covariates.

The study reveals that, irrespective of the product type, consumers react differently to the three types of recommendations that are tested. This study shows that consumers have the most positive attitudes and most frequently utilize recommendations coming directly from other consumer. This suggests that more attention should be directed to these recommendations in marketing theory and practice. Consumers also hold more positive attitudes towards third‐party recommendation systems than recommendation systems coming from the seller. They also have more positive reactions toward recommendations designed for search and experience goods rather than credence products. Finally, the study also examines the usefulness of different characteristics of these recommendations to help online managers develop most effective recommendations online and finds that it varies with different types of recommendations and products for which recommendations are used.

In addition to the recommendation systems that have been explored in the past (seller and third party systems), the study examines reactions to recommendations coming directly from other consumers, as these recommendations may be better suited for today's audiences. The study shows which recommendation type is best received and most frequently used online. It also tests reactions to recommendations designed for different types of goods. This study includes credence goods, in addition to search and experience products, since consumer reactions to recommendations designed for credence goods have not been yet explored in the past research. It also found that recommendations are better received for goods with a higher number of search features. Finally, the study explores the specific features of different recommendation types and based on the findings proposes how these online recommendations should be structured to be most effective.

Traditional library book recommendation methods are mainly based on association rules and user profiles. They may help to learn about students' interest in different types of books, e.g., students majoring in science and engineering tend to pay more attention to computer books. Nevertheless, most of them still need to identify users' interests accurately. To solve the problem, the authors propose a novel embedding-driven model called InFo, which refers to users' intrinsic interests and academic preferences to provide personalized library book recommendations.

The authors analyze the characteristics and challenges in real library book recommendations and then propose a method considering feature interactions. Specifically, the authors leverage the attention unit to extract students' preferences for different categories of books from their borrowing history, after which we feed the unit into the Factorization Machine with other context-aware features to learn students' hybrid interests. The authors employ a convolution neural network to extract high-order correlations among feature maps which are obtained by the outer product between feature embeddings.

The authors evaluate the model by conducting experiments on a real-world dataset in one university. The results show that the model outperforms other state-of-the-art methods in terms of two metrics called Recall and NDCG.

It requires a specific data size to prevent overfitting during model training, and the proposed method may face the user/item cold-start challenge.

The embedding-driven book recommendation model could be applied in real libraries to provide valuable recommendations based on readers' preferences.

The proposed method is a practical embedding-driven model that accurately captures diverse user preferences.

Although brands have developed mobile applications (apps) to offer consumers new experiences, low app usage numbers indicate the need to develop a systematic, practical evaluation framework for branded app design that specifies concrete design features.

An expert review provides an overview of the design of current branded apps. On the basis of an extensive literature review, this article classifies state-of-the-art design features for branded apps according to a proposed evaluation framework that includes human–computer interaction (HCI)–related and marketing-related evaluation criteria. In an application of these evaluation criteria, the authors evaluate 73 branded apps issued by 11 top fast-moving consumer goods (FMCG) brands.

The expert review identifies strengths and weaknesses that are common to the design of current branded apps. These findings inform the set of design recommendations that this article offers, which includes 14 features common to all types of apps and 9 features specific to particular types of apps.

This research offers practical implications for app designers, who need to address design dimensions contained in the proposed framework including the HCI-related (mobile, social and user experience design features) and marketing-related (branding and customer relationship management design features) to create effective branded apps.

Design elements identified in prior literature remain abstract and do not prescribe a systematic or pragmatic approach to using them in practice. This study takes a multidisciplinary perspective (HCI, marketing and design science) to establish a practical evaluation framework for branded app designs.