Search results

The purpose of this research is to compare several machine learning techniques on the task of Asian language text classification, such as Chinese and Japanese where no word boundary information is available in written text. The paper advocates a simple language modeling based approach for this task.

Naïve Bayes, maximum entropy model, support vector machines, and language modeling approaches were implemented and were applied to Chinese and Japanese text classification. To investigate the influence of word segmentation, different word segmentation approaches were investigated and applied to Chinese text. A segmentation‐based approach was compared with the non‐segmentation‐based approach.

There were two findings: the experiments show that statistical language modeling can significantly outperform standard techniques, given the same set of features; and it was found that classification with word level features normally yields improved classification performance, but that classification performance is not monotonically related to segmentation accuracy. In particular, classification performance may initially improve with increased segmentation accuracy, but eventually classification performance stops improving, and can in fact even decrease, after a certain level of segmentation accuracy.

Apply the findings to real web text classification is ongoing work.

The paper is very relevant to Chinese and Japanese information processing, e.g. webpage classification, web search.

Maintenance is a critical business function with a great impact on economic, environmental and social aspects. However, maintenance decisions' planning has been driven by merely economic and technical measures with inadequate consideration of environmental and social dimensions. This paper presents a review of the literature pertaining to sustainable maintenance decision-making models supported by a bibliometric analysis that seeks to establish the evolution of this research over time and identify the main research clusters.

A systematic literature review, supported with a bibliometric and network analysis, of the extant studies is conducted. The relevant literature is categorized based on which sustainability pillar, or possibly multiple ones, is being considered with further classification outlining the application area, modeling approach and the specific peculiarities characterizing each area.

The review revealed that maintenance and sustainability modeling is an emerging area of research that has intensified in the last few years. This fertile area can be developed further in several directions. In particular, there is room for devising models that are implementable, based on reliable and timely data with proven tangible practical results. While the environmental aspect has been considered, there is a clear scarcity of works addressing the social dimension. One of the identified barriers to developing applicable models is the lack of the required, accurate and timely data.

This work contributes to the maintenance and sustainability modeling research area, provides insights not previously addressed and highlights several avenues for future research. To the best of the authors' knowledge, this is the first review that looks at the integration of sustainability issues in maintenance modeling and optimization.

The purpose of this paper is to utilize the proposed function transformation to make the original data series meet the properties of smooth ratio being lessen and stepwise ratio deviation being reduced, so that to improve the accuracy of grey forecasting model.

According to the characteristics of anti-cotangent functional graph variation, the theory of functional transformation and grey system modeling, the authors proposed a grey model based on the transformation of Aarc cot x+B function.

The calculated result of practical example shows that the proposed method is both valid on improving fitting effectiveness and forecasting accuracy.

The proposed method in this paper can effectively improve the accuracy of forecasting of high-growth original data series (derivative of data series is not only greater than 1 but also increasing).

The paper succeeds in providing an effective function transformation to make the smooth ratio and stepwise ratio deviation reduced significantly.

The purpose of this paper is to develop a new approach to investigate complex processes, such as software development processes, using business process modeling.

The paper presents an investigation into the use of role activity diagramming (RAD) to model complex processes in the software industry sector, with reference to the process of TestWarehouse as a case study.

Systematic extension and quantitative analysis to RAD models led to the discovery of process bottlenecks, identification of cross functional boundary problems, and focused discussion about automation of processes.

Further work is required to validate and evaluate the proposed approach using several cases with different application domains and thus generalize the adopted approach.

A new approach has been used successfully to understand and analyze business processes. The tools and techniques that are used to perform the approach are not complicated and do not need much specialist expertise, so the approach is not only oriented toward specialists but also toward organizations' managers and staff.

New techniques have been developed by using process modelling to deepen the understanding and analyzing of complex organizational processes. This research implements a practical investigation which uses a case study to validate the new techniques.

This paper aims to describe the extent of supplier access to customer forecast information and the perceived quality of such information and also to explain the impact of forecast information access and forecast information quality (FIQ) on supply chain performance.

FIQ is defined, and a measurement instrument is developed from theory. The analysis is based on a survey of the most important suppliers of 136 Swedish companies.

Findings show that a large proportion of the suppliers receive customer forecasts, but that the FIQ is lower further upstream in the supply chain and, in some variables, lower for make‐to‐order suppliers. The greatest information quality deficiency of the forecast was that it was considered unreliable. The only significant difference in supply chain performance found between make‐to‐stock suppliers with and without access to forecast was related to the use of safety stock in finished goods inventory.

The study contains two types of conclusions: those developed from the conceptual discussion in the theoretical framework and those of the empirical study. In the theoretical framework, measurement instruments for FIQ and supply chain performance (corrective actions, preventive actions and customer service performance) were developed. The study identified several empirical relationships, but it was conducted on a sample with a lot of variation.

The understanding of the performance impact of FIQ. FIQ shows quality deficiencies on all variables, which indicates room for improvement.

Research on supply chain information quality as well as dyadic research approaches are rare.

In performative architectural design, daylighting is a crucial design consideration; however, the evaluation of daylighting in the design process can be challenging. Immersive environments (IEs) can create a dynamic, multi-sensory, first-person view in computer-generated environments, and can improve designers' visual perception and awareness during performative design processes. This research addresses the need for interactive and integrated design tools for IEs toward better-performing architectural solutions in terms of daylighting illumination. In this context, building information modeling and performance simulations are identified as critical technologies to be integrated into performative architectural design.

This research adopts a design science research (DSR) methodology involving an iterative process of development, validation and improvement of a novel and immersive tool, HoloArch, that supports design development during daylighting-informed design processes. HoloArch was implemented in a game engine during a spiral software development process. HoloArch allows users to interact with, visualize, modify and explore architectural models. The evaluation is performed in two workshops and a user study. A hybrid approach that combines qualitative and quantitative data collection was adopted for evaluation. Qualitative data analyses involve interviews, while quantitative data analyses involve both daylighting simulations and questionnaires (e.g. technology acceptance model (TAM), presence and system usability scale (SUS)).

According to the questionnaire results, HoloArch had 92/100 for SUS, a mean value of 120.4 for presence questionnaire (PQ) and 9.4/10 for TAM. According to the simulation results, all participants improved the given building's daylighting performance using HoloArch. The interviews also indicated that HoloArch is an effective design tool in terms of augmented perception, continuous design processes, performative daylighting design and model interaction. However, challenges still remain regarding the complete integration of tools and simultaneous simulation visualization. The study concludes that IEs hold promising potentials where performative design actions at conceptual, spatial and architectural domains can take place interactively and simultaneously with immediate feedback.

The research integrates building information modeling (BIM), performative daylighting simulations and IEs in an interactive environment for the identification of potentials and limitations in performative architectural design. Different from existing immersive tools for architecture, HoloArch offers a continuous bidirectional workflow between BIM tools and IEs.

It is widely known that fast-fashion retailers are struggling to keep up with consumer attention for quick responses within the fashion industry. With the advance of Internet and e-commerce, consumers prefer to purchase online. Online platform information has become an essential source for exploring consumer attention. However, there is often a mismatch between the information provided by retailers and the feedback received from consumers, leading to an imbalance between the supply side and demand side of online information. The purpose of this study is therefore to provide a unified approach to discover consumer attention from the design topic aspect by revealing the information imbalance between supply side and demand side.

To address the issue of online information imbalance and discover consumer attention, this study proposed an approach that focuses on the design topic perspective. The design topic is a collection of design elements that represent a clothing-design feature more comprehensively and accurately compared to a single design element. The proposed approach begins with generating design topics through topic modeling based on online information provided by retailers on e-commerce platforms. Two indicators, influence degree and attention degree, are then used to quantify the intensity of supply information and consumer attention related to design topics. Finally, design topic strategy diagrams are constructed to reveal information imbalance and discover consumer attention.

The experimental case demonstrates the existence of information imbalance, indicating that the intensity of supply information and consumer attention from the perspective of design topics is not uniform, although both follow the Pareto principle. The results of consumer attention distribution with heavy power-law tails are consistent with current research findings. This further demonstrates that the proposed approach is capable of discovering consumer attention in the design topic strategy diagrams.

The issue of information imbalance between retailers and consumers poses a challenge in keeping up with customer attention. The proposed approach offers a practical solution by visually identifying the symptoms of information imbalance and discovering consumer attention through design topic strategy diagrams. This approach provides fast-fashion retailers with a valuable reference to seize market opportunities, improve product design and adjust marketing or management strategies.

This study proposes a novel approach to disclose the issue of information imbalance between supply side and demand side and therefore to discover consumer attention from the perspective of design topics. In addition, guidelines for applying the proposed approach for fast-fashion marketing and management are presented.

Considering the swift adoption of innovative sustainability practices in businesses to accomplish sustainable development goals (SDGs), research on corporate sustainability has increased significantly over the years. This research intends to analyze the published literature, emphasizing the existing, emerging and future research directions on achieving the SDGs through corporate sustainability.

This research analyzed the growing trends in corporate sustainability by incorporating 2,038 Scopus articles published between 1999 and 2022 using latent Dirichlet allocation (LDA) topic modeling, bibliometrics and qualitative content analysis techniques. The bibliometric data were analyzed using performance and science mapping. Thereafter, topic modeling and content analysis uncovered the topics included under the corporate sustainability umbrella.

The findings indicate that investigation into corporate sustainability has considerably increased from 2015 to date. Additionally, the majority of studies on corporate sustainability are from the United States of America, the United Kingdom and Germany. Besides, the USA has the most collaboration in terms of co-authorship. S. Schaltegger was considered the most productive author. However, P. Bansal was ranked as the top author based on a co-citation analysis of authors. Further, bibliometric data were evaluated to analyze leading publications, journals and institutions. Besides, keyword co-occurrence analysis, topic modeling and content analysis highlighted the theoretical underpinnings and new patterns and provided directions for further research.

This study demonstrates various existing and emerging themes in corporate sustainability, which have various repercussions for academicians and organizations. This research also examines the lagging themes in the current domain.

The purpose of this paper is to capture the dynamic variations in sales of a product based upon the dynamic estimation of the time series data and propose a model that imitates the price discounting and promotion strategy for a product category in a retail organization. A modest attempt has been made in the study to capture the relationship between the sales promotion, price discount and the batch procurement strategy of a particular product category to maximize sales volume and profitability.

Time series data relating to sales have been used to model the sales estimates using moving average and proportional and derivative control; thereafter a sales forecast is generated to estimate the sales of a particular product category. This provides valuable inputs for taking lot sizing decisions regarding procurement of the products that considerably impact the sales promotion and intelligent pricing decisions. A conceptual framework is developed for modeling the dynamic price discounting strategy in retail using fuzzy logic.

The model captures the lag effect of sales promotion and price discounting strategy; other strategies have been formulated based upon the sales forecast that was done for taking the lot sizing decisions regarding procurement of products in the selected category. This has helped minimize the inventory cost thereby keeping the profitability of the retail organization intact.

There is no appropriate empirical data to verify the models. In light of the research approach (modeling based upon historical time series data of a particular product category) that was undertaken, there is a possibility that the research results may be valid for the product category that was selected. Therefore, the researchers are advised to test the proposed propositions further for other product categories.

The study provides valuable insight on how to use the real-time sales data for designing a dynamic automated model for product sales promotion and price discounting strategy using fuzzy logic for a retail organization.

With the current wave of modernization in the dairy industry, the global dairy market has seen significant shifts. Making the most of inventory planning, machine learning (ML) maximizes the movement of commodities from one site to another. By facilitating waste reduction and quality improvement across numerous components, it reduces operational expenses. The focus of this study was to analyze existing dairy supply chain (DSC) optimization strategies and to look for ways in which DSC could be further improved. This study tends to enhance the operational excellence and continuous improvements of optimization strategies for DSC management

Preferred reporting items for systematic reviews and meta-analyses (PRISMA) standards for systematic reviews are served as inspiration for the study's methodology. The accepted protocol for reporting evidence in systematic reviews and meta-analyses is PRISMA. Health sciences associations and publications support the standards. For this study, the authors relied on descriptive statistics.

As a result of this modernization initiative, dairy sector has been able to boost operational efficiency by using cutting-edge optimization strategies. Historically, DSC researchers have relied on mathematical modeling tools, but recently authors have started using artificial intelligence (AI) and ML-based approaches. While mathematical modeling-based methods are still most often used, AI/ML-based methods are quickly becoming the preferred method. During the transit phase, cloud computing, shared databases and software actually transmit data to distributors, logistics companies and retailers. The company has developed comprehensive deployment, distribution and storage space selection methods as well as a supply chain road map.

Many sorts of environmental degradation, including large emissions of greenhouse gases that fuel climate change, are caused by the dairy industry. The industry not only harms the environment, but it also causes a great deal of animal suffering. Smaller farms struggle to make milk at the low prices that large farms, which are frequently supported by subsidies and other financial incentives, set.

This paper addresses a need in the dairy business by giving a primer on optimization methods and outlining how farmers and distributors may increase the efficiency of dairy processing facilities. The majority of the studies just briefly mentioned supply chain optimization.