Customization Framework Research Articles

GREEN SERVICE QUALITY AND CUSTOMER SATISFACTION FOR MALAYSIA AIRLINE COMPANIES

Purpose: The purpose of this paper is to propose a framework of airlines customer’s evaluation of green service quality toward customer’s satisfaction provided by Malaysia Airline Companies.
 
 Design/Methodology/Approach: This paper reviews the conceptual and empirical literature to develop a model of the various aspects of the service quality – customer satisfaction relationship encompassed by the concept of ‘airline customer satisfaction’ and to assess the advantages and disadvantages of alternative methods of measurement. Six conceptual dimensions are identified: (1) Airline tangibles (2) Terminal tangibles (3) Personnel (4) Empathy (5) Image (6) Green Airport (7) Customer Satisfaction
 Findings: Integration of these dimensions into a conceptual framework that describes the relationships among the components and how they collectively result in green service quality and customer satisfaction. We also elucidate future research directions for management scholars
 
 Research Limitation/Implication: The research examines the relationship between green service quality dimension and customer satisfaction in airline industry. This study focuses on the evaluation of all airline service user regarding airline service quality. The main limitation of this study is that it focusses to customer satisfaction on all Airlines Companies: thus, the result cannot be generalized.
 
 Practical Implications: The framework proposed can be applied to future research on green service quality and customer satisfaction. This study will lead to passenger’s satisfaction and encourage the development of long-term relationships with their customers.

Simulating quantum key distribution in fiber-based quantum networks

Quantum networks exploit the unique properties of quantum mechanics to enable communication and networking tasks unavailable to existing distributed classical systems. Recently, the research community has focused considerable effort on the simulation of large-scale quantum networks with the ultimate goal of understanding their general properties, developing technical standards, and estimating their expected performance. However, comparatively little effort has been spent considering how quantum networks may impact tactical scenarios of military relevance where both quantum and classical resources may be severely constrained. Here, we develop a custom framework, called QuanTACT, for quantum network simulation explicitly designed for future integration into existing tactical simulation tools. In particular, our framework extends the existing quantum networking tool, SQUANCH, to include channel models required to simulate deployed fiber environments. Furthermore, we implement the additional subroutines needed to simulate entanglement-based quantum key distribution (QKD) and use published results from various field-deployed QKD experiments to benchmark the performance of our framework.

Social media user behavior analysis applied to the fashion and apparel industry in the big data era

With the rapid development of the Internet and new media, the enormous data from social media and other public platforms have attracted increasing attention to user behavior research. Fashion is a hot topic for both the general public and the social economy, so there is great potential for exploring and manipulating social media data for the development of the fashion industry in the current era. This paper aims to explore the current status of social media user behavior analysis applied to the fashion and apparel industry for advanced product development, branding strategy planning and the resolution of other decision-making problems in the big data context. First, articles were retrieved from the database "Web of Science". With the assistance of experts, 201 articles were determined for further study. Next, the evolution of hot topics within the domain was visualized and discussed through bibliometric analysis. Then, the application of social media data in the fashion domain was investigated, and common data mining methods were discussed. Finally, the paper summarized the development status of social media user behavior analysis (SMUBA) applied to the fashion and apparel industry and put forward the future prospect under the framework of mass customization in the big data era.

Research on Intelligent Customization of Cross-Border E-Commerce Based on Deep Learning

Cross-border e-commerce has become an important way of “New Infrastructure for Foreign Trade” and “Online Silk Road construction.” Utilizing intelligent technology to energize cross-border e-commerce can improve the quality and efficiency of the whole industrial chain. Cross-border e-commerce enterprises generally face the problem of product customization and development due to the large difference in international market demand. This study first analyzes the research status and technical underpinnings of intelligent customization of cross-border e-commerce, then establishes the technical framework of intelligent customization of cross-border e-commerce based on in-depth learning, and subsequently trains, tests, and analyzes the model, and the intelligent customization model has achieved a higher learning level. Finally, it puts forward the promotion and application strategy of cross-border e-commerce intelligent customization based on deep learning. It has theoretical significance and practical value for intelligently identifying changes in international market demand, helping cross-border e-commerce enterprises select products, and optimizing cross-border e-commerce product development.

CUSTOMised return to training: supporting trainers and trainees with bespoke simulation courses

10% of 50,000 doctors in postgraduate training programmes in England are taking approved time out of training at any time [1]. The NHS People Plan [2] aims to welcome back colleagues who want to return, which can be a stressful experience for trainees. It is our duty as educators to provide support. Health Education England offer SuppoRTT funding to create opportunities for trainee development. Despite regional courses, returning trainees felt their individual needs were not met. We aimed to provide additional, bespoke 1:1 training within a psychologically safe environment to paediatric trainees in our hospital before their return to training. Trainee participants had email and phone correspondence with a consultant paediatrician prior to their return date. A half-day bespoke simulation course was co-designed with the participant at a mutually convenient date. Teaching was delivered by a consultant or senior registrar trained in simulation and debriefing. The bespoke course included a variety of activities to meet personal goals, including basic procedures, scenarios in the simulation centre, and if ready, a short in-situ simulation with multidisciplinary staff (if available). In addition, trainees were signposted to existing courses and resources. The simulation centre also offered support to the Educational Supervisor in completing SuppoRTT Funding applications. Afterwards, returning trainees were asked to provide feedback via email. This experience has led us to develop a framework for future learners from different specialities and the wider multidisciplinary team; the CUSTOM framework, Creating Unique Support for Trainees and Others with the Multidisciplinary team. In three years, we provided bespoke training to six paediatric doctors, four of whom were returning after maternity leave and two from research. Five trainees had bespoke sessions, one trainee chose to attend a simulation course with additional support and feedback rather than requesting an individualised course which would have had to be created. Themes from feedback included a positive learning environment, appreciation for bespoke training opportunities, increasing trainee confidence and appreciation for general support ( Feedback received from trainees Our bespoke courses were successful and well received by paediatric trainees. We are launching a new framework, CUSTOM, Creating Unique Support for Trainees and Others with the Multidisciplinary Team. CUSTOM will support other departments to offer bespoke courses. Going forward, we aspire to expand this support to returners from the multidisciplinary team. 1. Health Education England. SuppoRTT. Health Education England. 2022. 2. NHS England. NHS England NHS People Plan. England.nhs.uk. 2022.

Predictive modeling of a subcritical pulverized-coal power plant for optimization: Parameter estimation, validation, and application

As renewable power generation deployment increases, fossil fuel plants are increasingly required to operate more flexibly. Many coal-fired power plants were originally designed to operate at base load and do not operate optimally at partial load. Predictive first-principles plant-wide models can be employed to identify opportunities for flexibility improvements and diagnose low-load operating issues. This paper describes the application of the Institute for the Design of Advanced Energy Systems Integrated Platform (IDAES) to model and optimize flexible power plant operations. The key benefits of using IDAES are that it provides an open-source, fully equation-oriented modeling framework for efficient modular model construction, reuse, and customization, together with a mathematical optimization framework leveraging powerful, state-of-the-art solvers. The process systems engineering workflow from predictive process simulation to parameter estimation, model validation, and plant optimization is applicable to a variety of existing and next-generation energy systems as well as other chemical and environmental processes. To demonstrate this capability, a physics-based, steady-state model was developed to improve full- and part-load performance of the Escalante Generating Station, a 245 MWe (net) subcritical pulverized coal-fired power plant owned and operated by Tri-State Generation and Transmission Association. Specifically, sixty-nine model parameters were simultaneously estimated from several months of operating data enabling prediction of flow rates, temperatures, pressures, and steam quality throughout the plant. The validated model was leveraged by Escalante to reduce the minimum operating load from 90 MW to 50 MW by diagnosing a low-load water-hammer issue, enabling coal usage and emissions reductions during periods of low power demand. Additionally, opportunities for heat rate reduction (i.e., efficiency improvement) through a steeper sliding-pressure approach to load-following and optimization of other boiler operating variables were also identified and quantified. For example, a potential efficiency improvement of 0.7 percentage points was observed at half-load operation.

Blockchain-based mass customization framework using optimized production management for industry 4.0 applications

Customers want to experience unique products that suit their individual preferences. Therefore, companies are looking for ways to produce personalized products by moving away from traditional production models. Technologies such as blockchain, IoT, and cyber-physical systems have an important role in adopting the personal custom production model. In this study, a reliable and optimized mass customization framework is proposed. The framework has three main contributions. First, the use of Blockchain provides advantages in terms of data persistence, traceability, transparency, and reliability. Second, the production process is optimized by using artificial intelligence methods. A decision support mechanism is proposed for customers who will place orders. As a combination of the contributions, the proposed mass customization framework covers the processes from ordering to production. In addition to contributions such as facilitated customization and reliable data, energy saving in production is increased with the proposed framework. Simulation results show that energy savings between 10 and 47% are achieved.

An Online Learning Framework for Targeting Demand Response Customers

We study the optimal design of demand response and peak-time rebate programs in the electricity sector. Load-serving entities (LSEs) frequently use demand response or peak-time rebate programs to reduce consumption during peak hours. However, LSEs have imperfect information, so they typically estimate a customer’s counterfactual energy consumption—often referred to as ‘baseline’— and offer compensations for reductions below this threshold. Due to the inherent variability and uncertainty of demand, this approach may lead to generous incentives to customers who make no effort to reduce their demand, and underpayment to those who do. We show that the estimated baseline is not necessarily the optimal threshold for calculating rebates in demand response programs. The LSE needs to learn about customers’ demand patterns and also customers’ propensity for reductions over time. We bring in tools and methodologies from online learning to formulate and solve the LSE’s optimization problem in designing demand response program. By appropriately tuning the parameters, the LSE can use this framework to balance multiple objectives to determine the appropriate rebate threshold for customers. Using the data from a ToU pricing experiment in London, we show that compared to a conventional demand response program, our approach significantly improves the targeting of demand response payments.

The impact of e-service on hotels' booking: adjusted TAM framework for customers' intentions to book hotels online

Electronic services have modified the procedures of online communication, namely in terms of available information which facilitates comparisons and transparency of markets, information diversity, and website interactivity. Understanding the determinants of customers' intentions for booking online through electronic services becomes important for the hospitality industry because, within this industry, hotels are witnessing a reorganisation of the distribution channels and marketing strategies. The purpose of this study was to examine the relationship between the TAM model, dimensions of e-service quality, and clients' hotel e-booking intentions, focusing on evidence drawn from consumers of five-star hotels in Beirut, Lebanon. Customers still seek assistance during their online booking procedure. Results revealed that perceived trust, followed by perceived ease of use and perceived risk are key factors of e-booking. In managerial terms, this research enables decision-makers to identify factors influencing consumer behaviour when buying online, as well as the motivation factors that drive them to make online purchases. Finally, this study determined the degree of association of variables through linear regression analysis in an empirical study conducted on 154 hotel guests.

The impact of e-service on hotels' booking: adjusted TAM framework for customers' intentions to book hotels online

The impact of e-service on hotels' booking: adjusted TAM framework for customers' intentions to book hotels online

Attention based CNN model for fire detection and localization in real-world images

Fire is a severe natural calamity that causes significant harm to human lives and the environment. Recent works have proposed the use of computer vision for developing a cost-effective automated fire detection system. This paper presents a custom framework for detecting fire using transfer learning with state-of-the-art CNNs trained over real-world fire breakout images. The framework also uses the Grad-CAM method for the visualization and localization of fire in the images. The model also uses an attention mechanism that has significantly assisted the network in achieving better performances. It was observed through Grad-CAM results that the proposed use of attention led the model towards better localization of fire in the images. Among the plethora of models explored, the EfficientNetB0 emerged as the best-suited network choice for the problem. For the selected real-world fire image dataset, a test accuracy of 95.40% strongly supports the model's efficiency in detecting fire from the presented image samples. Also, a very high recall of 97.61 highlights that the model has negligible false negatives, suggesting the network to be reliable for fire detection.

Guest Editors’ Introduction: Machine Intelligence at the Edge

<bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Recent years have</b> seen widespread application of machine learning (ML) to a diverse range of industries and problem domains. By taking advantage of the availability of massive amounts of data and scalable compute resources, ML methods are able to outperform traditional hand-tuned models on today’s wide-range of AI tasks, particularly in the settings of server computing and/or cloud computing. However, the success of ML in sensing applications such as object detection and speech recognition has also driven a demand for such technology (both training and inference) in edge settings, for applications such as autonomous vehicles, mobile devices, and embedded/Internet of Things (IoT) systems. Unfortunately, most existing ML models, hardware, and frameworks are tailored toward the server and/or cloud computing environments and are ill-equipped for edge computing. State- of-the-art ML systems in industry today already use custom frameworks, algorithms, and hardware built for a server infrastructure. Addressing the unique challenges of ML at the edge will similarly require specialization, codesign, and integration of domain knowledge for the edge across the computing stack. This timely special issue <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">IEEE Design&amp;Test</i> of called for novel research on ML models, hardware architectures, programming tools, and design methodologies for ML at the edge.

A Parametric Product Design Framework for the Development of Mass Customized Head/Face (Eyewear) Products

This study led to the development of a parametric design method for mass-customised head/face products. A systematic review of different approaches for mass customization was conducted, identifying advantages and limitations for their application to new product development. A parametric modelling algorithm of a 3D human face was developed using selected scanned 3D head models. The algorithm was developed from a set of measurable and adjustable parameter points related to the facial geometry. These parameters were defined using planimetry. Using the assigned parameter values as input, the parametric model generated 3D models of a human face that served as a reference for the design of customized eyewear. The current challenges and opportunities of mass customized head/face products are described, along with the possibilities for new parametric product design approaches to enable rapid manufacturing and mass customization. This study also explored whether a new parametric design framework for mass customization could be effectively implemented as an early-stage new product development strategy for head/face products.

A neural network based price sensitive recommender model to predict customer choices based on price effect

The impact of price and price changes should not be ignored while designing algorithms for predicting customer choice. Consumer preferences should be modeled with consideration of price effects. Businesses need to consider for efficient prediction of an individual's purchase behaviour. Personalized recommendation systems have been studied with machine learning algorithms. However, the price-aware personalized recommendation has received little attention. In this paper, we attempt to capture insightful economic results considered in the marketing and economics disciplines by employing modern machine learning architecture for predicting customer choice in a large-scale supermarket context. We extract personalized price sensitivities and examine their importance in consumer behaviour. The employed data collected from a supermarket chain in Germany consists of implicit feedback based on customer-product interactions and the price of every interaction. We propose a two-pathway matrix factorization (2way-MF) model that is price-aware and tries to memorize customer-product interaction's implicit feedback. The proposed models achieve better model performance than standard Matrix Factorization models widely used in the industry. The approach was re-validated with data from supermarket chain in Taiwan. Other industries can adopt the proposed framework of modeling customer's preferences based on price sensitivity. We suggest that further research and analyses could help understand the cross-price elasticities.

An effective adaptive customization framework for small manufacturing plants using extreme gradient boosting-XGBoost and random forest ensemble learning algorithms in an Industry 4.0 environment

The prevailing competitive manufacturing industry calls for continuous customer satisfaction for business sustainability. With the emergence of the Industry 4.0 paradigm, product customization, which gives customers the means to personalized products to meet their needs, has become a strategy to increase companies’ value. High-tech manufacturing firms are already diving deep into Industry 4.0 standards adopting innovative strategies to outstand themselves in the market, while small manufacturing plants are slow in embracing the digital transformation. The high cost involved in acquiring indispensable resources and the lack of expertise are some of the obstacles low-tech businesses face in endorsing this new paradigm. Inspired by the customization challenges of a small manufacturing plant, our main research contribution is to develop an effective adaptive customization platform that encodes the customization data history of a small manufacturing plant, from a static database, into a dynamic machine learning model to produce personalized products for their customers accurately. Our research improves customers’ experience by reducing the customization system’s complexity consisting of inputting several parameters to obtain personalized products to a single entry. The back-end of the platform uses powerful machine learning (ML) algorithms like extreme gradient boosting (XGBoost) and Random Forest (RF) ensemble learning to match a single customer input to the desired customized product category. Our research experiments convey insights, such as the best scenarios to use XGBoost over RF algorithms for regression problems with non-linear data. The excellent experimental results achieved on both machine learning models show the merits of this customization platform.

Hybrid depletion framework using mixed-fidelity transport solutions and substeps

An improved depletion coupling scheme is presented, employing reduced-order transport solutions at substeps between high-fidelity solutions. The purpose of the reduced-order solver is to quickly approximate how the one-group flux would change within the depletion interval. This method builds off existing substep methods, where smaller depletion intervals are used to better approximate reaction rates and material compositions. The proposed scheme relies on the use of reduced-order transport simulations at the substeps, allowing the new compositions to influence the scalar neutron flux in other materials, approaching a time-continuous model of reaction rates. The hybrid approach is achieved by coupling a Monte Carlo code to a perturbation-theory-based reduced-order solver in a custom framework. The results demonstrate that the reduced-order solutions provide increased stability compared to the standard predictor time integration scheme, as well as higher order methods. This stability translates to increased accuracy for modeling problems where stability is an issue.

PMC

Deep learning models have been deployed to a wide range of edge devices. Since the data distribution on edge devices may differ from the cloud where the model was trained, it is typically desirable to customize the model for each edge device to improve accuracy. However, such customization is hard because collecting data from edge devices is usually prohibited due to privacy concerns. In this paper, we propose PMC, a privacy-preserving model customization framework to effectively customize a CNN model from the cloud to edge devices without collecting raw data. Instead, we introduce a method to extract statistical information from the edge, which contains adequate domain-related knowledge for model customization. PMC uses Gaussian distribution parameters to describe the edge data distribution, reweights the cloud data based on the parameters, and uses the reweighted data to train a specialized model for the edge device. During this process, differential privacy can be enforced by adding computed noises to the Gaussian parameters. Experiments on public datasets show that PMC can improve model accuracy by a large margin through customization. Finally, a study on user-generated data demonstrates the effectiveness of PMC in real-world settings.

Blockchain-based customization towards decentralized consensus on product requirement, quality, and price

As product customization becomes increasingly complex, it calls for a new architecture to enhance collaborations among numerous stakeholders who unnecessarily trust each other. This paper presents a blockchain-based collaborative customization framework, in which, blockchain is exploited as computational infrastructure to moderate, maintain, and manage a decentralized consensus on customization. Collaborative customization is made more transparent by enabling stakeholders to broadcast data, more flexible by fluctuating customization price against requirement fulfillment, more efficient by automating transactions through smart contracts, and more traceable by chaining transactions to constitute product identity. A practical example is presented to apply the framework to elevator customization.

Rethinking the bottom of the pyramid: Towards a new marketing mix

The purpose of this study is to re-conceptualize the conventional marketing mix for Bottom of the Pyramid (BoP) markets and propose a revised framework by reorganizing the elements based on the customer perspective while retaining the principles of services marketing. Primary data was collected through a questionnaire with a sample size of 400 people from both urban and rural markets in the BoP. Findings indicate that the needs and perspective of the BoP members is distinct from the Middle of the Pyramid (MoP). Managers should consider this point while formulating marketing mix strategies for BoP markets. The present study is the first of its kind to present a revised marketing mix framework for customers in the BoP markets. The framework comprises five Ps, including personalization, product, place, the process of service delivery and price. Thus, a theoretical contribution is made in the context of service marketing and the BoP.

Analytical approach to digital channel performance optimization of mobile money transactions in emerging markets

Understanding marketing channel performance is a crucial and complex task for the mobile financial technology segment of the mobile industry in emerging markets. However, poor techniques and capabilities for channel optimization of the mobile money users across available channels by the service providers often undermine the performance of these channels. The research aims to develop a target selection and campaign optimization framework for mobile money customers along two channels of transactions. It is complemented by mapping the appropriate campaign techniques across digital and non-digital channels of mobile money transactions. The key analytical method is the combination of fuzzy c-means clustering and RFM algorithm for the target selection development through the usage logs of customers (n = 300) of a mobile service provider. The results indicated that fuzzy c-means clustering and RFM algorithm are efficient for target selection. Also, the mapping of clusters with the appropriate channel of transactions revealed that mobile money users’ transactions could be optimized along the digital channel. The analytic model’s output enables appropriate cross-selling and up-selling campaigns that optimize the service provider revenue from existing and new mobile money users within the customer base. The channel evaluation revealed mobile application channels to be a promising and future channel for mobile money transactions as smartphone penetration continues to grow in emerging mobile markets. That is a positive sign of the digital channel’s future potential for mobile money transactions in developing markets. Acknowledgment The authors wish to thank the University of Pecs under the Higher Education Institution Excellence Program of the Ministry of Innovation and Technology in Hungary within the framework of the 4th Thematic Program – “Enhancing the Role of Domestic Companies in the Re-industrialization of Hungary.”