A Systems Study on Interprofessional Collaboration in Healthcare

This study aims to translate and adapt the Assessment of Interprofessional Team Collaboration Scale II (AITCS-II) cross-culturally for effective and systemic use in Japan, to describe floor and ceiling values, and to examine in terms of such criteria as reliability and face and content validity. The AITCS-II was translated from English into Japanese to develop the Japanese version of the Assessment of Interprofessional Team Collaboration Scale II (hereinafter referred to AITCS-II-J). Then, cross-sectional and cross-professional data analyses were carried out to seek evidence of construct validity. Analysis demonstrated good content and face validity. With a Cronbach's alpha coefficient greater than 0.9 (r varied from 0.912 to 0.940), the AITCS-II-J exhibited excellent internal consistency. The AITCS-II-J showed evidence of acceptable validity and reliability; therefore, this measurement system will be useful for informing the enhancement of interprofessional team collaboration within the Japanese acute healthcare context.

A State-of-the-Art Survey on Context-Aware Recommender Systems and Applications

In the digital transformation era, increasingly more individuals and organizations use or create services in digital spaces. Many business transactions have been moving from the offline to online mode. For example, sellers intend to introduce their products on e-commerce platforms rather than display them on store shelves as in traditional business. Although this new format business has advantages, such as more space for product displays, more efficient searches for a specific item, and providing a good tool for both buyers and sellers to manage their products, it is also accompanied by the obviously important problem that users are confused when choosing an appropriate item due to a large amount of information. For this reason, the need for a recommendation system appears. Informally, a recommender system is similar to an information filtering system that helps identify a set of items that best satisfy users' demands based on their preference profiles. The integration of contextual information (e.g., location, weather conditions, and user's mood) into recommender systems to improve their performance has recently received considerable attention in the research literature. However, incorporating such contextual information into recommendation models is a challenging task because of the increase in both the dimensionality and sparsity of the model. Different approaches with their own advantages and disadvantages have been proposed. This paper provides a comprehensive survey on context-aware recommender systems in recent years. In particular, the authors pay more attention to journal and conference proceedings papers published from 2016 to 2020. In addition, this paper also presents open issues for context-aware recommender systems and discuss promising directions for future research.

A Methodology of Task Allocation to Design a Human-Robot Assembly Line

There are successful cases in lean manual assembly lines; however, in some cases, such as the ease of assembly in quicker cycle time, the designs are not satisfactory and must be transformed to semi-automation. This research studies human-robot task allocation when designing for semi-automation considering not only time-cost effectiveness as in the existing research but also assembly difficulty and ergonomic issues. A proposed methodology optimally determines what tasks should be performed by humans or robots, at which station, and in what sequence. A multi-objective linear programming (MOLP) model is proposed to simultaneously minimize total operating cost, cycle time, and ergonomic difficulty. Solving the model has two approaches: with and without optimal weights. The methodology is applied to a Lego-car assembly line. To illustrate the benefits of the proposed MOLP, a comparison between it and three single-objective models is made. Results show that the optimal-weight MOLP yields a better performance (a shorter cycle time, a lower cost, and especially, a significant ergonomic improvement) when compared to the other MOLP and single-objective models.

Hybrid Simulation-Based Optimization for Production Planning of a Dedicated Remanufacturing System

This paper presents a comparative simulation study of a dedicated remanufacturing system. The production line of a dedicated remanufacturing system producing multiple products under uncertain environment is improved through the simulation-based optimization approach. Appropriate inventory capacity of buffers, a proper switching rule, and a suitable run size of each product should be optimally set to yield the highest system's profit. Then, hybrid simulation-based optimization algorithms with two hybrid optimization forms using a Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) as complementary to each other in relation to their standard algorithms are proposed and compared. A case study is used to demonstrate and compare the performances among the algorithms to show the advantages of the proposed algorithms. This approach can assist in decision making for the planning and management of dedicated remanufacturing systems that are required to operate with various decision variables under uncertainties.

Optimizing Inventory Classification and Service Levels Under Budget and Warehouse Space Control

There are several techniques of inventory classification and prioritization based on a single criteria, bi-criteria, or multiple criteria; however, managing inventory can fail when trying to fit inventory classes into the operating budget and available warehouse space. This research focuses on optimizing inventory classes and determining an optimal service level of each class while simultaneously satisfying operating budget and space constraints. The idea is to help decision makers to effectively rank and group SKUs and manage them within the constraints while satisfying customers. This proposed methodology is an optimality-based approach that uses mixed integer linear programing to solve the problem. Computational experiments are conducted to illustrate the proposed method. Results are compared with a classical ABC inventory analysis.

Learning Pattern Relation-Based Hyperbolic Embedding for Adverse Drug Reaction Extraction

Hyperbolic embedding has been recently developed to allow us to embed words in a Cartesian product of hyperbolic spaces, and its efficiency has been proved in several works of literature since the hierarchical structure is the natural form of texts. Such a hierarchical structure exhibits not only the syntactic structure but also semantic representation. This paper presents an approach to learn meaningful patterns by hyperbolic embedding and then extract adverse drug reactions from electronic medical records. In the experiments, the public source of data from MIMIC-III (Medical Information Mart for Intensive Care III) with over 58,000 observed hospital admissions of the brief hospital course section is used, and the result shows that the approach can construct a set of efficient word embeddings and also retrieve texts of the same relation type with the input. With the Poincaré embeddings model and its vector sum (PC-S), the authors obtain up to 82.3% in the precision at ten, 85.7% in the mean average precision, and 93.6% in the normalized discounted cumulative gain.

An Association Rule Mining Approach to Discover Demand and Supply Patterns Based on Thai Social Media Data

In the digital age, social media technology has an important role as a communication platform for interpersonal interactions in the online virtual world. In addition, social media has impacted product exchange behavior in both vendors and buyers, with a shift from the traditional sales model to communication between parties via social media. Social media marketing, an online means of buying, selling, and exchanging goods and services, is increasingly popular due to convenience, speed, and greater choices. This trend has grown rapidly and is set to expand, leading to increased interest in research which analyzes and processes social media marketing data to gain a new integrated body of knowledge to better serve online business transactions. This research covers a new field, which may cause research and development limitations requiring background knowledge in several areas, such as digital technology, data analytics, and business analysis. This research aims to develop a framework to search for association rule mining of demand and supply data on social media platforms. Data is collected from Twitter and underwent cleansing and labeling for separating into five groups. Hashtag data from tweets is then extracted and transformed to input attributes of the framework. Next, association rule mining is performed using the Apriori algorithm in order to determine frequent items and extract candidate association rules. The last stage is rule selection, which uses Twitter-specific statistical attributes, that is, number of retweets and likes, to select highly effective association rules. The findings are that it is possible to mine association rules relating to demand and supply on Twitter. Based on an analysis of the association rule results, the content of those rules reflects trending activities and events at different times. Such information can be analyzed in further research to design improvements in social media marketing.

Special Children Behaviour Pattern and Their Teaching Strategies

Every child is unique and has some different qualities. Special children have their own strengths and weaknesses which defines their interests. Their development progresses are quite slow as compared to normal children. However, the parents should carefully observe if the children have difficulties in one or more developmental areas, notice their performance as compared with other children of the same age. There are various methods available to analyze the behavior of children, but all mothers may not be able to recognize the real problem and hence not able to teach them so. The paper describes various case studies of children suffering from behavioral disorder. The behavior patterns of children are recognize by analyzing all behavioral aspects with the help of images, videos, and questionnaires and help parents and teachers by suggesting teaching strategies for their bright future. Assessment techniques defined by teachers and doctors to educate the children are also discussed. This study will be very helpful to society, especially those with a special child.

A Novel Approach for Determining Shelter Location-Allocation in Humanitarian Relief Logistics

This study proposes a methodology that integrates the epsilon constraint method (EC) and artificial neural network (ANN) to determine shelter location-allocation. Since shelter location-allocation is a critical part of disaster response stage, fast decision-making is very important. A multi-objective optimization model is formulated to simultaneously minimize total cost and minimize total evacuation time. The proposed model is solved by EC because it generates the optimal solutions without intervention of decision-makers during the solution process. However, EC requires intensive computational time, especially when dealing with large-scale data. Thus, ANN is combined with EC to facilitate prompt decision-making and address the complexity. Herein, ANN is supervised by the optimal solutions generated by EC. The applicability of the proposed methodology is demonstrated through a case study of shelter allocation in response to flooding in Surat Thani, Thailand. It is plausible to use this proposed methodology to improve disaster response for the benefit of victims and decision-makers.

A Multi-Objective Approach to Big Data View Materialization

Big data comprises voluminous and heterogeneous data that has a limited level of trustworthiness. This data is used to generate valuable information that can be used for decision making. However, decision making queries on Big data consume a lot of time for processing resulting in higher response times. For effective and efficient decision making, this response time needs to be reduced. View materialization has been used successfully to reduce the query response time in the context of a data warehouse. Selection of such views is a complex problem vis-à-vis Big data and is the focus of this paper. In this paper, the Big data view selection problem is formulated as a bi-objective optimization problem with the two objectives being the minimization of the query evaluation cost and the minimization of the update processing cost. Accordingly, a Big data view selection algorithm that selects Big data views for a given query workload, using the vector evaluated genetic algorithm, is proposed. The proposed algorithm aims to generate views that are able to reduce the response time of decision-making queries.