Search results

This paper aims to propose a machine learning-based automatic labeling methodology for chemical tanker activities that can be applied to any port with any number of active tankers and the identification of important predictors. The methodology can be applied to any type of activity tracking that is based on automatically generated geospatial data.

The proposed methodology uses three machine learning algorithms (artificial neural networks, support vector machines (SVMs) and random forest) along with information fusion (IF)-based sensitivity analysis to classify chemical tanker activities. The data set is split into training and test data based on vessels, with two vessels in the training data and one in the test data set. Important predictors were identified using a receiver operating characteristic comparative approach, and overall variable importance was calculated using IF from the top models.

Results show that an SVM model has the best balance between sensitivity and specificity, at 93.5% and 91.4%, respectively. Speed, acceleration and change in the course on the ground for the vessels are identified as the most important predictors for classifying vessel activity.

The study evaluates the vessel movements waiting between different terminals in the same port, but not their movements between different ports for their tank-cleaning activities.

The findings in this study can be used by port authorities, shipping companies, vessel operators and other stakeholders for decision support, performance tracking, as well as for automated alerts.

This analysis makes original contributions to the existing literature by defining and demonstrating a methodology that can automatically label vehicle activity based on location data and identify certain characteristics of the activity by finding important location-based predictors that effectively classify the activity status.

We propose a machine learning based methodology to deal with data collected from a mobile application asking users their opinion regarding fashion products. Based on different machine learning techniques, the proposed approach relies on the data value chain principle to enrich data into knowledge, insights and learning experience.

Online interaction and the usage of social media have dramatically altered both consumers’ behaviors and business practices. Companies invest in social media platforms and digital marketing in order to increase their brand awareness and boost their sales. Especially for fashion retailers, understanding consumers’ behavior before launching a new collection is crucial to reduce overstock situations. In this study, we aim at providing retailers better understand consumers’ different assessments of newly introduced products.

By creating new product-related and user-related attributes, the proposed prediction model attends an average of 70.15% accuracy when evaluating the potential success of new future products during the design process of the collection. Results showed that by harnessing artificial intelligence techniques, along with social media data and mobile apps, new ways of interacting with clients and understanding their preferences are established.

From a practical point of view, the proposed approach helps businesses better target their marketing campaigns, localize their potential clients and adjust manufactured quantities.

The originality of the proposed approach lies in (1) the implementation of the data value chain principle to enhance the information of raw data collected from mobile apps and improve the prediction model performances, and (2) the combination consumer and product attributes to provide an accurate prediction of new fashion, products.

This article revisits some theories and concepts of public administration, including those related to public value, transaction costs and social equity, to analyze the advantages and disadvantages of using artificial intelligence (AI) algorithms in public service delivery. The author seeks to mobilize theory to guide AI-era public management practitioners and researchers.

The author uses an existing task classification model to mobilize and juxtapose public management theories against artificial intelligence potential impacts in public service delivery. Theories of social equity and transaction costs as well as some concepts such as red tape, efficiency and economy are used to argue that the discipline of public administration provides a foundation to ensure algorithms are used in a way that improves service delivery.

After presenting literature on the challenges and promises of using AI in public service, the study shows that while the adoption of algorithms in public service has benefits, some serious challenges still exist when looked at under the lenses of theory. Additionally, the author mobilizes the public administration concepts of agenda setting and coproduction and finds that designing AI-enabled public services should be centered on citizens who are not mere customers. As an implication for public management practice, this study shows that bringing citizens to the forefront of designing and implementing AI-delivered services is key to reducing the reproduction of social biases.

As a fast-growing subject, artificial intelligence research in public management is yet to empirically test some of the theories that the study presented.

The paper vulgarizes some theories of public administration which practitioners can consider in the design and implementation of AI-enabled public services. Additionally, the study shows practitioners that bringing citizens to the forefront of designing and implementing AI-delivered services is key to reducing the reproduction of social biases.

The paper informs a broad audience who might not be familiar with public administration theories and how those theories can be taken into consideration when adopting AI systems in service delivery.

This research is original, as, to the best of the author’s knowledge, no prior work has combined these concepts in analyzing AI in the public sector.

The current natural language processing algorithms are still lacking in judgment criteria, and these approaches often require deep knowledge of political or social contexts. Seeing the damage done by the spreading of fake news in various sectors have attracted the attention of several low-level regional communities. However, such methods are widely developed for English language and low-resource languages remain unfocused. This study aims to provide analysis of Hindi fake news and develop a referral system with advanced techniques to identify fake news in Hindi.

The technique deployed in this model uses bidirectional long short-term memory (B-LSTM) as compared with other models like naïve bayes, logistic regression, random forest, support vector machine, decision tree classifier, kth nearest neighbor, gated recurrent unit and long short-term models.

The deep learning model such as B-LSTM yields an accuracy of 95.01%.

This study anticipates that this model will be a beneficial resource for building technologies to prevent the spreading of fake news and contribute to research with low resource languages.

The construction industry is a crucial industry for national development worldwide. Because the construction industry is tied to national and international economic activities, the COVID-19 outbreak has limited construction projects. Therefore, this study investigates the most influential factors regarding COVID-19 and their effects on the construction industry.

The potential impacts of COVID-19 on the construction industry were identified through a realistic literature review and interviews with professionals. A questionnaire was distributed via e-mail to architects, civil engineers and contractors who play vital roles during the construction processes. The data were analysed using SPSS 22 and LISREL 8.7 software to quantify the most influential pandemic-related factors faced by the construction industry.

Ten influential pandemic factors affecting the construction industry in Turkey were identified. Among them, “increased costs and price escalations due to shortage of raw materials and supply chain disruption” and “challenges with payment and cash flows” were determined as the most influential pandemic factors.

This research aims to advance comprehension of pandemic impacts and contributes an incipient assessment framework based on 10 determined pandemic factors. Therefore, contractors, architects and civil engineers may analyse their weaknesses and organise precise priorities so that their firms may remain competitive, thus minimising the adverse impact of COVID-19 and possible forthcoming waves.

Few studies have identified the effect of pandemics on the construction industry qualitatively, forcing management to make projections to the current situation. Moreover, no study has provided insights into the influential factors of pandemics using quantitative methods. Therefore, this study comprehensively and quantitatively determines the relevant COVID-19 pandemic factors using exploratory factor analysis (EFA) and utilises confirmatory factor analysis (CFA) and structural equation modelling to present a structural model of how pandemic factors affect the Turkish construction industry.

The purpose of this paper is to handle the anaphors through anaphora resolution in aspect-oriented sentiment analysis. Sentiment analysis is one of the predictive analytics of social media. In particular, the social media platform Twitter is an open platform to post the opinion by subscribers on contextual issues, events, products, individuals and organizations.

The sentiment polarity assessment is not deterministic to conclude the opinion of the target audience unless the polarity is assessed under diversified aspects. Hence, the aspect-oriented sentiment polarity assessment is a crucial objective of the opinion assessment over social media. However, the aspect-oriented sentiment polarity assessment often influences by the curse of anaphora resolution.

Focusing on these limitations, a scale to estimate the aspects oriented sentiment polarity under anaphors influence has been portrayed in this article. To assess the aspect-based sentiment polarity of the tweets, the anaphors of the tweets have been considered to assess the weightage of the tweets toward the sentiment polarity.

The experimental study presents the performance of the proposed model by comparing it with the contemporary models, which are estimating the sentiment polarity tweets under anaphors impact.

This study examines the economic crisis caused by coronavirus on the global tourism industry in general and the Indian tourism industry in particular. This paper highlights the strategies that tourism companies should implement in times of crisis to reduce the negative impact. It also discovers the business opportunities which can be offered amid this deadly pandemic.

The study is based on a systematic literature review. The literature has been explored by utilizing the keywords “economic crises,” “coronavirus,” “Indian tourism industry,” “Global tourism industry” on the three most popular databases namely Scopus, Web of Science and Google Scholar. In this study, statistics, current events, published research papers and a synthesis of news transmitted by various media sources were used to assess the economic crisis caused by coronavirus.

The obtained findings demonstrate that coronavirus severely affected the economy of the world and India. The pandemic has hit the economies that are dependent on tourism the worst. These countries are expected to bear the brunt of the crisis's consequences for longer than other economies. This coronavirus outbreak indicates that the tourism industry was unprepared to deal with such a pandemic, which affected and crippled the economy.

This study demonstrates economic crisis, management strategies and business opportunities during any crisis, chaos and disaster, in addition to its academic contribution to the existing body of the literature. Policymakers and industry practitioners might be offered suggestions based on the findings of current study to design futuristic strategies for better economic crisis management. The data given in this study is timely because taking an exact idea of tourism losses through the data is difficult, as the data changes as quickly as the virus spreads.

This paper forms its originality by concentrating on the aspects of economic crisis, strategies to mitigate the negative impact of coronavirus on the tourism economy and detailing the business opportunities which these crises can offer. This paper provides an evaluation of the current status of the tourism economy of the world and India as well.

The authors develop a methodology to select appropriate sustainable supply chain indicators (SSCIs) to measure Sustainable Development Goals (SDGs) in the global supply chain.

SSCIs are identified by reviewing the extant literature and topic modeling. Further, they are evaluated based on existing SDGs and ranked using the fuzzy technique for order preference by similarity to ideal solution (TOPSIS) method. Notably, the evaluation of indicators is a multi-criteria decision-making (MCDM) process within a fuzzy environment. The methodology has been explained using a case study from the automobile industry.

The case study identifies appropriate SSCIs and differentiates them among peer suppliers for gaining a competitive advantage. The results reveal that top-ranked sustainability indicators include the management of natural resources, energy, greenhouse gas (GHG) emissions and social investment.

The study outcome will enable suppliers, specialists and decision makers to understand the criteria that improve supply chain sustainability in the automobile industry. The analysis provides a comprehensive understanding of the competitive package of indicators for gaining strategic advantage. This proactive sustainability indicator selection promotes and enhances sustainability reporting while fulfilling regulatory requirements and increasing collaboration potential with trustworthy downstream partners. This study sets the stage for further research in SSCIs’ competitive strategy in the automobile industry along with its supply chains.

This study is unique as it provides a framework for determining relevant SSCIs, which can be distinguished from peer suppliers, while also matching economic, environmental and social metrics to achieve a competitive advantage.

The purpose of this paper is to propose and develop PA2200-based composite powder containing 0-15 Wt.% magnesium oxide before directly using it in selective laser sintering (SLS) machine to produce end-use products for low-volume production in the engineering applications with keen focus to meet the functional requirements which rely on material properties.

The methodology reported emphasises PA2200-based composite powder containing 0-15 Wt.% magnesium oxide development for SLS process which starts with preparation and characterisation of composite material, thermal and rheological study of composite material to decide optimum process parameters for SLS process machine to get optimal part properties. Further, to verify composite material properties, a conventional casting methodology is used. The composition of composite materials those possessing good properties are further selected for processing in SLS process under optimal processing parameters.

The process parameters of SLS machine are material-dependent. The effect of temperature in X-ray diffraction profile is negligible in the case of magnesium oxide reinforced PA2200 composite material. The cyclic heating of material increases melting point temperature, this grounds to modify part bed temperature of material every time before processing on SLS machine to uphold build part properties, as well as material. With the rise in temperature, the Melt flow index and rheological property of materials change. The magnesium oxide reinforced PA2200 composite material has high thermal stability than pure PA2200 material. By the addition of small quantity of magnesium oxide, most of the mechanical property and flammability property improves while elongation at break (percentage) decreases significantly.

The proposed PA2200-based composite powder containing 0-15 Wt.% magnesium oxide material development system and casting metrology to verify developed material properties will be very useful to develop new composite material for SLS process with use of less material. The developed methodology has proven, especially in the case where non-experts or student need to develop composite material for SLS process according to the property requirement of applications.

Unlike earlier composite material development methodology, the projected methodology of polymer-based composite material and confirmation of material properties instead of commencing SLS process provides straight forward means for SLS process composite materials development with less use of the material and period of time.

The corona virus disease 2019 (COVID-19) pandemic had devastating impact on sporting activities, education and global health. Given the impact of the pandemic-related restrictions and closed fitness centers and other sports facilities, the coping strategies adopted by athletes while training at home to continue their training remain an important question. The purpose of this review is to examine the findings of key studies focusing on the impact of the pandemic on sport training.

A review was conducted on Google Scholar, Scopus and PubMed to identify articles on physical activity and sport training during the COVID-19 pandemic. Eligibility criteria included peer-reviewed empirical and quantitative studies. The selected articles were reviewed using contextual analysis.

The COVID-19 pandemic had devastating impact on sports activities globally. Studies evaluating the influence of the pandemic on sports training have revealed abysmal decline in training volume and general physical fitness, limited access to facilities and equipment and significant reduction in training load. The damage of the pandemic on the sporting world should serve as a guide for proactive steps that should be taken to prevent recurrence of a similar calamity.

This paper highlights important lessons to be learned from the lockdown imposed by the COVID-19 pandemic by stakeholders in sport, including the importance of improvisation of sports facilities by utilizing available spaces at home and neighborhood for physical training.