Search results

As the number of web applications is increasing day by day web mining acts as an important tool to extract useful information from weblogs and analyse them according to the attributes and predict the usage of a website. The main aim of this paper is to inspect how process mining can be used to predict the web usability of hotel booking sites based on the number of users on each page, and the time of stay of each user. Through this paper, the authors analyse the web usability of a website through process mining by finding the web usability metrics. This work proposes an approach to finding the usage of a website using the attributes available in the weblog which predicts the actual footfall on a website.

PROM (Process Mining tool) is used for the analysis of the event log of a hotel booking site. In this work, authors have used a case study to apply the PROM (process mining tool) to pre-process the event log dataset for analysis to discover better-structured process maps than without pre-processing.

This article first provided an overview of process mining, then focused on web mining and later discussed process mining techniques. It also described different target languages: system nets (i.e. Petri nets with an initial and a final state), inductive miner and heuristic miner, graphs showing the change in behaviour of the dataset and predicting the outcome, that is the webpage having the maximum number of hits.

In this work, a case study has been used to apply the PROM (process mining tool) to pre-process the event log dataset for analysis to discover better-structured process maps than without pre-processing.

Recognising the as-built state of construction elements is crucial for construction progress monitoring. Construction scholars have used computer vision-based algorithms to automate this process. Robust object recognition from indoor site images has been inhibited by technical challenges related to indoor objects, lighting conditions and camera positioning. Compared with traditional machine learning algorithms, one-stage detector deep learning (DL) algorithms can prioritise the inference speed, enable real-time accurate object detection and classification. This study aims to present a DL-based approach to facilitate the as-built state recognition of indoor construction works.

The one-stage DL-based approach was built upon YOLO version 4 (YOLOv4) algorithm using transfer learning with few hyperparameters customised and trained in the Google Colab virtual machine. The process of framing, insulation and drywall installation of indoor partitions was selected as the as-built scenario. For training, images were captured from two indoor sites with publicly available online images.

The DL model reported a best-trained weight with a mean average precision of 92% and an average loss of 0.83. Compared to previous studies, the automation level of this study is high due to the use of fixed time-lapse cameras for data collection and zero manual intervention from the pre-processing algorithms to enhance visual quality of indoor images.

This study extends the application of DL models for recognising as-built state of indoor construction works upon providing training images. Presenting a workflow on training DL models in a virtual machine platform by reducing the computational complexities associated with DL models is also materialised.

This study aims to develop a machine learning model to detect structure fire fatalities using a dataset comprising 11,341 cases from 2011 to 2019.

Exploratory data analysis (EDA) was conducted prior to modelling, in which ten machine learning models were experimented with.

The main fatal structure fire risk factors were fires originating from bedrooms, living areas and the cooking/dining areas. The highest fatality rate (20.69%) was reported for fires ignited due to bedding (23.43%), despite a low fire incident rate (3.50%). Using 21 structure fire features, Random Forest (RF) yielded the best detection performance with 86% accuracy, followed by Decision Tree (DT) with bagging (accuracy = 84.7%).

Limitations of the study are pertaining to data quality and grouping of categories in the data pre-processing stage, which could affect the performance of the models.

The study is the first of its kind to manipulate risk factors to detect fatal structure classification, particularly focussing on structure fire fatalities. Most of the previous studies examined the importance of fire risk factors and their relationship to the fire risk level.

Sharing and obtaining information over social media has enabled people to express their opinions regarding any event. Since the tweets regarding the Russia-Ukraine war were extensively publicized on social media, this study aims to analyse the temporal sentiments people express through tweets related to the war.

Relevant hashtag related to the Russia-Ukraine war was identified, and tweets were downloaded using Twitter API, which were later migrated to Orange Data mining software. Pre-processing techniques like transformation, tokenization, and filtering were applied to the extracted tweets. VADER (Valence Aware Dictionary for Sentiment Reasoning) sentiment analysis module of Orange software was used to categorize tweets into positive, negative and neutral ones based on the tweet polarity. For ascertaining the key and co-occurring terms and phrases in tweets and also to visualize the keyword clusters, VOSviewer, a data visualization software, was made use of.

An increase in the number of tweets is witnessed in the initial days, while a decline is observed over time. Most tweets are negative in nature, followed by positive and neutral ones. It is also ascertained that tweets from verified accounts are more impactful than unverified ones. russiaukrainewar, ukraine, russia, false, war, nato, zelensky and stoprussia are the dominant co-occurring keywords. Ukraine, Russia and Putin are the top hashtags for sentiment representation. India, the USA and the UK contribute the highest tweets.

The study tries to explore the public sentiments expressed over Twitter related to Russia-Ukraine war.

The current gap between the required and available artificial intelligence (AI) professionals poses significant challenges for organisations and academia. Organisations are challenged to identify and secure the appropriate AI competencies. Simultaneously, academia is challenged to design, offer and quickly scale academic programmes in line with industry needs and train new generations of AI professionals. Therefore, identifying and structuring AI competencies is necessary to effectively overcome the AI competence shortage.

A probabilistic topic model was applied to explore the AI competence categories empirically. The authors analysed 1159 AI-related online job ads published on LinkedIn.

The authors identified five predominant competence categories: (1) Data Science, (2) AI Software Development, (3) AI Product Development and Management, (4) AI Client Servicing, and (5) AI Research. These five competence categories were summarised under the developed AI competence framework.

The AI competence framework contributes to clarifying and structuring the diverse AI landscape. These findings have the potential to aid various stakeholders involved in the process of training, recruiting and selecting AI professionals. They may guide organisations in constructing a complementary portfolio of AI competencies by helping users match the right competence requirements with an organisation's needs and business objectives. Similarly, they can support academia in designing academic programmes aligned with industry needs. Furthermore, while focusing on AI, this study contributes to the research stream of information technology (IT) competencies.

The present study aims to evaluate the effect of climate change on the flood hazard potential in the Kelantan River Basin using current and future scenarios.

The intensity-duration-frequency (IDF) was used to estimate the current 50- and 100-year return period 24-h design rainfall, and the climate change factor (CCF) was used to compute the future design rainfall. The CCF was calculated from the rainfall projections of two global climate models, CGCM1 and CCSM3, with different pre-processing steps applied to each. The IDF data were used in the rainfall-runoff-inundation model to simulate current and future flood inundation scenarios.

The estimated CCF values demonstrate a contrast, whereby each station had a CCF value greater than one for CGCM1, while some stations had a CCF value of less than one for CCSM3. Therefore, CGCM1 projected an aggravation and CCSM3 a reduction of flood hazard for future scenarios. The study reveals that topography plays an essential role in calculating the CCF.

To the best of the author’s knowledge, this is the first study to examine flood projections in the Kelantan River Basin. It is, therefore, hoped that these results could benefit local managers and authorities by enabling them to make informed decisions regarding flood risk mitigation in a climate change scenario.

A new research domain known as the Quantified Self has recently emerged and is described as gaining self-knowledge through using wearable technology to acquire information on self-monitoring activities and physical health related problems. However, very little is known about the impact of time window models on discovering self-quantified patterns that can yield new self-knowledge insights. This paper aims to discover the self-quantified patterns using multi-time window models.

This paper proposes a multi-time window analytical workflow developed to support the streaming k-means clustering algorithm, based on an online/offline approach that combines both sliding and damped time window models. An intervention experiment with 15 participants is used to gather Fitbit data logs and implement the proposed analytical workflow.

The clustering results reveal the impact of a time window model has on exploring the evolution of micro-clusters and the labelling of macro-clusters to accurately explain regular and irregular individual physical behaviour.

The preliminary results demonstrate the impact they have on finding meaningful patterns.

Machine learning (ML), and deep learning in particular, is gaining traction across a myriad of real-life applications. Portfolio management is no exception. This paper provides a systematic literature review of deep learning applications for portfolio management. The findings are likely to be valuable for industry practitioners and researchers alike, experimenting with novel portfolio management approaches and furthering investment management practice.

This review follows the guidance and methodology of Linnenluecke et al. (2020), Massaro et al. (2016) and Fisch and Block (2018) to first identify relevant literature based on an appropriately developed search phrase, filter the resultant set of publications and present descriptive and analytical findings of the research itself and its metadata.

The authors find a strong dominance of reinforcement learning algorithms applied to the field, given their through-time portfolio management capabilities. Other well-known deep learning models, such as convolutional neural network (CNN) and recurrent neural network (RNN) and its derivatives, have shown to be well-suited for time-series forecasting. Most recently, the number of papers published in the field has been increasing, potentially driven by computational advances, hardware accessibility and data availability. The review shows several promising applications and identifies future research opportunities, including better balance on the risk-reward spectrum, novel ways to reduce data dimensionality and pre-process the inputs, stronger focus on direct weights generation, novel deep learning architectures and consistent data choices.

Several systematic reviews have been conducted with a broader focus of ML applications in finance. However, to the best of the authors’ knowledge, this is the first review to focus on deep learning architectures and their applications in the investment portfolio management problem. The review also presents a novel universal taxonomy of models used.

The set of 2,509 documents related to the human-centric aspect of manufacturing were retrieved from Scopus database and systmatically analyzed. Using an unsupervised machine learning approach based on Latent Dirichlet Allocation we were able to identify latent topics related to human-centric aspect of Industry 5.0.

This study aims to create a scientific map of the human-centric aspect of manufacturing and thus provide a systematic framework for further research development of Industry 5.0.

In this study a 140 unique research topics were identified, 19 of which had sufficient research impact and research interest so that we could mark them as the most significant. In addition to the most significant topics, this study contains a detailed analysis of their development and points out their connections.

Industry 5.0 has three pillars – human-centric, sustainable, and resilient. The sustainable and resilient aspect of manufacturing has been the subject of many studies in the past. The human-centric aspect of such a systematic description and deep analysis of latent topics is currently just passing through.

Sustainable human resource management (SuHRM), which aims to achieve positive environmental, social and economic outcomes at the same time, has gained prominence across industries. However, the challenges of implementing SuHRM across industries are largely under-studied. The purpose of this study is to identify the grey areas in the field of SuHRM by using an unsupervised learning algorithm on the abstracts of 607 papers published in prominent journals from 1995 to 2023. Most of the articles have been published post-2018.

The analysis of the data (abstracts of the selected articles) has been done using topic modelling via latent Dirichlet algorithm (LDA).

The output from topic modelling-LDA reveals nine primary focus areas of SuHRM research – the link between SuHRM and employee well-being; job satisfaction; challenges of implementing SuHRM; exploring new horizons in SuHRM; reaping the benefits of using SuHRM as a strategic tool; green HRM practices; link between SuHRM and organisational performance; link between corporate social responsible and HRM.

The insights gained from this study along with the discussions on each topic will be extremely beneficial for researchers, academicians, journal editors and practitioners to channelise their research focus. No other study has used a smart algorithm to identify the research clusters of SuHRM.

By utilizing topic modeling techniques, the study offers a novel approach to analyzing and understanding trends and patterns in HRM research related to sustainability. The significance of the paper would be in its potential to shed light on emerging areas of interest and provide valuable implications for future research and practice in Sustainable HRM.