Applied Sciences

Editorial

Jump to: Research, Review

3 pages, 196 KiB

Open AccessEditorial

Applications of Data Science and Artificial Intelligence

by Carlos J. Costa and Manuela Aparicio

Appl. Sci. 2023, 13(15), 9015; https://doi.org/10.3390/app13159015 - 7 Aug 2023

Cited by 5 | Viewed by 3952

Abstract

A series of waves have marked the history of artificial intelligence (AI) [...] Full article

(This article belongs to the Special Issue Applications of Data Science and Artificial Intelligence)

Research

Jump to: Editorial, Review

27 pages, 12866 KiB

Open AccessArticle

Multimodal Augmented Reality System for Real-Time Roof Type Recognition and Visualization on Mobile Devices

by Bartosz Kubicki, Artur Janowski and Adam Inglot

Appl. Sci. 2025, 15(3), 1330; https://doi.org/10.3390/app15031330 - 27 Jan 2025

Cited by 1 | Viewed by 926

Abstract

The utilization of augmented reality (AR) is becoming increasingly prevalent in the integration of virtual reality (VR) elements into the tangible reality of the physical world. It facilitates a more straightforward comprehension of the interconnections, interdependencies, and spatial context of data. Furthermore, the [...] Read more.

The utilization of augmented reality (AR) is becoming increasingly prevalent in the integration of virtual reality (VR) elements into the tangible reality of the physical world. It facilitates a more straightforward comprehension of the interconnections, interdependencies, and spatial context of data. Furthermore, the presentation of analyses and the combination of spatial data with annotated data are facilitated. This is particularly evident in the context of mobile applications, where the combination of real-world and virtual imagery facilitates enhances visualization. This paper presents a proposal for the development of a multimodal system that is capable of identifying roof types in real time and visualizing them in AR on mobile devices. The current approach to roof identification is based on data made available by public administrations in an open-source format, including orthophotos and building contours. Existing computer processing technologies have been employed to generate objects representing the shapes of building masses, and in particular, the shape of roofs, in three-dimensional (3D) space. The system integrates real-time data obtained from multiple sources and is based on a mobile application that enables the precise positioning and detection of the recipient’s viewing direction (pose estimation) in real time. The data were integrated and processed in a Docker container system, which ensured the scalability and security of the solution. The multimodality of the system is designed to enhance the user’s perception of the space and facilitate a more nuanced interpretation of its intricacies. In its present iteration, the system facilitates the extraction and classification/generalization of two categories of roof types (gable and other) from aerial imagery through the utilization of deep learning methodologies. The outcomes achieved suggest considerable promise for the advancement and deployment of the system in domains pertaining to architecture, urban planning, and civil engineering. Full article

(This article belongs to the Special Issue Applications of Data Science and Artificial Intelligence)

► Show Figures

Figure 1

20 pages, 1363 KiB

Open AccessArticle

Time Series Methods and Business Intelligent Tools for Budget Planning—Case Study

by Katarzyna Grobler-Dębska, Rafał Mularczyk, Bartłomiej Gawęda and Edyta Kucharska

Appl. Sci. 2025, 15(1), 287; https://doi.org/10.3390/app15010287 - 31 Dec 2024

Viewed by 1690

Abstract

Corporate budget planning involves forecasting expenses and revenues to support strategic goals, resource allocation, and supply chain coordination. Regular updates to forecasts and collaboration across organizational levels ensure adaptability to changing business conditions. Long-term sales forecasts form the foundation for budgeting, guiding resource [...] Read more.

Corporate budget planning involves forecasting expenses and revenues to support strategic goals, resource allocation, and supply chain coordination. Regular updates to forecasts and collaboration across organizational levels ensure adaptability to changing business conditions. Long-term sales forecasts form the foundation for budgeting, guiding resource allocation and enhancing financial efficiency. The budgeting process in organizations is complex and requires data from various operational areas, which is collected over a representative period. Key inputs include quantitative sales data, direct costs indirect costs, and historical revenues and profitability, which are often sourced from ERP systems. While ERP systems typically provide tools for basic budgeting, they lack advanced capabilities for forecasting and simulation. We proposed a solution, which includes dynamic demand forecasting based on time series methods such as Build-in method in Power BI (which is ETS—exponential smoothing), linear regression, XGBoost, ARIMA and flexible product groupings, which are simulations for cost changes. The case study concerns a manufacturing company in the mass customization industry. The solution is designed to be intuitive and easily implemented in the business. Full article

(This article belongs to the Special Issue Applications of Data Science and Artificial Intelligence)

► Show Figures

Figure 1

21 pages, 4241 KiB

Open AccessArticle

MIPART: A Partial Decision Tree-Based Method for Multiple-Instance Classification

by Kadriye Filiz Balbal

Appl. Sci. 2024, 14(24), 11696; https://doi.org/10.3390/app142411696 - 14 Dec 2024

Viewed by 1143

Abstract

Multi-instance learning (MIL) is a critical area in machine learning, particularly for applications where data points are grouped into bags. Traditional methods, however, often face challenges in accurately classifying these bags. This paper presents the multi-instance partial decision tree (MIPART), a method that [...] Read more.

Multi-instance learning (MIL) is a critical area in machine learning, particularly for applications where data points are grouped into bags. Traditional methods, however, often face challenges in accurately classifying these bags. This paper presents the multi-instance partial decision tree (MIPART), a method that incorporates the partial decision tree (PART) algorithm within a Bagging framework, utilizing the simple multi-instance classifier (SimpleMI) as its base. MIPART was evaluated on 12 real-world multi-instance datasets using various performance metrics. Experimental results show that MIPART achieved an average accuracy of 84.27%, outperforming benchmarks in the literature. Notably, MIPART outperformed established methods such as Citation-KNN, MIBoost, MIEMDD, MILR, MISVM, and MITI, demonstrating a 15% improvement in average accuracy across the same datasets. The significance of these improvements was confirmed through rigorous non-parametric statistical tests, including Friedman aligned ranks and Wilcoxon signed-rank analyses. These findings suggest that the MIPART method is a significant advancement in multiple-instance classification, providing an effective tool for interpreting complex multi-instance datasets. Full article

(This article belongs to the Special Issue Applications of Data Science and Artificial Intelligence)

► Show Figures

Figure 1

43 pages, 4570 KiB

Open AccessArticle

Fine-Tuning Retrieval-Augmented Generation with an Auto-Regressive Language Model for Sentiment Analysis in Financial Reviews

by Miehleketo Mathebula, Abiodun Modupe and Vukosi Marivate

Appl. Sci. 2024, 14(23), 10782; https://doi.org/10.3390/app142310782 - 21 Nov 2024

Cited by 2 | Viewed by 3288

Abstract

Sentiment analysis is a well-known task that has been used to analyse customer feedback reviews and media headlines to detect the sentimental personality or polarisation of a given text. With the growth of social media and other online platforms, like Twitter (now branded [...] Read more.

Sentiment analysis is a well-known task that has been used to analyse customer feedback reviews and media headlines to detect the sentimental personality or polarisation of a given text. With the growth of social media and other online platforms, like Twitter (now branded as X), Facebook, blogs, and others, it has been used in the investment community to monitor customer feedback, reviews, and news headlines about financial institutions’ products and services to ensure business success and prioritise aspects of customer relationship management. Supervised learning algorithms have been popularly employed for this task, but the performance of these models has been compromised due to the brevity of the content and the presence of idiomatic expressions, sound imitations, and abbreviations. Additionally, the pre-training of a larger language model (PTLM) struggles to capture bidirectional contextual knowledge learnt through word dependency because the sentence-level representation fails to take broad features into account. We develop a novel structure called language feature extraction and adaptation for reviews (LFEAR), an advanced natural language model that amalgamates retrieval-augmented generation (RAG) with a conversation format for an auto-regressive fine-tuning model (ARFT). This helps to overcome the limitations of lexicon-based tools and the reliance on pre-defined sentiment lexicons, which may not fully capture the range of sentiments in natural language and address questions on various topics and tasks. LFEAR is fine-tuned on Hellopeter reviews that incorporate industry-specific contextual information retrieval to show resilience and flexibility for various tasks, including analysing sentiments in reviews of restaurants, movies, politics, and financial products. The proposed model achieved an average precision score of 98.45%, answer correctness of 93.85%, and context precision of 97.69% based on Retrieval-Augmented Generation Assessment (RAGAS) metrics. The LFEAR model is effective in conducting sentiment analysis across various domains due to its adaptability and scalable inference mechanism. It considers unique language characteristics and patterns in specific domains to ensure accurate sentiment annotation. This is particularly beneficial for individuals in the financial sector, such as investors and institutions, including those listed on the Johannesburg Stock Exchange (JSE), which is the primary stock exchange in South Africa and plays a significant role in the country’s financial market. Future initiatives will focus on incorporating a wider range of data sources and improving the system’s ability to express nuanced sentiments effectively, enhancing its usefulness in diverse real-world scenarios. Full article

(This article belongs to the Special Issue Applications of Data Science and Artificial Intelligence)

► Show Figures

Figure 1

19 pages, 3351 KiB

Open AccessArticle

Automatizing Automatic Controller Design Process: Designing Robust Automatic Controller under High-Amplitude Disturbances Using Particle Swarm Optimized Neural Network Controller

by Celal Onur Gökçe

Appl. Sci. 2024, 14(17), 7859; https://doi.org/10.3390/app14177859 - 4 Sep 2024

Cited by 1 | Viewed by 955

Abstract

In this study, a novel approach of designing automatic control systems with the help of AI tools is proposed. Given plant dynamics, expected references, and expected disturbances, the design of an optimal neural network-based controller is performed automatically. Several common reference types are [...] Read more.

In this study, a novel approach of designing automatic control systems with the help of AI tools is proposed. Given plant dynamics, expected references, and expected disturbances, the design of an optimal neural network-based controller is performed automatically. Several common reference types are studied including step, square, sine, sawtooth, and trapezoid functions. Expected reference–disturbance pairs are used to train the system for finding optimal neural network controller parameters. A separate test set is used to test the system for unexpected reference–disturbance pairs to show the generalization performance of the proposed system. Parameters of a real DC motor are used to test the proposed approach. The real DC motor’s parameters are estimated using a particle swarm optimization (PSO) algorithm. Initially, a proportional–integral (PI) controller is designed using a PSO algorithm to find the simple controller’s parameters optimally and automatically. Starting with the neural network equivalent of the optimal PI controller, the optimal neural network controller is designed using a PSO algorithm for training again. Simulations are conducted with estimated parameters for a diverse set of training and test patterns. The results are compared with the optimal PI controller’s performance and reported in the corresponding section. Encouraging results are obtained, suggesting further research in the proposed direction. For low-disturbance scenarios, even simple controllers can have acceptable performance, but the real quality of a proposed controller should be shown under high-amplitude and difficult disturbances, which is the case in this study. The proposed controller shows higher performance, especially under high disturbances, with an 8.6% reduction in error rate on average compared with the optimal PI controller, and under high-amplitude disturbances, the performance difference is of more than 2.5 folds. Full article

(This article belongs to the Special Issue Applications of Data Science and Artificial Intelligence)

► Show Figures

Figure 1

14 pages, 766 KiB

Open AccessArticle

ULYSSES: Automated FreqUentLY ASked QueStions for KnowlEdge GraphS

by Giannis Vassiliou, Georgia Eirini Trouli, Georgia Troullinou, Nikolaos Spyridakis, George Bitzarakis, Fotini Droumalia, Antonis Karagiannakis, Georgia Skouteli, Nikolaos Oikonomou, Dimitra Deka, Emmanouil Makaronas, Georgios Pronoitis, Konstantinos Alexandris, Stamatios Kostopoulos, Yiannis Kazantzakis, Nikolaos Vlassis, Eleftheria Sfinarolaki, Vardis Daskalakis, Iakovos Giannakos, Argyro Stamatoukou, Nikolaos Papadakis and Haridimos Kondylakis Show full author list Hide full author list

Appl. Sci. 2024, 14(17), 7640; https://doi.org/10.3390/app14177640 - 29 Aug 2024

Viewed by 1253

Abstract

The exponential growth of Knowledge Graphs necessitates effective and efficient methods for their exploration and understanding. Frequently Asked Questions (FAQ) is a service that typically presents a list of questions and answers related to a specific topic, and which is intended to help [...] Read more.

The exponential growth of Knowledge Graphs necessitates effective and efficient methods for their exploration and understanding. Frequently Asked Questions (FAQ) is a service that typically presents a list of questions and answers related to a specific topic, and which is intended to help people understand that topic. Although FAQ has already shown its value on large websites and is widely used, to the best of our knowledge it has not yet been exploited for Knowledge Graphs. In this paper, we present ULYSSES, the first system for automatically constructing FAQ lists for large Knowledge Graphs. Our method consists of three key steps. First, we select the most frequent queries by exploiting the available query logs. Next, we answer the selected queries, using the original graph. Finally, we construct textual descriptions of both the queries and the corresponding answers, exploring state-of-the-art transformer models, i.e., ChatGPT 3.5 and Gemini 1.5 Pro. We evaluate the results of each model, using a human-constructed FAQ list, contributing a unique dataset to the domain and showing the benefits of our approach. Full article

(This article belongs to the Special Issue Applications of Data Science and Artificial Intelligence)

► Show Figures

Figure 1

16 pages, 1570 KiB

Open AccessArticle

A Classification Method for Incomplete Mixed Data Using Imputation and Feature Selection

by Gengsong Li, Qibin Zheng, Yi Liu, Xiang Li, Wei Qin and Xingchun Diao

Appl. Sci. 2024, 14(14), 5993; https://doi.org/10.3390/app14145993 - 9 Jul 2024

Cited by 2 | Viewed by 1522

Abstract

Data missing is a ubiquitous problem in real-world systems that adversely affects the performance of machine learning algorithms. Although many useful imputation methods are available to address this issue, they often fail to consider the information provided by both features and labels. As [...] Read more.

Data missing is a ubiquitous problem in real-world systems that adversely affects the performance of machine learning algorithms. Although many useful imputation methods are available to address this issue, they often fail to consider the information provided by both features and labels. As a result, the performance of these methods might be constrained. Furthermore, feature selection as a data quality improvement technique has been widely used and has demonstrated its efficiency. To overcome the limitation of imputation methods, we propose a novel algorithm that combines data imputation and feature selection to tackle classification problems for mixed data. Based on the mean and standard deviation of quantitative features and the selecting probabilities of unique values of categorical features, our algorithm constructs different imputation models for quantitative and categorical features. Particle swarm optimization is used to optimize the parameters of the imputation models and select feature subsets simultaneously. Additionally, we introduce a legacy learning mechanism to enhance the optimization capability of our method. To evaluate the performance of the proposed method, seven algorithms and twelve datasets are used for comparison. The results show that our algorithm outperforms other algorithms in terms of accuracy and

F_{1}

score and has reasonable time overhead. Full article

(This article belongs to the Special Issue Applications of Data Science and Artificial Intelligence)

► Show Figures

Figure 1

24 pages, 3487 KiB

Open AccessArticle

A New Hybrid Approach for Product Management in E-Commerce

by Hacire Oya Yüregir, Metin Özşahin and Serap Akcan Yetgin

Appl. Sci. 2024, 14(13), 5735; https://doi.org/10.3390/app14135735 - 1 Jul 2024

Cited by 3 | Viewed by 1385

Abstract

Nowadays, due to the developments in technology and the effects of the pandemic, people have largely switched to e-commerce instead of traditional face-to-face commerce. In this sector, the product variety reaches tens of thousands, which has made it difficult to manage and to [...] Read more.

Nowadays, due to the developments in technology and the effects of the pandemic, people have largely switched to e-commerce instead of traditional face-to-face commerce. In this sector, the product variety reaches tens of thousands, which has made it difficult to manage and to make quick decisions on inventory, promotion, pricing, and logistics. Therefore, it is thought that obtaining accurate and fast forecasting for the future will provide significant benefits to such companies in every respect. This study was built on the proposal of creating a cluster-based–genetic algorithm hybrid forecasting model including genetic algorithm (GA), cluster analysis, and some forecasting models as a new approach. In this study, unlike the literature, an attempt was made to create a more successful forecasting model for many products at the same time inside of single product forecasting. The proposed CBGA model success was compared separately to both the single prediction method successes and only genetic algorithm-based hybrid model successes by using real values from a popular B2C company. As a result, it has been observed that the forecasting success of the model proposed in this study is more successful than the forecasting made using single models or only the genetic algorithm. Full article

(This article belongs to the Special Issue Applications of Data Science and Artificial Intelligence)

► Show Figures

Figure 1

16 pages, 15347 KiB

Open AccessArticle

Transforming Customer Digital Footprints into Decision Enablers in Hospitality

by Achini Adikari, Su Nguyen, Rashmika Nawaratne, Daswin De Silva and Damminda Alahakoon

Appl. Sci. 2024, 14(7), 3114; https://doi.org/10.3390/app14073114 - 8 Apr 2024

Cited by 2 | Viewed by 1427

Abstract

The proliferation of online hotel review platforms has prompted decision-makers in the hospitality sector to acknowledge the significance of extracting valuable information from this vast source. While contemporary research has primarily focused on extracting sentiment and discussion topics from online reviews, the transformative [...] Read more.

The proliferation of online hotel review platforms has prompted decision-makers in the hospitality sector to acknowledge the significance of extracting valuable information from this vast source. While contemporary research has primarily focused on extracting sentiment and discussion topics from online reviews, the transformative potential of such insights remains largely untapped. In this paper, we propose an approach that leverages Natural Language Processing (NLP) techniques to convert unstructured textual reviews into a quantifiable and structured representation of emotions and hotel aspects. Building upon this derived representation, we conducted a segmentation analysis to gauge distinct emotion and concern-based profiles of customers, as well as profiles of hotels with similar customer emotions using a self-organizing unsupervised algorithm. We demonstrated the practicality of our approach using 22,450 online reviews collected from 44 hotels. The insights garnered from emotion analysis and review segmentation facilitate the development of targeted customer management strategies and informed decision-making. Full article

(This article belongs to the Special Issue Applications of Data Science and Artificial Intelligence)

► Show Figures

Figure 1

40 pages, 5710 KiB

Open AccessArticle

The Impacts of Open Data and eXplainable AI on Real Estate Price Predictions in Smart Cities

by Fátima Trindade Neves, Manuela Aparicio and Miguel de Castro Neto

Appl. Sci. 2024, 14(5), 2209; https://doi.org/10.3390/app14052209 - 6 Mar 2024

Cited by 5 | Viewed by 9812

Abstract

In the rapidly evolving landscape of urban development, where smart cities increasingly rely on artificial intelligence (AI) solutions to address complex challenges, using AI to accurately predict real estate prices becomes a multifaceted and crucial task integral to urban planning and economic development. [...] Read more.

In the rapidly evolving landscape of urban development, where smart cities increasingly rely on artificial intelligence (AI) solutions to address complex challenges, using AI to accurately predict real estate prices becomes a multifaceted and crucial task integral to urban planning and economic development. This paper delves into this endeavor, highlighting the transformative impact of specifically chosen contextual open data and recent advances in eXplainable AI (XAI) to improve the accuracy and transparency of real estate price predictions within smart cities. Focusing on Lisbon’s dynamic housing market from 2018 to 2021, we integrate diverse open data sources into an eXtreme Gradient Boosting (XGBoost) machine learning model optimized with the Optuna hyperparameter framework to enhance its predictive precision. Our initial model achieved a Mean Absolute Error (MAE) of EUR 51,733.88, which was significantly reduced by 8.24% upon incorporating open data features. This substantial improvement underscores open data’s potential to boost real estate price predictions. Additionally, we employed SHapley Additive exPlanations (SHAP) to address the transparency of our model. This approach clarifies the influence of each predictor on price estimates and fosters enhanced accountability and trust in AI-driven real estate analytics. The findings of this study emphasize the role of XAI and the value of open data in enhancing the transparency and efficacy of AI-driven urban development, explicitly demonstrating how they contribute to more accurate and insightful real estate analytics, thereby informing and improving policy decisions for the sustainable development of smart cities. Full article

(This article belongs to the Special Issue Applications of Data Science and Artificial Intelligence)

► Show Figures

Figure 1

16 pages, 541 KiB

Open AccessArticle

Research on Ensemble Learning-Based Feature Selection Method for Time-Series Prediction

by Da Huang, Zhaoguo Liu and Dan Wu

Appl. Sci. 2024, 14(1), 40; https://doi.org/10.3390/app14010040 - 20 Dec 2023

Cited by 4 | Viewed by 2938

Abstract

Feature selection has perennially stood as a pivotal concern in the realm of time-series forecasting due to its direct influence on the efficacy of predictive models. Conventional approaches to feature selection predominantly rely on domain knowledge and experiential insights and are, therefore, susceptible [...] Read more.

Feature selection has perennially stood as a pivotal concern in the realm of time-series forecasting due to its direct influence on the efficacy of predictive models. Conventional approaches to feature selection predominantly rely on domain knowledge and experiential insights and are, therefore, susceptible to individual subjectivity and the resultant inconsistencies in the outcomes. Particularly in domains such as financial markets, and within datasets comprising time-series information, an abundance of features adds complexity, necessitating adept handling of high-dimensional data. The computational expenses associated with traditional methodologies in managing such data dimensions, coupled with vulnerability to the curse of dimensionality, further compound the challenges at hand. In response to these challenges, this paper advocates for an innovative approach—a feature selection method grounded in ensemble learning. The paper explicitly delineates the formal integration of ensemble learning into feature selection, guided by the overarching principle of “good but different”. To operationalize this concept, five feature selection methods that are well suited to ensemble learning were identified, and their respective weights were determined through K-fold cross-validation when applied to specific datasets. This ensemble method amalgamates the outcomes of diverse feature selection techniques into a numeric composite, thereby mitigating potential biases inherent in traditional methods and elevating the precision and comprehensiveness of feature selection. Consequently, this method improves the performance of time-series prediction models. Full article

(This article belongs to the Special Issue Applications of Data Science and Artificial Intelligence)

► Show Figures

Figure 1

Review

Jump to: Editorial, Research

18 pages, 1246 KiB

Open AccessReview

Artificial Intelligence-Powered Recommender Systems for Promoting Healthy Habits and Active Aging: A Systematic Review

by Juan Lopez-Barreiro, Jose Luis Garcia-Soidan, Luis Alvarez-Sabucedo and Juan M. Santos-Gago

Appl. Sci. 2024, 14(22), 10220; https://doi.org/10.3390/app142210220 - 7 Nov 2024

Cited by 2 | Viewed by 3825

Abstract

(1) Background: Increasing life expectancy allows for more age-related health issues. Enhancing physical, cognitive, mental, and social health is crucial. Promoting healthy habits combats stress and diseases. Recommendation systems, like collaborative filtering, tailor suggestions but face challenges. Techniques such as artificial intelligence and [...] Read more.

(1) Background: Increasing life expectancy allows for more age-related health issues. Enhancing physical, cognitive, mental, and social health is crucial. Promoting healthy habits combats stress and diseases. Recommendation systems, like collaborative filtering, tailor suggestions but face challenges. Techniques such as artificial intelligence and machine learning are vital. Personalized health recommendations improve lifestyles and mitigate issues. (2) Methods: A systematic review adhering to the general principles of the Preferred Reporting Items for Systematic Reviews and Meta-Analyses was conducted with the aim of identifying articles on innovative research about using recommendation algorithms, machine learning, or artificial intelligence to promote healthy habits and active aging. (3) Results: A total of 34 articles were included in this work. They address the topic of recommendation systems that use machine learning or artificial intelligence in the promotion of healthy habits. (4) Conclusions: This article reviews health-related activity recommendation techniques for the general population. With rising life expectancy and common health issues, effective recommendations are crucial for future public health. Limitations include excluding simpler models. Despite many proposals, systematic adherence mechanisms are lacking. Developing traceable, verifiable systems for healthy activity recommendations is vital for aging populations in developed countries. Full article

(This article belongs to the Special Issue Applications of Data Science and Artificial Intelligence)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Applications of Data Science and Artificial Intelligence

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (13 papers)

Editorial

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI