Smart City Digital Twins (SCDT) are virtual replicas of cities (or parts thereof) that integrate real-time data from various sources to enable simulation, monitoring, and optimization of urban systems for more efficient and sustainable urban management. In this article, we provide a survey of modular SCDTs, covering standardization and key enabling technologies. Modular hardware and software architectures pave way for standardization, which is crucial for efficient maintenance as well as scalability and portability to new application domains.
Diabetic retinopathy (DR) is a major global cause of blindness, underscoring the critical need for early and accurate detection. This study addresses this challenge by conducting an in-depth comparative analysis of various image processing techniques coupled with the state-of-the-art EfficientNetB0 model for DR identification. The researchers employed retinal images from the Asia-Pacific Teleophthalmology Society (APTOS) 2019 Blindness Detection competition on Kaggle, a valuable dataset for this purpose. The study considers five image processing methods: Median Subtraction, Ben Graham's Filter, Adaptive Histogram Equalization, Histogram Normalization, and Selective Gamma Correction. These techniques aim to enhance image quality and information content, which is crucial for training the model effectively. The study's primary performance metric is accuracy, recall, precision, and F1 score, which measures the model's ability to classify images correctly. The outcomes reveal that the choice of image pre-processing techniques significantly influences the model's performance. In summary, the study demonstrates that by combining advanced image pre-processing methods with a powerful deep learning model, Ben Graham's Filter can notably enhance diabetic retinopathy detection performance with 86
AI is increasingly present in creative industries, including industrial design. However, there is insufficient understanding of professionals' perceptions of such tools. This knowledge is crucial for fostering adoption and trust in technology. The article explores designers' perceptions and trust in these tools and examines the possibilities for integration and collaboration. It employs a mixed-methods explanatory sequential approach to investigate these professionals' trust in AI during the creative stages of New Product Development (NPD), such as sketching and rendering. The results reveal designers' limited trust in AI tools, influenced equally by their perceptions of the artifacts' risk, competency, and benevolence. Participants envisioned AI as a future adjunct to their toolkit, pinpointing ethics, transparency, tool control, and efficiency as areas for improvement. The study offers insights into fostering trust and presents design recommendations for future AI-enabled applications in industrial design. It sheds light on AI's potential as a creative partner, underlining the need for ethical and transparent integration.
Continuous monitoring of the risk of civil unrest events and predicting their occurrence is of paramount importance. This task involves identifying and understanding the primary factors that contribute to such events, especially in regions with unique dynamics, such as South Africa. Although many global and South African-specific studies have conducted research on predicting the frequency or probability of these events, there is a notable gap in identifying the influential factors behind them. This study unveiled several contributing factors, including demanding behaviour, power outages, service delivery, wage disputes, acts of violence, gender-based conflicts, and unemployment rates. These factors, individually or collectively, contribute to the complexity of civil unrest in the region. The 2021 South African unrest, also known as the July 2021 riots, the Zuma unrest, or Zuma riots, serves as an example. This event was triggered by the imprisonment of former president Jacob Zuma for contempt of court, inciting his followers to demand his release, a situation aligning with the ‘demanding behaviour’ influential factor identified in our study. We used advanced data analysis and machine learning techniques to explore these factors. Specifically, the Logit model was used to determine the coefficients that optimally fit the data, establishing significant relationships between these factors and incidents of civil unrest. Our research not only offers insights on influential factors, but also presents a predictive framework. We evaluated logistic regression, support vector clustering, decision tree classifier, and random forest classifier models to predict civil unrest. The results showed that the decision tree and the random forest classifiers perform better, achieving an accuracy of 98
Predicting credit card defaults is pivotal for financial institutions to mitigate risks and implement proactive measures. Despite the monumental successes of deep learning in domains like computer vision and natural language processing, its efficacy in leveraging tabular data structures, especially in credit default prediction, remains contentious. In this manuscript, we systematically investigate various deep learning architectures, juxtaposing their performance with a meticulously optimized Gradient Boosted Decision Tree (GBDT) classifier. Our empirical findings reveal that the apex deep learning model achieved a performance metric of 0.783, slightly under performing against the GBDT model's 0.791. This reinforces existing literature, accentuating the superior prowess of tree-based algorithms in deciphering the intricacies of credit default prediction over contemporary deep learning paradigms.
Representations of social robots influence the formation and change of attitudes toward them. Researchers propose a study focused on representation to explain the psychological factors determining behaviour toward robots and intercultural comparisons of attitudes toward them. The primary goal is to provide insights for the enhanced construction of such robotic systems and the optimization of human-robot interactions. The present study adopts Nomura's scale and extends it to include situation-specific questions and questions about opinions and attitudes toward the general development of robotics. Possible theoretical and practical implications are discussed.
Chili plants face susceptibility to a range of fungal, bacterial, and viral diseases, with leaves being particularly vulnerable. This study focuses on chili leaves and provides an extensive examination of various chili diseases and existing research in this domain. Traditional disease detection methods are labor-intensive for farmers. The paper introduces innovative image processing and deep learning techniques for early and effective disease identification in chili leaves. The proposed framework highlights a well-defined methodology to classify chili leaf diseases from the healthy ones termed as Chili-Net. The work focuses on an ensemble technique to extract features from the images. Three different deep neural networks viz. ResNet 50, VGG 16 and Inception V3 are integrated into a single channel to extract important features. Furthermost a customized deep neural network comprising 10 layers is utilized to classify the classes. The presented framework generated an accuracy of 97
We present preliminary research on the use of Virtual Reality (VR) technology to measure finger range of motion to support the diagnosis and rehabilitation of hand diseases. The use of VR technology could make it possible to reliably store and quantify the data, which could be crucial in preclinical diagnosis and in the development of rehabilitation programs. The method is based on analyzing the position of the finger phalanges as seen in virtual reality. Using a VR application created in Unity, the movement of the phalanges of the hand was transferred to a block model for the DIP, PIP, and MCP joints. The results indicate that the technology-based method could be a promising alternative to traditional methods of measuring range of motion. The next stage of work will be to extend the application to the remaining fingers and validate the measurements using a glove with embedded inertia sensors. This approach could significantly affect the quality of diagnosis and rehabilitation of patients with hand movement disorders, opening up new research opportunities.
The primary objective of this study is to develop a real-time audio transmission and multimedia messaging platform that can operate between mobile devices, utilizing smartphones or devices equipped with Bluetooth Low Energy (BLE) connectivity, all without necessitating internet access. In pursuit of this goal, the study delved into the examination of the BLE application programming interfaces designed for smartphones, with the aim of establishing a well-suited architecture for real-time audio transmission. The study also meticulously scrutinized the challenges encountered during the audio data transmission process and implemented potential solutions to address them. As part of the investigation, the study involved a comparison of various codec alternatives designed to compress audio data, with the Opus codec emerging as the preferred choice. Ultimately, the study successfully achieved real-time audio transmission between mobile devices via BLE and meticulously recorded and analyzed the obtained results.
This article proposes an autonomous and adaptive communication model that is applied during failures and attacks on e-services. We explore what kind of model is relevant in the rapidly changing environments that are typical for agile projects and teams. Then, through an extensive literature review and a practical case study, we critically examine existing communication and security models, which rely primarily on static, well established procedures. We conclude that security protocols must undergo continuous and frequent updates to keep pace with the swiftly evolving design landscape, in which systems and teams progress rapidly. The process of updating communication pathways can prove both costly and error prone. These findings justify the need for a novel approach: a model that recommends appropriate actions in a dynamically changing organisation.
Electricity prices are an essential factor for industry and intelligent systems. An important part of energy trading takes place on the Day-ahead Market. Predicting prices in this market allows economically rational decisions to be made. Our study aims to model prices in the day-ahead market using neural networks. An attempt is made to reproduce the results of the paper [Marcjasz et al., 2020], where two network structures are compared: one with one output and one with 24 outputs. Our work adapts the modelling methodology to the current challenging market conditions and variable data reporting methods. We show that a structure predicting 24 values is more resilient in dynamic price conditions.
Widespread access to latest technologies including cloud computing, Artificial Intelligence, Virtual and Augmented Reality, and constant business needs to increase efficiency and competitive advantages open industry and manufacturing sectors to a modern and unusual solutions well known from completely different applications. In this article we will be focusing on a concept of time perspective in Extended Reality applications, and interactions with users based on a Smart Refinery example. It's also important to add that presented concept is a part of wider scientific research and considerations related to an Implementation Doctorate project focusing on decarbonization of an industrial environment through application of Information Technologies and integration to industrial systems. Designed solution connects Operational Technologies with a comprehensive Industrial IoT platform enriched by an Extended Reality interfaces to enable true integration of surrounding industrial environment and various types of users. Depends on a use-case, presented concept allows immersive interaction with things and devices, and view a multidimensional data set in context of past, present, and future time perspective. Thus, described concept allows analysis, investigation and evaluation of past production cycles, real-time monitoring, adjustment of current process parameters, and finally testing of settings for a future iteration based on Digital Twins of petrochemical processes through interfaces knowns mostly from an entertainment industry. Applied technologies in a form of Smart Refinery system, support that way a sustainability through efficient energy consumption and reduced carbon footprint.
The examination of thesis diplomas for instances of plagiarism can be a difficult and time-consuming task. However, some parts of these documents are more important and are more susceptible to being plagiarized than others. This work investigates four distinct approaches to the detection and exclusion of such irrelevant fragments from the process of plagiarism detection to reduce the cognitive load inflicted upon supervisors. We evaluate the relevance of image and text data on solving this task by exploring models that are multimodal, purely image-based, purely text-based, and based on handcrafted features.
This research project, conducted at the Laboratory of Media Studies, University of Warsaw in cooperation with CREC Saint Cyr Écoles de Coëtquidan, Guer, France, aims to explore the integration of automated gameplay analysis and biometric tools to enhance the game user experience. The study utilized a custom-developed first-person shooter game. Twenty-two student participants from the Faculty of Journalism and Book Studies at the University of Warsaw took part in the research. They were divided into two groups based on their gaming experience—heavy gamers and light gamers. The study focused on the emotional reactions (facetracking) of these participants during gameplay and specified in-game events. The research findings revealed that heavy gamers exhibited stronger emotional responses, particularly joy, when successfully hitting targets in the game. This suggests that game elements could be modified to enhance player satisfaction. However, the study acknowledges the absence of baseline recordings and the need for additional biometric measurements. The research demonstrates the potential of integrating automated gameplay analysis and biometric research to improve game user experiences. It offers valuable insights for game developers and highlights the significance of individual gaming backgrounds. Future work should address the limitations and refine the research procedure for wider application in the gaming industry.
Contemporary virtual reality (VR) technologies, combined with advanced computational tools such as MATLAB, open up new possibilities in the design and control of industrial robots. This article presents a potential control system for Fanuc manipulators, utilizing VR simulation within the Unity environment and the advanced computational tools of the Robotics System Toolbox in MATLAB. This system enables real-time control, as well as planning and visualization of the manipulators' trajectories, representing a significant step towards remote and intuitive management of industrial robots.
Road conditions have a big impact on the effectiveness and safety of road transport. Potholes, cracks, and bumps in the road may impact driving behaviors and increase the risk of accidents and casualties. To improve the driving experience, proper road maintenance procedures are required. This research paper focuses on the DenseNet model to classify potholes using road image data. A self-generated dataset of 1721 road images with 4 classes is used to train the model. The model is tested with different dataset division strategies and epoch counts. The model provided a maximum accuracy of 98.3
VisualSLAM is currently a common research topic, and ensuring the highest quality of these systems is an issue that receives much attention. The following article collects, divides and systematises the knowledge published on the fusion of VisualSLAM with LiDAR scanners. It can serve as a source to familiarise oneself with the subject and as a collection of literature that can be used to deepen knowledge and gather detailed information on the subject.
With the growing importance of business process automation practices, companies deploy a variety of tools and policies to reduce manual workload and achieve strategic goals. Our study explored the perception of strategic approaches to enterprise hyperautomation among 136 responders, representing 52 leading companies from Nordic Europe. Findings highlight the importance of custom code, as well as low-code and RPA solutions, occasionally accompanied by AI and no-code. The strongest impact of hyperautomation success was related to governance, security and compliance, as well as engagement of all stakeholders, and celebration of achievements among persons taking part at the transition.
This study addresses the issue of procrastination in home-based virtual reality (VR) physical exercise. A total of n = 52 participants who owned Oculus Quest 2 headsets were involved in the study. The participants were tasked with completing six fifteen-minute High-Intensity Interval Training (HIIT) sessions within fourteen days, with three training sessions to be completed within the first seven days. The participants were allowed to schedule the sessions themselves. First we measured the participants' average physical training performance using our custom VR application. Next we calculated the average interval between individual training sessions and categorized the participants into two groups. Those inclined to cluster their training sessions daily were assigned to the block training group, while those whose sessions were distributed more evenly were assigned to the distributed training group. Our findings suggest that procrastination leads to poorer performance during training sessions in a VR environment. Individuals in the block training group demonstrated significantly lower average training performance than those in the distributed training group.
The fourth industrial revolution and internet of things applications have led to significant advancements in sensor technology and cloud services. Modern systems can easily gather, transport, and store large amounts of data using the advanced powerful processing capabilities and cutting-edge GPU. Such massive data may be exploited extravagantly for a variety of purposes, including the development of intelligent maintenance strategies. To ensure the safe and reliable operations of any industrial assets, prognostics and health management plays a significant role. Among all the aspects in prognostics and health management (PHM) used for efficient deployment of predictive maintenance, machine health states estimation and remaining useful life prediction are the most pivotal tasks. This study thus proposes a novel technique based on hidden markov model (HMM) for the health states estimations and prediction of the failure occurrence time of a roller element bearing. Given the success of HMMs with its wide variety of applications in speech recognition, language processing, and image processing. This study proposes to use it in the domain of machine prognostics as well. The three prime benefits of HMM are (i) the number of clusters is not required to be pre-determined, (ii) HMM works best with sequential data (iii) it can extract hidden states of the system that are not directly observable in the concerned problem. Finally, the efficacy of the proposed model has been tested on the IEEE-PHM-2012 challenge data sets. The results obtained are much better when compared with the existing literatures.
