Grupa za vizuelno računarstvo i percepciju

This paper uses data sampled at hourly and daily frequencies to predict Bitcoin returns. We consider various advanced non-linear models based on a multitude of popular technical indicators that represent market trend, momentum, volume, and sentiment. We run a robust empirical exercise to observe the impact of forecast horizon, model type, time period, and the choice of inputs (predictors) on the forecast performance of the competing models. We find that Bitcoin prices are weakly efficient at the hourly frequency. In contrast, technical analysis combined with non-linear forecasting models becomes statistically significantly dominant relative to the random walk model on a daily horizon. Our comparative analysis identifies the random forest model as the most accurate at predicting Bitcoin. The estimated measures of the relative importance of predictors reveal that the nature of investing in the Bitcoin market evolved from trend-following to excessive momentum and sentiment in the most recent time period.

The COVID-19 pandemic strengthens the use of digital services in the supply chains of manufacturers and suppliers in the automotive industry. Furthermore, the digitalization of the production process changed how manufacturing firms manage their value chains in the era of Industry 4.0. The automotive sector represents the ecosystem with rapid digital transformation, which provides a strong relationship between manufacturing firms in supply chains. However, there are many gaps in understanding how digital technologies and services could better shape relations between manufacturers and suppliers in the automotive industry. Accordingly, this study investigates the relations in deliveries of digital services in supply chains of the automotive industry. The data set was obtained through annual reports of the automotive firms, both from suppliers and manufacturers, between 2018 and 2020. From the network perspective, throughout the years, authors have used Social Network Analysis (SNA) method. SNA evaluates the relationship between actors (i.e., manufacturers and suppliers) in the use of services in their business models. The research results demonstrate how suppliers influence car manufacturers to deliver digital services to their customers. Finally, this study provides information that the combination of digital technologies with product-related services enables a stronger relationship between manufacturers and suppliers in the manufacturing ecosystem. These relations support the manufacturing ecosystem to survive the influence of different environments.

This paper addresses the interpretability problem of non-parametric option pricing models by using the explainable artificial intelligence (XAI) approach. We study call options written on the S&P 500 stock market index across three market regimes: pre-COVID-19, COVID-19 market crash, and post-COVID-19 recovery. Our comparative option pricing exercise demonstrates the superiority of the random forest and extreme gradient boosting models for each market regime. We also show that the model’s pricing accuracy has worsened from the pre-COVID-19 to the recovery period. Moneyness was the most important price determinants across the market regimes, while the implied volatility and time-to-maturity inputs contributed intermittently to a lesser extent. During the COVID-19 crash, open interest gained more economic importance due to the increased behavioral tendencies of traders consistent with market distress.

Large-scale infrastructure, such as China–Europe Railway Express (CER-Express), which connects countries and regions across Asia and Europe, has a potentially profound effect on land use, as evidenced by changes in land cover along the railway. To ensure sustainable development of such infrastructure and appropriate land administration, effective ways to monitor and assess its impact need to be developed. Remote sensing based on publicly available satellite imagery represents an obvious choice. In the study presented here, we employ a state-of-the-art deep-learning-based approach to automatically detect different types of land cover based on multispectral Sentinel-2 imagery. We then use these data to conduct and present a study of the changes in land use in two geopolitically diverse regions of interest (in Serbia and China and with and without CER-Express infrastructure) for the period of the last three years. Our results show that the standard image-patch-based land cover classification approaches suffer a significant drop in performance in our target scenario in which each pixel needs to be assigned a cove class, but still, validate the applicability of the proposed approach as a remote sensing tool to support the sustainable development of large infrastructure. We discuss the technical limitations of the proposed approach in detail and potential ways in which it can be improved.

Images synthesized using depth-image-based-rendering (DIBR) techniques may suffer from complex structural distortions. The goal of the primary visual cortex and other parts of brain is to reduce redundancies of input visual signal in order to discover the intrinsic image structure, and thus create sparse image representation. Human visual system (HVS) treats images on several scales and several levels of resolution when perceiving the visual scene. With an attempt to emulate the properties of HVS, we have designed the no-reference model for the quality assessment of DIBR-synthesized views. To extract a higher-order structure of high curvature which corresponds to distortion of shapes to which the HVS is highly sensitive, we define a morphological oriented Difference of Closings (DoC) operator and use it at multiple scales and resolutions. DoC operator nonlinearly removes redundancies and extracts fine grained details, texture of an image local structure and contrast to which HVS is highly sensitive. We introduce a new feature based on sparsity of DoC band. To extract perceptually important low-order structural information (edges), we use the non-oriented Difference of Gaussians (DoG) operator at different scales and resolutions. Measure of sparsity is calculated for DoG bands to get scalar features. To model the relationship between the extracted features and subjective scores, the general regression neural network (GRNN) is used. Quality predictions by the proposed DoC-DoG-GRNN model show higher compatibility with perceptual quality scores in comparison to the tested state-of-the-art metrics when evaluated on four benchmark datasets with synthesized views, IRCCyN/IVC image/video dataset, MCL-3D stereoscopic image dataset and IST image dataset.

Vegetation suppression on and near the railway tracks is very important to keep trains running safely and on time. This paper presents an automated real-time system, developed for the Serbian Railways company, that is used to maintain vegetation on and near railway tracks. This system allows precise spraying of herbicides only in locations where it is really needed, unlike older systems for controlling vegetation where herbicides are sprayed evenly along the railways tracks. The system consists of a camera mounted on a locomotive, which records the railway in front of the train, the video stream from the camera is sent to the standard PC and processed using software based on convolutional neural networks. This software allows the detection of weed and bushes on and near the railway tracks and sends signals to the PLC when it is the right moment to activate the herbicide sprayers.

In the currently ongoing process of retro-digitization of Serbian dialectal dictionaries, the biggest obstacle is the lack of machine-readable versions of paper editions. Therefore, one essential step is needed before venturing into the dictionary-making process in the digital environment -OCRing the pages with the highest possible accuracy. Successful retro-digitization of Ser-bian dialectal dictionaries, currently in progress, has shown a dire need for one basic yet necessary step, lacking until now-OCRing the pages with the highest possible accuracy. OCR processing is not a new technology, as many open-source and commercial software solutions can reliably convert scanned images of paper documents into digital documents. Available software solutions are usually efficient enough to process scanned contracts, invoices, financial statements, newspapers , and books. In cases where it is necessary to process documents that contain accented text and precisely extract each character with diacritics, such software solutions are not efficient enough. This paper presents the OCR software called „SCyDia“, developed to overcome this issue. We demonstrate the organizational structure of the OCR software „SCyDia“ and the first results. The „SCyDia“ is a web-based software solution that relies on the open-source software „Tes-seract“ in the background. „SCyDia“ also contains a module for semi-automatic text correction. We have already processed over 15000 pages, 13 dialectal dictionaries, and five dialectal monographs. At this point in our project, we have analyzed the accuracy of the „SCyDia“ by processing 13 dialectal dictionaries. The results were analyzed manually by an expert who examined a number of randomly selected pages from each dictionary. The preliminary results show great promise, spanning from 97.19% to 99.87%.

In order to establish safe operation of the railway, it is very important to maintain vegetation on and near the railway. In this paper, a solution based on deep learning for detection of weeds and bushes on the railways and the control of intelligent herbicide sprayers using PLC, is presented. Hardware setup, software implementation, the configurations of the convolutional neural networks, and the datasets used to train the neural networks are described. A video stream with recording of the railway tracks in front of the train, is sent to a PC computer located in the cabin. This video stream is processed using software for detection of weeds and bushes based on multiple convolutional neural networks. This software sends signals to the PLC that controls the opening of the nozzles on the herbicide sprayer. The presented solution is developed for Serbian Railways company.

The paper examines the role of social media in spreading information and shaping public discourse, using the release of ChatGPT in 2022 and the global discussions about COVID-19 vaccines in 2021 as case studies. Over 12 million posts and news articles from various online platforms were analysed through topic modelling techniques and sentiment analysis. The findings reveal different thematic emphases and public perceptions on each platform, whilst also showing that discussions about COVID-19 vaccines spread faster due to the urgency of the topic, in comparison to discussions about ChatGPT which spread more gradually.

The study highlights the significant impact that AI recommendation systems have on more than half of the world’s population daily, influencing every aspect of a user’s online life. It identifies issues such as misinformation, polarization, addiction, emotional contagion, privacy, and bias. Despite the wide-ranging societal impact of these AI algorithms, the scientific community has largely overlooked their influence. Among the potential solutions suggested is a tripartite decision-making algorithm that takes into account inputs from individuals, society, and tech corporations. The study calls for further research to assess these systems’ effect on human imagination, creativity, and wellbeing, emphasizing the need for broader conversations around aligning AI with societal values.

This chapter examines the possible effects of immersion in the Metaverse on cognitive load, highlighting how personalized experiences may escalate addiction, encapsulate users in digital echo chambers, and lead to negative social consequences. The Metaverse’s ability to meet desires might create a false sense of gratification, increasing the risk of addiction. Referencing David Chalmers’ „Reality+,“ the study critiques the notion of virtual reality as a „genuine reality,“ warning against potential misuse. It finds that the psychological impact of the Metaverse parallels that of fiction and evaluates its influence on empathy, outlining both benefits and drawbacks. The chapter concludes that there is significant potential for manipulation in Metaverse environments, advocating for regulations to protect society. It calls for further research to comprehend, mitigate, and manage the risks associated with Metaverse immersion.

This paper investigates a multidisciplinary approach to testing and aligning artificial intelligence (AI), particularly focusing on large language models (LLMs). Highlighting the collaboration with CERN, the study tackles ethical, controllability, and predictability challenges that accompany the rapid development of LLMs. The research introduces an innovative simulation-based framework within a virtual reality environment that replicates real-world conditions. This framework is populated by automated ‘digital citizens’ to simulate complex social interactions and structures, aimed at optimizing AI performance. By integrating theories from sociology, social psychology, computer science, physics, biology, and economics, the study aspires to create a more human-aligned and socially responsible AI. The simulation enables advanced AI agents to make autonomous decisions in dynamic, realistic scenarios. Despite its considerable potential, this approach confronts challenges, such as the unpredictable nature of social dynamics. The research seeks to advance AI development by emphasizing the integration of social, ethical, and theoretical dimensions.

This study develops machine learning models to detect subtle changes in hepatocyte chromatin organization due to Iron (II, III) oxide nanoparticle exposure. The hypothesis is that such exposure will significantly alter chromatin texture. By analyzing 2000 hepatocyte nuclear regions of interest (ROIs) from mouse liver tissue, the research calculates five parameters for each ROI: Long Run Emphasis, Short Run Emphasis, Run Length Nonuniformity, and two wavelet coefficient energies from discrete wavelet transform. These parameters are used as input for supervised machine learning models, specifically random forest and gradient boosting classifiers. The models show robust performance in distinguishing between chromatin structures of exposed and control groups. The findings suggest that iron oxide nanoparticles cause significant changes in hepatocyte chromatin distribution, highlighting the potential of AI techniques in enhancing the evaluation of hepatocytes in both physiological and pathological states.