Search

Lecture Notes in Computer Science (LNCS) is a globally recognised publication outlet for the field of Computer Science, including in South Africa. In this study, spanning from 1973 to 2022, we investigated the research participation of South African based authors in LNCS. The publication output and citation impact of these authors were compared to the global Computer Science and LNCS output. The authorship patterns and collaborative behaviour of South African LNCS papers were explored, and a keyword or topic analysis also conducted. Of the total of 518 662 LNCS papers published globally between 1973 and 2022, South African based researchers contributed 1150 papers (0.22%). The LNCS papers from South Africa exhibit a strong collaborative publication culture, with 1043 (91%) co-authored and 107 (9%) singleauthored works. Local LNCS researchers prefer institutional collaboration (43%), followed by international (37%) and national collaboration (11%). Europe emerged as the most significant collaboration partner for LNCS researchers in South Africa. Of the 1150 papers, 836 (73%) had received citations, while 314 (27%) had not. On average, papers published by South African based authors received 6.05 citations, compared to the global LNCS average of 9.49 citations per paper. A keyword analysis revealed that the majority of papers by South African authors focus on artificial intelligence. The results indicate that, although LNCS serves as a reputable dissemination platform for Computer Science research output both globally and locally, South African authors should consider publishing more journal articles to build and improve their researcher profiles. Significance: * The study shows that LNCS is the most frequent publication outlet for Computer Science researchers, globally and in South Africa. * The study offers insight into the publication output, authorship patterns, collaborative behaviour and citation impact of South African based Computer Science researchers. [ABSTRACT FROM AUTHOR]

The International Journal of Semantic Computing has published a special issue on Semantic Computing, which includes five selected papers from the 17th IEEE International Conference on Semantic Computing. Semantic Computing focuses on the derivation, description, integration, and use of semantics for various resources. The papers in the special issue cover topics such as intent detection, constructing probabilistic models from knowledge graphs, unsupervised estimation of subjective content descriptions, the influence of noisy labels on question answering systems, and automatic domain-adaptive sentiment analysis. Each paper presents innovative approaches and findings in their respective areas of research. [Extracted from the article]

Continuous improvement in the clinical performance of neonatal intensive care units (NICU) depends on the use of locally relevant, reliable data. However, neonatal databases with these characteristics are typically unavailable in NICUs using paper-based records, while in those using electronic records, the inaccuracy of data and the inability to customize commercial data systems limit their usability for quality improvement or research purposes. We describe the characteristics and uses of a simple, neonatologist-centered data system that has been successfully maintained for 30 years, with minimal resources and serving multiple purposes, including quality improvement, administrative, research support and educational functions. Structurally, our system comprises customized paper and electronic components, while key functional aspects include the attending-based recording of diagnoses, integration into clinical workflows, multilevel data accuracy and validation checks, and periodic reporting on both data quality and NICU performance results. We provide examples of data validation methods and trends observed over three decades, and discuss essential elements for the successful implementation of this system. This database is reliable and easily maintained; it can be developed from simple paper-based forms or used to supplement the functionality and end-user customizability of existing electronic medical records. This system should be readily adaptable to NICUs in either high- or limited-resource environments. [ABSTRACT FROM AUTHOR]

A drug molecule is a substance that changes an organism's mental or physical state. Every approved drug has an indication, which refers to the therapeutic use of that drug for treating a particular medical condition. While the Large Language Model (LLM), a generative Artificial Intelligence (AI) technique, has recently demonstrated effectiveness in translating between molecules and their textual descriptions, there remains a gap in research regarding their application in facilitating the translation between drug molecules and indications (which describes the disease, condition or symptoms for which the drug is used), or vice versa. Addressing this challenge could greatly benefit the drug discovery process. The capability of generating a drug from a given indication would allow for the discovery of drugs targeting specific diseases or targets and ultimately provide patients with better treatments. In this paper, we first propose a new task, the translation between drug molecules and corresponding indications, and then test existing LLMs on this new task. Specifically, we consider nine variations of the T5 LLM and evaluate them on two public datasets obtained from ChEMBL and DrugBank. Our experiments show the early results of using LLMs for this task and provide a perspective on the state-of-the-art. We also emphasize the current limitations and discuss future work that has the potential to improve the performance on this task. The creation of molecules from indications, or vice versa, will allow for more efficient targeting of diseases and significantly reduce the cost of drug discovery, with the potential to revolutionize the field of drug discovery in the era of generative AI. [ABSTRACT FROM AUTHOR]

This paper investigates the evolving landscape of blockchain technology in renewable energy. The study, based on a Scopus database search on 21 February 2024, reveals a growing trend in scholarly output, predominantly in engineering, energy, and computer science. The diverse range of source types and global contributions, led by China, reflects the interdisciplinary nature of this field. This comprehensive review delves into 33 research papers, examining the integration of blockchain in renewable energy systems, encompassing decentralized power dispatching, certificate trading, alternative energy selection, and management in applications like intelligent transportation systems and microgrids. The papers employ theoretical concepts such as decentralized power dispatching models and permissioned blockchains, utilizing methodologies involving advanced algorithms, consensus mechanisms, and smart contracts to enhance efficiency, security, and transparency. The findings suggest that blockchain integration can reduce costs, increase renewable source utilization, and optimize energy management. Despite these advantages, challenges including uncertainties, privacy concerns, scalability issues, and energy consumption are identified, alongside legal and regulatory compliance and market acceptance hurdles. Overcoming resistance to change and building trust in blockchain-based systems are crucial for successful adoption, emphasizing the need for collaborative efforts among industry stakeholders, regulators, and technology developers to unlock the full potential of blockchains in renewable energy integration. [ABSTRACT FROM AUTHOR]

Motivated by the fact that the fuzzy quasi-normed space provides a suitable framework for complexity analysis and has important roles in discussing some questions in theoretical computer science, this paper aims to study the nearest point problems in fuzzy quasi-normed spaces. First, by using the theory of dual space and the separation theorem of convex sets, the properties of the fuzzy distance from a point to a set in a fuzzy quasi-normed space are studied comprehensively. Second, more properties of the nearest point are given, and the existence, uniqueness, characterizations, and qualitative properties of the nearest points are obtained. The results obtained in this paper are of great significance for expanding the application fields of optimization theory. [ABSTRACT FROM AUTHOR]

Currently, generative applications are reshaping different fields, such as art, computer vision, speech processing, and natural language. The computer science personalization area is increasingly relevant since large companies such as Spotify, Netflix, TripAdvisor, Amazon, and Google use recommender systems. Then, it is rational to expect that generative learning will increasingly be used to improve current recommender systems. In this paper, a method is proposed to generate synthetic recommender system datasets that can be used to test the recommendation performance and accuracy of a company on different simulated scenarios, such as large increases in their dataset sizes, number of users, or number of items. Specifically, an improvement in the state-of-the-art method is proposed by applying the Wasserstein concept to the generative adversarial network for recommender systems (GANRS) seminal method to generate synthetic datasets. The results show that our proposed method reduces the mode collapse, increases the sizes of the synthetic datasets, improves their ratings distributions, and maintains the potential to choose the desired number of users, number of items, and starting size of the dataset. Both the baseline GANRS and the proposed Wasserstein-based WGANRS deep learning architectures generate fake profiles from dense, short, and continuous embeddings in the latent space instead of the sparse, large, and discrete raw samples that previous GAN models used as a source. To enable reproducibility, the Python and Keras codes are provided in open repositories along with the synthetic datasets generated to test the proposed architecture (https://github.com/jesusbobadilla/ganrs.git). [ABSTRACT FROM AUTHOR]

As the world grapples with the pressing challenge of environmental sustainability, the need for innovative solutions to combat air pollution has become paramount. Air pollution is a complex issue that necessitates real-time monitoring of pollution sources for effective mitigation. This paper explores the potential of swarm algorithms applied as a novel and efficient approach to address this critical environmental concern. Swarm algorithms offer a promising framework for coordinating fleets of drones to collaboratively monitor and analyze air pollution sources. The unique capabilities of drones, including their agility, accessibility, and versatility, make them ideal candidates for aerial data collection. When harnessed in a swarm, these drones can create a dynamic and adaptable network that provides a more comprehensive and fine-grained understanding of air pollution dynamics. This paper delves into the conceptual foundations of using swarm algorithms in drone-based air pollution monitoring. [ABSTRACT FROM AUTHOR]

Metaphors that compare the computer to a human brain are common in computer science and can be traced back to a fertile period of research that unfolded after the Second World War. To conceptualize the emerging "intelligent" properties of computing machines, researchers of the era created a series of virtual objects that served as interpretive devices for representing the immaterial functions of the computer. This paper analyses the use of the terms "artificial" and "virtual" in scientific papers, textbooks, and popular articles of the time, and examines how, together, they shaped models in computer science used to conceptualize computer processes. [ABSTRACT FROM AUTHOR]

Social media platforms have completely revolutionized human communication and social interactions. Their positive impacts are simply undeniable. What has also become undeniable is the prevalence of harmful antisocial behaviors on these platforms. Cyberbullying, misinformation, hate speech, radicalization, and extremist propaganda have caused significant harms to society and its most vulnerable populations. Thus, the social media forensics field was born to enable investigators and law enforcement agents to better investigate and prosecute these cybercrimes. This paper surveys the latest research works in the field to explore how artificial intelligence (AI) techniques are being utilized in social media forensics investigations. We examine how natural language processing can be used to identify extremist ideologies, detect online bullying, and analyze deceptive profiles. Additionally, we explore the literature on GNNs and how they are applied in social network modeling for forensic purposes. We conclude by discussing the key challenges in the field and suggest future research directions. [ABSTRACT FROM AUTHOR]

This research paper delves into the effectiveness and impact of behavior change techniques fostered by information technologies, particularly wearables and Internet of Things (IoT) devices, within the realms of engineering and computer science. By conducting a comprehensive review of the relevant literature sourced from the Scopus database, this study aims to elucidate the mechanisms and strategies employed by these technologies to facilitate behavior change and their potential benefits to individuals and society. Through statistical measurements and related works, our work explores the trends over a span of two decades, from 2000 to 2023, to understand the evolving landscape of behavior change techniques in wearable and IoT technologies. A specific focus is placed on a case study examining the application of behavior change techniques (BCTs) for monitoring vital signs using wearables, underscoring the relevance and urgency of further investigation in this critical intersection of technology and human behavior. The findings shed light on the promising role of wearables and IoT devices for promoting positive behavior modifications and improving individuals' overall well-being and highlighting the need for continued research and development in this area to harness the full potential of technology for societal benefit. [ABSTRACT FROM AUTHOR]

Researchers in cognitive science have long been interested in modeling human perception using statistical methods. This requires maneuvers because these multiple dimensional data are always intertwined with complex inner structures. The previous studies in cognitive sciences commonly applied principal component analysis (PCA) to truncate data dimensions when dealing with data with multiple dimensions. This is not necessarily because of its merit in terms of mathematical algorithm, but partly because it is easy to conduct with commonly accessible statistical software. On the other hand, dimension reduction might not be the best analysis when modeling data with no more than 20 dimensions. Using state-of-the-art techniques, researchers in various research disciplines (e.g., computer vision) classified data with more than hundreds of dimensions with neural networks and revealed the inner structure of the data. Therefore, it might be more sophisticated to process human perception data directly with neural networks. In this paper, we introduce the multi-dimensional data analysis platform (MuDAP), a powerful toolbox for data analysis in cognitive science. It utilizes artificial intelligence as well as network analysis, an analysis method that takes advantage of data symmetry. With the graphic user interface, a researcher, with or without previous experience, could analyze multiple dimensional data with great ease. [ABSTRACT FROM AUTHOR]

The ordered weighted averaging (OWA) operator was proposed by Yager back in 1988 and constitutes a parameterized family of aggregation functions between the minimum and the maximum. The purpose of this paper is to perform a bibliometric review of this aggregation operator during the last 35 years through the Web of Science (WoS) Core Collection database and the Visualization of Similarities (VOS) viewer software. The results show that the OWA operator is an increasingly popular aggregation operator, especially in Computer Science. The results also allow the assertion that Yager, as expected, is still the most influential and productive author. Moreover, the study reveals that institutions from over 80 countries have contributed to OWA research, highlighting the high presence of Chinese universities and the emergence of Pakistani ones. Other interesting findings are presented to provide a comprehensive and up-to-date analysis of the OWA operator literature. [ABSTRACT FROM AUTHOR]

Photonic crystals are periodic dielectric structures that possess a wealth of physical characteristics. Owing to the unique way they interact with the light, they provide new degrees of freedom to precisely modulate the electromagnetic fields, and have received extensive research in both academia and industry. At the same time, fueled by the advances in computer science, inverse design strategies are gradually being used to efficiently produce on-demand devices in various domains. As a result, the interdisciplinary area combining photonic crystals and inverse design emerges and flourishes. Here, we review the recent progress for the application of inverse design in photonic crystals. We start with a brief introduction of the background, then mainly discuss the optimizations of various physical properties of photonic crystals, from eigenproperties to response-based properties, and end up with an outlook for the future directions. Throughout the paper, we emphasize some insightful works and their design algorithms, and aim to give a guidance for readers in this emerging field. [ABSTRACT FROM AUTHOR]

Affective computing is a multidisciplinary field encompassing artificial intelligence, natural language processing, linguistics, computer science, and social sciences. This field aims to deepen our comprehension and capabilities by deploying inventive algorithms. This article presents a groundbreaking approach, the Cumulative Attribute-Weighted Graph Neural Network, which is innovatively designed to integrate trimodal textual, audio, and visual data from the two multimodal datasets. This method exemplifies its effectiveness in performing comprehensive multimodal sentiment analysis. Our methodology employs vocal inputs to generate speaker embeddings trimodal analysis. Using a weighted graph structure, our model facilitates the efficient integration of these diverse modalities. This approach underscores the interrelated aspects of various emotional indicators. The paper's significant contribution is underscored by its experimental results. Our novel algorithm achieved impressive performance metrics on the CMU-MOSI dataset, with an accuracy of 94% and precision, recall, and F1-scores above 92% for Negative, Neutral, and Positive emotion categories. Similarly, on the IEMOCAP dataset, the algorithm demonstrated its robustness with an overall accuracy of 93%, where exceptionally high precision and recall were noted in the Neutral and Positive categories. These results mark a notable advancement over existing state-of-the-art models, illustrating the potential of our approach in enhancing Sentiment Recognition through the synergistic use of trimodal data. This study's comprehensive analysis and significant results demonstrate the proposed algorithm's effectiveness in nuanced emotional state recognition and pave the way for future advancements in affective computing, emphasizing the value of integrating multimodal data for improved accuracy and robustness. [ABSTRACT FROM AUTHOR]

Community detection has been a subject of extensive research due to its broad applications across social media, computer science, biology, and complex systems. Modularity stands out as a predominant metric guiding community detection, with numerous algorithms aimed at maximizing modularity. However, modularity encounters a resolution limit problem when identifying small community structures. To tackle this challenge, this paper presents a novel approach by defining community structure information from the perspective of encoding edge information. This pioneering definition lays the foundation for the proposed fast community detection algorithm CSIM, boasting an average time complexity of only O (n log n) . Experimental results showcase that communities identified via the CSIM algorithm across various graph data types closely resemble ground truth community structures compared to those revealed via modularity-based algorithms. Furthermore, CSIM not only boasts lower time complexity than greedy algorithms optimizing community structure information but also achieves superior optimization results. Notably, in cyclic network graphs, CSIM surpasses modularity-based algorithms in effectively addressing the resolution limit problem. [ABSTRACT FROM AUTHOR]

There can be many reasons why students fail to answer correctly to summative tests in advanced computer science courses: often the cause is a lack of prerequisites or misconceptions about topics presented in previous courses. One of the ITiCSE 2020 working groups investigated the possibility of designing assessments suitable for differentiating between fragilities in prerequisites (in particular, knowledge and skills related to introductory programming courses) and advanced topics. This paper reports on an empirical evaluation of an instrument focusing on data structures, among those proposed by the ITiCSE working group. The evaluation aimed at understanding what fragile knowledge and skills the instrument is actually able to detect and to what extent it is able to differentiate them. Our results support that the instrument is able to distinguish between some specific fragilities (e.g., value vs. reference semantics), but not all of those claimed in the original report. In addition, our findings highlight the role of relevant skills at a level between prerequisite and advanced skills, such as program comprehension and reasoning about constraints. We also suggest ways to improve the questions in the instrument, both by improving the distractors of the multiple-choice questions, and by slightly changing the content or phrasing of the questions. We argue that these improvements will increase the effectiveness of the instrument in assessing prerequisites as a whole, but also to pinpoint specific fragilities. [ABSTRACT FROM AUTHOR]

The theory of Formal Concept Analysis (FCA) finds diverse applications in fields like knowledge extraction, cognitive concept learning and data mining. The construction of a concept lattice significantly influences the effectiveness of formal concept analysis; hence, the development of high-performance algorithms for concept construction is crucial. In this paper, we introduce a novel algorithm called "Bit-Close" for formal concept construction. Bit-Close leverages bit representation and operations, fundamental to computer science, to enhance the In-Close algorithm. Furthermore, we explore the parallel method of Bit-Close. Our experimental results, obtained from multiple public and random datasets, demonstrate that Bit-Close outperforms In-Close by approximately 20% and is significantly better than other competing algorithms. [ABSTRACT FROM AUTHOR]

The integration of biology, computer science, and statistics has given rise to the interdisciplinary field of bioinformatics, which aims to decode biological intricacies. It produces extensive and diverse features, presenting an enormous challenge in classifying bioinformatic problems. Therefore, an intelligent bioinformatics classification system must select the most relevant features to enhance machine learning performance. This paper proposes a feature selection model based on the fractal concept to improve the performance of intelligent systems in classifying high-dimensional biological problems. The proposed fractal feature selection (FFS) model divides features into blocks, measures the similarity between blocks using root mean square error (RMSE), and determines the importance of features based on low RMSE. The proposed FFS is tested and evaluated over ten high-dimensional bioinformatics datasets. The experiment results showed that the model significantly improved machine learning accuracy. The average accuracy rate was 79% with full features in machine learning algorithms, while FFS delivered promising results with an accuracy rate of 94%. [ABSTRACT FROM AUTHOR]

Since the Ronan Point collapse in the UK in 1968, the progressive collapse analysis of residential buildings has gradually drawn the attention of civil engineers and the scientific community. Recent advances in computer science and the development of new numerical methodologies allow us to perform high-fidelity collapse simulations. This paper assesses different scenarios that could have hypothetically caused the collapse of the Champlain Tower South Condo in Surfside, Florida, in 2021, one of the most catastrophic progressive collapse events that has ever occurred. The collapse analysis was performed using the latest developments in the Applied Element Method (AEM). A high-fidelity numerical model of the building was developed according to the actual structural drawings. Several different collapse hypotheses were examined, considering both column failures and degradation scenarios. The analyses showed that the failure of deep beams at the pool deck level, directly connected to the perimeter columns of the building, could have led to the columns' failure and subsequent collapse of the eastern wing of the building. The simulated scenario highlights the different stages of the collapse sequence and appears to be consistent with what can be observed in the footage of the actual collapse. To improve the performance of the structure against progressive collapse, two modifications to the original design of the building were introduced. From the analyses, it was found that disconnecting the pool deck beam from the perimeter columns could have been effective in preventing the local collapse of the pool deck slab from propagating to the rest of the building. Moreover, these analyses indicate that enhancing the torsional strength and stiffness of the core could have prevented the collapse of the eastern part of the building, given the assumptions and initiation scenarios considered. Building catastrophic collapses can cause significant lives and economic losses. Poor design and maintenance, in combination with aging, will more likely increase, in the next years, the number of buildings potentially vulnerable to the risk of collapse, due to either seismic, accidental, or degradation actions. This research focuses on the analysis of the Champlain Tower South condo collapse, which occurred in Surfside, Florida, in 2021. Different hypothetical collapse scenarios were simulated, comparing the analysis results with the actual evidence of the collapse. The analyses have shown that the degradation of the pool deck slab, due to corrosion, may have contributed to the collapse of the building. Finally, two different minor revisions of the original design of the building were analyzed to reduce the risk of failure and understand how the collapse of similar residential buildings could be prevented. [ABSTRACT FROM AUTHOR]

Machine learning (ML) methods are proliferating in scientific research. However, the adoption of these methods has been accompanied by failures of validity, reproducibility, and generalizability. These failures can hinder scientific progress, lead to false consensus around invalid claims, and undermine the credibility of ML-based science. ML methods are often applied and fail in similar ways across disciplines. Motivated by this observation, our goal is to provide clear recommendations for conducting and reporting ML-based science. Drawing from an extensive review of past literature, we present the REFORMS checklist (recommendations for machine-learning-based science). It consists of 32 questions and a paired set of guidelines. REFORMS was developed on the basis of a consensus of 19 researchers across computer science, data science, mathematics, social sciences, and biomedical sciences. REFORMS can serve as a resource for researchers when designing and implementing a study, for referees when reviewing papers, and for journals when enforcing standards for transparency and reproducibility. [ABSTRACT FROM AUTHOR]

Trust can be considered as a multidisciplinary concept, which is strongly related to the context and it falls in different fields such as Philosophy, Psychology or Computer Science. Trust is fundamental in every relationship, because without it, an entity will not interact with other entities. This aspect is very important especially in the Internet of Things (IoT), where many entities produced by different vendors and created for different purposes have to interact among them through the internet often under uncertainty. Trust can overcome this uncertainty, creating a strong basis to ease the process of interaction among these entities. We believe that considering trust in the IoT is fundamental, and in order to implement it in any IoT entity, it is fundamental to consider it through the whole System Development Life Cycle. In this paper, we propose an analysis of different works that consider trust for the IoT. We will focus especially on the analysis of frameworks that have been developed in order to include trust in the IoT. We will make a classification of them providing a set of parameters that we believe are fundamental in order to properly consider trust in the IoT. Thus, we will identify important aspects to be taken into consideration when developing frameworks that implement trust in the IoT, finding gaps and proposing possible solutions. [ABSTRACT FROM AUTHOR]

Large-scale benchmark datasets are crucial in advancing research within the computer science communities. They enable the development of more sophisticated AI models and serve as "golden" benchmarks for evaluating their performance. Thus, ensuring the quality of these datasets is of utmost importance for academic research and the progress of AI systems. For the emerging vision-language tasks, some datasets have been created and frequently used, such as Flickr30k, COCO, and NoCaps, which typically contain a large number of images paired with their ground-truth textual descriptions. In this paper, an automatic method is proposed to assess the quality of large-scale benchmark datasets designed for vision-language tasks. In particular, a new cross-modal matching model is developed, which is capable of automatically scoring the textual descriptions of visual images. Subsequently, this model is employed to evaluate the quality of vision-language datasets by automatically assigning a score to each 'ground-truth' description for every image picture. With a good agreement between manual and automated scoring results on the datasets, our findings reveal significant disparities in the quality of the ground-truth descriptions included in the benchmark datasets. Even more surprising, it is evident that a small portion of the descriptions are unsuitable for serving as reliable ground-truth references. These discoveries emphasize the need for careful utilization of these publicly accessible benchmark databases. [ABSTRACT FROM AUTHOR]

The large number of scientific publications around the world is increasing at a rate of approximately 4%–5% per year. This fact has resulted in the need for tools that deal with relevant and high-quality publications. To address this necessity, search and reference management tools that include some recommendation algorithms have been developed. However, many of these solutions are proprietary tools and the full potential of recommender systems is rarely exploited. There are some solutions which provide recommendations for specific domains, by using ad-hoc resources. Furthermore, some other systems do not consider any personalization strategy to generate the recommendations. This paper presents ArZiGo , a web-based full prototype system for the search, management, and recommendation of scientific articles, which feeds on the Semantic Scholar Open Research Corpus, a corpus that is growing continually with more than 190M papers from all fields of science so far. ArZiGo combines different recommendation approaches within a hybrid system, in a configurable way, to recommend those papers that best suit the preferences of the users. A group of 30 human experts has participated in the evaluation of 500 recommendations in 10 research areas, 7 of which belong to the area of Computer Science and 3 to the area of Medicine, obtaining quite satisfactory results. Besides the appropriateness of the articles recommended, the execution time of the implemented algorithms has also been analyzed. • A web system for the search, management, and recommendation of scientific articles. • A hybrid and multidisciplinary scientific article recommendation system. • A modular and scalable recommendation system. • Use of the Semantic Scholar Open Research Corpus as a corpus of articles. [ABSTRACT FROM AUTHOR]

The document is an editorial from the Bulletin of the Polish Academy of Sciences: Technical Sciences. It introduces a special section on IIoT (Industrial Internet of Things) and AI-based optimization. The aim of the section is to present the latest developments and applications in these areas, including methods and systems in IIoT, IoT infrastructure, and applications of AI in IoT. The topics covered align with current research trends in computer science, telecommunications, and mechanical engineering. The document also highlights the importance of integrating intelligent machines and systems in industry and the role of AI in solving complex problems. [Extracted from the article]

As the world grapples with the pressing challenge of environmental sustainability, the need for innovative solutions to combat air pollution has become paramount. Air pollution is a complex issue that necessitates real-time monitoring of pollution sources for effective mitigation. This paper explores the potential of swarm algorithms applied as a novel and efficient approach to address this critical environmental concern. Swarm algorithms offer a promising framework for coordinating fleets of drones to collaboratively monitor and analyze air pollution sources. The unique capabilities of drones, including their agility, accessibility, and versatility, make them ideal candidates for aerial data collection. When harnessed in a swarm, these drones can create a dynamic and adaptable network that provides a more comprehensive and fine-grained understanding of air pollution dynamics. This paper delves into the conceptual foundations of using swarm algorithms in drone-based air pollution monitoring.

The text is a foreword for a special issue of the Journal of Information Science & Engineering on Combinatorial Mathematics and Computational Theory. It explains that these fields have a significant impact on computer science, mathematics, and science in general. Combinatorial Mathematics involves the study of discrete objects and has applications in various areas, while Computational Theory focuses on studying algorithms and their efficiency. The text also mentions a symposium that was held to promote academic exchanges and advance research in these fields. The special issue includes four papers on topics such as opinion optimization, local diagnosis, enumerating furthest pairs, and determining the 2-tuple total domination number of a graph. The authors express gratitude to the reviewers and authors for their contributions to the special issue. [Extracted from the article]

Abstract A drug molecule is a substance that changes an organism’s mental or physical state. Every approved drug has an indication, which refers to the therapeutic use of that drug for treating a particular medical condition. While the Large Language Model (LLM), a generative Artificial Intelligence (AI) technique, has recently demonstrated effectiveness in translating between molecules and their textual descriptions, there remains a gap in research regarding their application in facilitating the translation between drug molecules and indications (which describes the disease, condition or symptoms for which the drug is used), or vice versa. Addressing this challenge could greatly benefit the drug discovery process. The capability of generating a drug from a given indication would allow for the discovery of drugs targeting specific diseases or targets and ultimately provide patients with better treatments. In this paper, we first propose a new task, the translation between drug molecules and corresponding indications, and then test existing LLMs on this new task. Specifically, we consider nine variations of the T5 LLM and evaluate them on two public datasets obtained from ChEMBL and DrugBank. Our experiments show the early results of using LLMs for this task and provide a perspective on the state-of-the-art. We also emphasize the current limitations and discuss future work that has the potential to improve the performance on this task. The creation of molecules from indications, or vice versa, will allow for more efficient targeting of diseases and significantly reduce the cost of drug discovery, with the potential to revolutionize the field of drug discovery in the era of generative AI.

In natural language processing (NLP), transformer based models have surpassed recurrent neural networks (RNN) as state of the art, being introduced specifically to address the limitations of RNNs originating from its sequential nature. As a similar sequence modeling problem, transformer methods can be readily adapted for deep learning time series prediction. This paper proposes a sparse transformer based approach for electricity load prediction. The layers of a transformer addresses the shortcomings of RNNs and CNNs by applying the attention mechanism on the entire time series, allowing any data point in the input to influence any location in the output of the layer. This allows transformers to incorporate information from the entire sequence in a single layer. Attention computations can also be parallelized. Thus, transformers can achieve faster speeds, or trade this speed for more layers and increased complexity. In experiments on public datasets, the sparse transformer attained comparable accuracy to an RNN-based SOTA method (Liu et al., 2022) while being up to 5× faster during inference. Moreover, the proposed model is general enough to forecast the load from individual households to city levels as shown in the extensive experiments conducted. [ABSTRACT FROM AUTHOR]

We report the results of a 4800-respondent survey among students at a technical university regarding their usage of artificial intelligence tools, as well as their expectations and attitudes about these tools. We find that many students have come to differentiated and thoughtful views and decisions regarding the use of artificial intelligence. The majority of students wishes AI to be integrated into their studies, and several wish that the university would provide tools that are based on reliable, university-level materials. We find that acceptance of and attitudes about artificial intelligence vary across academic disciplines. We also find gender differences in the responses, which however are smaller the closer the student's major is to informatics (computer science). [ABSTRACT FROM AUTHOR]

This interview was given in 2008 by Arkady Zakrevsky (1928–2014), Corresponding Member of the National Academy of Sciences of Belarus (1972), Doctor of Technical Sciences (1967), and Professor (1969). He stood at the origins of the birth of cybernetics in the Soviet Union. He proposed the programming language for logical tasks LYaPAS, on the basis of which a series of computer-aided design systems for discrete devices was created, and methods for implementing parallel algorithms for the logical control of interacting processes. Some monographs: LYaPAS: A Programming Language for Logic and Coding Algorithms (N.-Y., L.: Academic Press, 1969; with M. A. Gavrilov); Boolesche Gleichungen: Theorie, Anwendung, Algorithmen (Berlin: VEB Verlag Technik, 1984; with Dieter Bochmann and Christian Posthoff); Combinatorial Algorithms of Discrete Mathematics (Tallinn: TUT Press, 2008; with Yu. Pottosin, L. Cheremisinova); Optimization in Boolean Space (Tallinn: TUT Press, 2009; with Yu. Pottosin, L. Cheremisinova); Design of Logical Control Devices (Tallinn: TUT Press, 2009; with Yu. Pottosin, L. Cheremisinova); Combinatorial Calculations in Many-Dimensional Boolean Space (Tallinn: TUT Press, 2012); Solving Large Systems Logical Equations (Tallinn: TUT Press, 2013). [ABSTRACT FROM AUTHOR]

This article explores the impact of automation on environmental sensing, focusing on advanced technologies that revolutionize data collection analysis and monitoring. The International Union of Pure and Applied Chemistry (IUPAC) defines automation as integrating hardware and software components into modern analytical systems. Advancements in electronics, computer science, and robotics drive the evolution of automated sensing systems, overcoming traditional limitations in manual data collection. Environmental sensor networks (ESNs) address challenges in weather constraints and cost considerations, providing high-quality time-series data, although issues in interoperability, calibration, communication, and longevity persist. Unmanned Aerial Systems (UASs), particularly unmanned aerial vehicles (UAVs), play an important role in environmental monitoring due to their versatility and cost-effectiveness. Despite challenges in regulatory compliance and technical limitations, UAVs offer detailed spatial and temporal information. Pollution monitoring faces challenges related to high costs and maintenance requirements, prompting the exploration of cost-efficient alternatives. Smart agriculture encounters hurdle in data integration, interoperability, device durability in adverse weather conditions, and cybersecurity threats, necessitating privacy-preserving techniques and federated learning approaches. Financial barriers, including hardware costs and ongoing maintenance, impede the widespread adoption of smart technology in agriculture. Integrating robotics, notably underwater vehicles, proves indispensable in various environmental monitoring applications, providing accurate data in challenging conditions. This review details the significant role of transfer learning and edge computing, which are integral components of robotics and wireless monitoring frameworks. These advancements aid in overcoming challenges in environmental sensing, underscoring the ongoing necessity for research and innovation to enhance monitoring solutions. Some state-of-the-art frameworks and datasets are analyzed to provide a comprehensive review on the basic steps involved in the automation of environmental sensing applications. [ABSTRACT FROM AUTHOR]

In human-human and human-robot interaction, the counterpart influences the human's affective state. Contrary to humans, robots inherently cannot respond empathically, meaning non-beneficial affective reactions cannot be mitigated. Thus, to create a responsible and empathetic human-robot interaction (HRI), involving anthropomorphic service robots, the effect of robot behavior on human affect in HRI must be understood. To contribute to this understanding, we provide the new comprehensive data set AFFECT-HRI, including, for the first time, physiological data labeled with human affect (i.e., emotions and mood) gathered from a conducted HRI study. Within the study, 146 participants interacted with an anthropomorphic service robot in a realistic and complex retail scenario. The participants' questionnaire ratings regarding affect, demographics, and socio-technical ratings are provided in the data set. Five different conditions (i.e., neutral, transparency, liability, moral, and immoral) were considered during the study, eliciting different affective reactions and allowing interdisciplinary investigations (e.g., computer science, law, and psychology). Each condition includes three scenes: a consultation regarding products, a request for sensitive personal information, and a handover. [ABSTRACT FROM AUTHOR]

In academia, it is rare for an event or issue to foster the extensive participation of multiple disciplines. Research related to COVID-19 has undeniably yielded a wealth of valuable insights and impetus for the progress of interdisciplinary research, encompassing concepts, methodologies, intellectual approaches, theories, frameworks, data integration and analysis, and pertinent considerations. In the academic community, there is a widespread expectation that as science and technology continue to progress, the convergence of medicine with various other fields will gain momentum. Fields like computer science are anticipated to see expanded applications in domains such as medicine, vaccine research, disease diagnosis, and more. This study aims to examine interdisciplinary approaches in health-related research, particularly in the context of COVID-19. The goal is to analyze and comprehend the involvement and collaboration patterns of various disciplines in pandemic research, with a specific emphasis on the role and integration level of computer science. This study analyzed 240,509 COVID-19 related articles published from December 2019 to September 2022 using methods such as chord diagrams, modularity analysis, and eigenvector centrality analysis in Social Networking Analysis (SNA). The findings revealed an emerging trend of integration trend between Humanities & Social Sciences and Natural Sciences. Expectations that computer science would prominently feature in pandemic research during this technology-driven era haven't materialized. While it maintains links with engineering, it hasn't formed strong connections with medicine. This indicates a gap between computer science and core medical research in large-scale health crises, where COVID-19 research remains centered on medicine with varying interdisciplinary collaboration, and high-tech disciplines like computer science have not achieved their expected influence in these studies. [ABSTRACT FROM AUTHOR]

A new algorithm is presented for detecting the local weak reflection symmetries in raster images. It uses contours extracted from the segmented image. A convex hull is constructed on the contours, and so-called anchor points are placed on it. The bundles of symmetry line candidates are placed in these points. Each line splits the plane into two open half-planes and arranges the contours into three sets: the first contains the contours pierced by the considered line, while the second and the third include the contours located in one or the other half-plane. The contours are then checked for the reflection symmetry. This means looking for self-symmetries in the first set, and symmetric pairs with one contour in the second set and one contour in the third set. The line which is evaluated as the best symmetry line is selected. After that, the symmetric contours are removed from sets two and three. The remaining contours are then checked again for symmetry. A multi-branch tree representing the hierarchy of the detected local symmetries is the result of the algorithm. [ABSTRACT FROM AUTHOR]

The relationship between philosophy and science has always been complementary. Today, while science moves increasingly fast and philosophy shows some problems in catching up with it, it is not always possible to ignore such relationships, especially in some disciplines such as philosophy of mind, cognitive science, and neuroscience. However, the methodological procedures used to analyze these data are based on principles and assumptions that require a profound dialogue between philosophy and science. Following these ideas, this work aims to raise the problems that a classical connectionist theory can cause and problematize them in a cognitive framework, considering both philosophy and cognitive sciences but also the disciplines that are near to them, such as AI, computer sciences, and linguistics. For this reason, we embarked on an analysis of both the computational and theoretical problems that connectionism currently has. The second aim of this work is to advocate for collaboration between neuroscience and philosophy of mind because the promotion of deeper multidisciplinarity seems necessary in order to solve connectionism's problems. In fact, we believe that the problems that we detected can be solved by a thorough investigation at both a theoretical and an empirical level, and they do not represent an impasse but rather a starting point from which connectionism should learn and be updated while keeping its original and profoundly convincing core. [ABSTRACT FROM AUTHOR]

A critical worldwide problem is that ransomware cyberattacks can be costly to organizations. Moreover, accidental employee cybercrime risk can be challenging to prevent, even by leveraging advanced computer science techniques. This exploratory project used a novel cognitive computing design with detailed explanations of the action-research case-study methodology and customized machine learning (ML) techniques, supplemented by a workflow diagram. The ML techniques included language preprocessing, normalization, tokenization, keyword association analytics, learning tree analysis, credibility/reliability/validity checks, heatmaps, and scatter plots. The author analyzed over 8 GB of employee behavior big data from a multinational Fintech company global intranet. The five-factor personality theory (FFPT) from the psychology discipline was integrated into semi-supervised ML to classify retrospective employee behavior and then identify cybercrime risk. Higher levels of employee neuroticism were associated with a greater organizational cybercrime risk, corroborating the findings in empirical publications. In stark contrast to the literature, an openness to new experiences was inversely related to cybercrime risk. The other FFPT factors, conscientiousness, agreeableness, and extroversion, had no informative association with cybercrime risk. This study introduced an interdisciplinary paradigm shift for big data cognitive computing by illustrating how to integrate a proven scientific construct into ML—personality theory from the psychology discipline—to analyze human behavior using a retrospective big data collection approach that was asserted to be more efficient, reliable, and valid as compared to traditional methods like surveys or interviews. [ABSTRACT FROM AUTHOR]