Wyniki wyszukiwania - BazTech

1

Adaptive modeling algorithm for energy optimization in nanosensor networks for smart IoT systems

Wiliński Artur, Datta Amitava, Kubica Bartłomiej

Advances in Science and Technology. Research Journal

|

2025

|

Vol. 19, no. 11

292--306

EN

Efficient energy management in nanosensor networks remains a challenge in the design of intelligent IoT systems. This study proposes an Adaptive Modeling Algorithm (NAMA) that dynamically adjusts the trade-off between energy consumption and stability in real-time nanosensor systems. The algorithm utilizes an energy-aware cost function combining total energy usage with a tunable parameter λ(t) that is adapted based on consumption thresholds. The research focuses on a sensor network model distributed across the artificial skin of a robotic system, consisting of nanosensors operating in the terahertz (THz) band. The model incorporates integral metrics to evaluate transmission, reception, and sensing power costs, and applies adaptive control rules, such as transmission suppression or reactive cut-off, to minimize global energy usage. Simulation results demonstrate that the NAMA achieves reduction in energy variance and over 11% extension of operational lifetime, compared to fixed-weight energy strategies, measured at the 80% cumulative energy threshold. Moreover, under a realistic energy-per-operation cost of 1 μJ, the adaptive algorithm enables the system to execute over 23,000 operations, with more than 26,000 operations remaining within a 50 mJ energy limit. This confirms the algorithm’s capability to efficiently manage energy distribution while preserving network longevity. The adaptive trade-off coefficient

2

Influence of the radiofrequency applicators arrangement on the sizes of ablative zones inside hepatic tumor

Gas Piotr, Miaskowski Arkadiusz

Archives of Electrical Engineering

|

2024

|

Vol. 73, nr 3

557--571

EN

Radiofrequency (RF) ablation is a popular therapeutic technique for heating solid tumors that are medically unsuitable for resection or other treatments. Thermal ablation applicators create high-frequency electromagnetic fields (EMFs) within the tumor site, which causes heating, coagulation, and ultimately death of the cancer cells. The aim of this study is the numerical analysis of the temperature distributions, ablation zones, and specific absorption rates (SAR) during RF ablation in relation to an ellipsoidal shaped tumor placed in the model of liver tissue. The source of heat is a three-element system of RF needle applicators operating at a frequency 100 kHz, with a given electrode potential, inserted into the tumor. In order to obtain an appropriate temperature distribution in the target area, the Laplace equation coupled with the Pennes equation were solved using the finite element method (FEM). The arrangement effect of three needle-type applicators on the resultant thermal profiles and the volumes of ablation zones were analyzed and compared. In addition, the ablation zones for various angles of the RF applicator placed in the center of the tumor were analyzed. The paper shows that in order to control temperature distribution and ablation zones the proposed system of RF applicators and the arrangement of electrodes can be successfully applied in hepatocellular carcinoma treatment.

3

SrpCNNeL: Serbian Model for Named Entity Linking

Ikonić Nešić Milica, Petalinkar Saša, Stanković Ranka, Utvić Miloš, Kitanović Olivera

Annals of Computer Science and Information Systems

|

2024

|

Vol. 39

465--473

EN

This paper presents the development of a Named Entity Linking (NEL) model to the Wikidata knowledge base for the Serbian language named SrpCNNeL. The model was trained to recognize and link seven different named entity types (persons, locations, organisations, professions, events, demonyms, and works of art) on the dataset containing sentences from novels, legal documents, as also sentences generated from the Wikidata knowledge base and Leximirka lexical database. The resulting model demonstrated robust performance, achieving an F1 score of 0.8 on the test set. Considering that the dataset contains the highest number of locations linked to the knowledge base, an evaluation was conducted on an independent dataset and compared to the baseline Spacy Entity Linker for locations only.

4

Key Factors Influencing Mobile Banking Adoption in Saudi Arabia

Alzahrani Amal, Beloff Natalia, White Martin

Annals of Computer Science and Information Systems

|

2024

|

Vol. 39

531--536

EN

The introduction of mobile banking has revolutionized traditional financial practices, enhancing efficiency, customer experiences, and business models globally. Despite these advancements, mobile banking adoption remains low in Saudi Arabia. This paper seeks to fill this gap by examining the significance of factors that either drive or hinder adoption. We propose a novel model integrating factors from the DeLone and McLean (D&M) model and factors from the Unified Theory of Acceptance and Use of Technology (UTAUT2) model, complemented by additional factors. Quantitative data was collected through online questionnaire from a diverse sample of Saudi banking customers, supplemented by qualitative insights from customer interviews. Findings revealed that net benefits, compatibility, facilitating conditions, and trust positively influence adoption, while literacy levels and digital skills pose barriers. Our study offers a significant theoretical contribution by synthesizing multiple models and enriches understanding of mobile banking adoption, aiding future research and industry decision making.

5

Decoding Financial Data: Machine Learning Approach to Predict Trading Actions

Fung Yat Chun, Amonov Bekzod

Annals of Computer Science and Information Systems

|

2024

|

Vol. 39

739--744

EN

This paper presents a study on predicting stock trends using a dataset consisting of key financial indicators from 300 S&P 500 companies over a decade. Each company is characterized by 58 financial indicators along with their 1-year changes, offering valuable insights into potential trends. The objective is to develop predictive models to accurately forecast trading actions (buy, sell, hold) based on fundamental financial data. Three machine learning models---Random Forest, CatBoost, and XGBoost classifiers---were trained, employing two distinct voting mechanisms. The first voting mechanism was utilized in the competition, while the second was developed post-competition after the test labels were released. Notably, the second model was trained solely on the training data. The results demonstrate that both voting mechanisms effectively capture trends, as reflected by the average error cost measure, evaluated using the provided error cost matrix.

6

Automatic Generation of OpenCL Code through Polyhedral Compilation with LLM

Palkowski Marek, Grużewski Mateusz

Annals of Computer Science and Information Systems

|

2024

|

Vol. 39

671--676

EN

In recent years, a multitude of AI solutions has emerged to facilitate code generation, commonly known as Language Model-based Programming (LLM). These tools empower programmers to automate their work. Automatic programming also falls within the domain of optimizing compilers, primarily based on the polyhedral model, which processes loop nests concentrating most computations. This article focuses on harnessing LLM tools to generate OpenCL code for non-serial polyadic dynamic programming kernels. We have chosen the Nussinov RNA folding computational task, previously employed to test polyhedral compilers in optimizing kernels with non-uniform dependences. The code generated in OpenMP by polyhedral optimizers is limited to CPU computations. We automatically convert it into the OpenCL standard using ChatGPT-3.5 through its source-to-source queries to extend the number of possible platforms. The validity and efficiency of the generated code were verified on various CPUs and GPUs from different manufacturers.

7

AI-Based Spatiotemporal Crop Monitoring by Cloud Removal in Satellite Images

Pihrt Jiří, Šimánek Petr, Kovalenko Alexander, Kvapil Jiří, Charvát Karel

Annals of Computer Science and Information Systems

|

2024

|

Vol. 39

485--492

EN

Efficient crop monitoring and crop dynamics fore- casting leveraging diverse satellite and point data are described. Attention-based architecture architecture is adapted for mono- temporal cloud removal which overcomes an issue of crop monitoring. Combining optical (Sentinel-2) and radar (Sentinel-1) satellite data improves the robustness and accuracy of the model in terms of satellite image reconstruction and normalized difference vegetation index prediction and forecasting. However, available soil-type geographical data and land surface analysis products, do not improve prediction accuracy significantly.

8

A network clustering method based on intersection of random spanning trees

Hajdu László, London András, Pluhár András

Annals of Computer Science and Information Systems

|

2024

|

Vol. 39

609--614

EN

We use a special edge centrality measure for node clustering in complex networks. The measure is based on the `spanning tree intersection' value motivated by previous work on the intersection and minimum expected overlap of random spanning trees in complex networks. First, we show that this new metric differs from some well-known edge centralities on random network models and real-world networks. Then, we show the applicability of the metric for clustering the nodes and point out some advantages over some other edge centrality based hierarchical clustering methods.

9

Towards automated detection of adversarial attacks on tabular data

Biczyk Piotr, Wawrowski Łukasz

Annals of Computer Science and Information Systems

|

2023

|

Vol. 35

247--251

EN

The paper presents a novel approach to investigating adversarial attacks on machine learning classification models operating on tabular data. The employed method involves using diagnostic parameters calculated on an approximated representation of a model under attack and analyzing differences in these diagnostic parameters over time. The hypothesis researched by the authors is that adversarial attack techniques, even if attempting a low-profile modification of input data, influence those diagnostic attributes in a statistically significant way. Thus, changes in diagnostic attributes can be used for detecting attack events. Three attack approaches on real-world datasets were investigated. The experiments confirm the approach as a promising technique to be further developed for detecting adversarial attacks.

10

Reranking for a Polish Medical Search Engine

Pokrywka Jakub, Jassem Krzysztof, Wierzchoń Piotr, Badylak Piotr, Kurzyp Grzegorz

Annals of Computer Science and Information Systems

|

2023

|

Vol. 35

297--302

EN

Healthcare professionals are often overworked, which may impair their efficacy. Text search engines may facilitate their work. However, before making health decisions, it is important for a medical professional to consult verified sources rather than unknown web pages. In this work, we present our approach for creating a text search engine based on verified resources in the Polish language, dedicated to medical workers. This consists of collecting and comprehensively analyzing texts annotated by medical professionals and evaluating various neural reranking models. During the annotation process, we differentiate between an abstract information need and a search query. Our study shows that even within a group of trained medical specialists there is extensive disagreement on the relevance of a document to the information need. We prove that available multilingual rerankers trained in the zero-shot setup are effective for the Polish language in searches initiated by both natural language expressions and keyword search queries.

11

Open Vocabulary Keyword Spotting with Small-Footprint ASR-based Architecture and Language Models

Pudo Mikołaj, Wosik Mateusz, Janicki Artur

Annals of Computer Science and Information Systems

|

2023

|

Vol. 35

657--666

EN

We present the results of experiments on minimizing the model size for the text-based Open Vocabulary Keyword Spotting task. The main goal is to perform inference on devices with limited computing power, such as mobile phones. Our solution is based on the acoustic model architecture adopted from the automatic speech recognition task. We extend the acoustic model with a simple yet powerful language model, which improves recognition results without impacting latency and memory footprint. We also present a method to improve the recognition rate of rare keywords based on the recordings generated by a text-to-speech system. Evaluations using a public testset prove that our solution can achieve a true positive rate in the range of 73%-86%, with a false positive rate below 24%. The model size is only 3.2 MB, and the real-time factor measured on contemporary mobile phones is 0.05.

12

One-shot federated learning with self-adversarial data

Danilenka Anastasiya, Bogacka Karolina, Wasielewska-Michniewska Katarzyna

Annals of Computer Science and Information Systems

|

2023

|

Vol. 35

919--924

EN

Federated learning (FL) is a decentralized approach that aims at training a global model with the help of multiple devices, without collecting or revealing individual clients' data. The training of a federated model is conducted in communication rounds. Still, in certain scenarios, numerous communication rounds are impossible to perform. In such cases, a one-shot FL is utilized, where the number of communication rounds is limited to one. In this article, the idea of one-shot FL is enhanced with the usage of adversarial data, exploring and illustrating the possibilities to improve the performance of resulting global models, including scenarios with non-IID data, for image classification datasets: MNIST and CIFAR-10.

13

Measuring Trustworthiness in Neuro-Symbolic Integration

Agiollo Andrea, Omicini Andrea

Annals of Computer Science and Information Systems

|

2023

|

Vol. 35

1--10

EN

Neuro-symbolic integration of symbolic and subsymbolic techniques represents a fast-growing AI trend aimed at mitigating the issues of neural networks in terms of decision processes, reasoning, and interpretability. Several state-of-the-art neuro-symbolic approaches aim at improving performance, most of them focusing on proving their effectiveness in terms of raw predictive performance and/or reasoning capabilities. Meanwhile, few efforts have been devoted to increasing model trustworthiness, interpretability, and efficiency - mostly due to the complexity of measuring effectively improvements in terms of trustworthiness and interpretability. This is why here we analyse and discuss the need for ad-hoc trustworthiness metrics for neuro-symbolic techniques. We focus on two popular paradigms mixing subsymbolic computation and symbolic knowledge, namely: (i) symbolic knowledge extraction (SKE), aimed at mapping subsymbolic models into human-interpretable knowledge bases; and (ii) symbolic knowledge injection (SKI), aimed at forcing subsymbolic models to adhere to a given symbolic knowledge. We first emphasise the need for assessing neuro-symbolic approaches from a trustworthiness perspective, highlighting the research challenges linked with this evaluation and the need for ad-hoc trust definitions. Then we summarise recent developments in SKE and SKI metrics focusing specifically on several trustworthiness pillars such as interpretability, efficiency, and robustness of neuro-symbolic methods. Finally, we highlight open research opportunities towards reliable and flexible trustworthiness metrics for neuro-symbolic integration.

14

Improving the Efficiency of Meta AutoML via Rule-based Training Strategies

Zender Alexander, Humm Bernhard G., Pachmann Tim

Annals of Computer Science and Information Systems

|

2023

|

Vol. 35

235--246

EN

Meta Automated Machine Learning (Meta AutoML) platforms support data scientists and domain experts by automating the ML model search. A Meta AutoML platform utilizes multiple AutoML solutions searching in parallel for their best ML model. Using multiple AutoML solutions requires a substantial amount of energy. While AutoML solutions utilize different training strategies to optimize their energy efficiency and ML model effectiveness, no research has yet addressed optimizing the Meta AutoML process. This paper presents a survey of 14 AutoML training strategies that can be applied to Meta AutoML. The survey categorizes these strategies by their broader goal, their advantage and Meta AutoML adaptability. This paper also introduces the concept of rule-based training strategies and a proof-of-concept implementation in the Meta AutoML platform OMA-ML. This concept is based on the blackboard architecture and uses a rule-based reasoner system to apply training strategies. Applying the training strategy "top-3" can save up to 70% of energy, while maintaining a similar ML model performance.

15

Improving Domain-Specific Retrieval by NLI Fine-Tuning

Dušek Roman, Galias Christopher, Wojciechowska Lidia, Wawer Aleksander

Annals of Computer Science and Information Systems

|

2023

|

Vol. 35

949--953

EN

The aim of this article is to investigate the fine-tuning potential of natural language inference (NLI) data to improve information retrieval and ranking. We demonstrate this for both English and Polish languages, using data from one of the largest Polish e-commerce sites and selected open-domain datasets. We employ both monolingual and multilingual sentence encoders fine-tuned by a supervised method utilizing contrastive loss and NLI data. Our results point to the fact that NLI fine-tuning increases the performance of the models in both tasks and both languages, with the potential to improve mono- and multilingual models. Finally, we investigate uniformity and alignment of the embeddings to explain the effect of NLI-based fine-tuning for out-of-domain use-case.

16

Exception Handling in Programmable Controllers with Denotational Model

Sadolewski Jan, Trybus Bartosz

Annals of Computer Science and Information Systems

|

2023

|

Vol. 35

721--730

EN

The paper introduces a customized approach to handle failures in IEC 61131-3 programmable controllers. The solution assumes the utilization of a virtual machine as a runtime environment to execute control code in an isolated manner. A formal model of the runtime is presented, employing denotational semantics. Subsequently, the model is expanded by incorporating new procedures that enable the handling of runtime exceptions using ST code constructs. This formal model serves as the foundation for implementing the exception infrastructure in the CPDev development environment. The research presented in the paper, driven by industry demands, aims to facilitate the development of more reliable and resilient control systems, capable of effectively dealing with failures.

17

Defect Backlog Size Prediction for Open-Source Projects with the Autoregressive Moving Average and Exponential Smoothing Models

Anioła Paulina, Pandey Sushant Kumar, Staron Miroslaw, Ochodek Mirosław

Annals of Computer Science and Information Systems

|

2023

|

Vol. 35

83--92

EN

Context: predicting the number of defects in a defect backlog in a given time horizon can help allocate project resources and organize software development. Goal: to compare the accuracy of three defect backlog prediction methods in the context of large open-source (OSS) projects, i.e., ARIMA, Exponential Smoothing (ETS), and the state-of-the-art method developed at Ericsson AB (SM). Method: we perform a simulation study on a sample of 20 open-source projects to compare the prediction accuracy of the methods. Also, we use the Na\"{\i}ve prediction method as a baseline for sanity check. We use statistical inference tests and effect size coefficients to compare the prediction errors. Results: ARIMA, ETS, and SM were more accurate than the Na\"{\i}ve method. Also, the prediction errors were statistically lower for ETS than for SM (however, the effect size was negligible). Conclusions: ETS seems slightly more accurate than SM when predicting defect backlog size of OSS projects.

18

Continual learning of a time series model using a mixture of HMMs with application to the IoT fuel sensor verification

Głomb Przemysław, Cholewa Michał, Foszner Paweł, Bularz Jakub

Annals of Computer Science and Information Systems

|

2023

|

Vol. 35

259--264

EN

This paper presents an application of a mixture of Hidden Markov Models (HMMs) as a tool for verification of IoT fuel sensors. The IoT fuel sensors report the level of fuel in tanks of a petrol station, and are a key component for monitoring system reliability (billing), safety (fuel/oil leak detection) and security (theft prevention). We propose an algorithm for learning a mixture of HMMs based on a continual learning principle, i.e. it adapts the model while monitoring a sensor over time, signalling unexpected or anomalous sensor reports. We have tested the proposed approach on a real-life data of 15 fuel tanks being monitored with the FuelPrime system, where it has shown a very good performance (average area under ROC curve of 0.94) of detecting anomalies in the sensor data. Additionally we show that the proposed method can be used for trend monitoring and present qualitative analysis of the short and long term learning performance. The proposed method has promising performance score, the resulting model has a high degree of explainability, limited memory and computation requirements and can be easily generalized to other domains of sensor verification.

19

Classifying Speech Acts in Political Communication: A Transformer-based Approach with Weak Supervision and Active Learning

Schmidt Klaus, Niekler Andreas, Kantner Cathleen, Burghardt Manuel

Annals of Computer Science and Information Systems

|

2023

|

Vol. 35

739--748

EN

We present a study on the automatic classification of speech acts in the domain of political communication, based on J. R. Searle's classification of illocutionary acts. Our research involves creating a dataset using the US State of the Union corpus and the UN General Debate corpus (UNGD) as data sources. To overcome limited labeled data, we employ a combination of weak supervision and active learning techniques for dataset creation and model training. Through various experiments, we investigate the influence of external and internal factors on speech act classification. In addition, we discuss the potential for further analysis of speech act usage, using the trained model on the UNGD corpus. The findings demonstrate the effectiveness of Transformer-based models for automatic speech act classification, highlight the benefits of weak supervision and active learning for dataset creation and model training, and underscore the potential for large-scale statistical analysis of speech act usage in the domain of political communication.

20

Classifying Industrial Sectors from German Textual Data with a Domain Adapted Transformer

Fechner Richard, Dörpinghaus Jens, Firll Anja

Annals of Computer Science and Information Systems

|

2023

|

Vol. 35

463--470

EN

For economics and sociological research, lists of industries and their branches are widely used in research to categorize data and get an overview on different types of industries. However, many different taxonomies and ordering schema exist, due to different research focus but also due to different national scenarios and interests. In this paper, we will focus without loss of generality on regional data from Germany. Manual annotation of textual data is time-consuming and tedious, naturally giving rise to our initial research question, also highly inspired by questions from computational social sciences: How can we automatically categorize textual data, e.g. job advertisements or business profiles, by industrial sectors? We will present an approach towards classification using a pre-trained domain-adapted Transformer model. We find that domain-adapted models generalize better and outperform state of the art non domain-adapted Transformer models on Out-Of-Distribution data. Additionally, we open source two novel data-sets mapping textual data to WZ2008 sections and divisions, enabling further research.