Journal Cover
Studia Universitatis Babeș-Bolyai Informatica
Number of Followers: 0  

  This is an Open Access Journal Open Access journal
ISSN (Print) 1224-869X - ISSN (Online) 2065-9601
Published by Babes-Bolyai University Homepage  [4 journals]
  • Extended Mammogram Classification From Textural Features

    • Authors: A Bajcsi, C. Chira, A Andreica
      Pages: 5 - 20
      Abstract: The efficient analysis of digital mammograms has an important role in the early detection of breast cancer and can lead to a higher percentage of recovery. This paper presents an extended computer-aided diagnosis system for the classification of mammograms into three classes (normal, benign and malignant). The performance of the system is evaluated for two different mammogram databases (MIAS and DDSM) in order to assess its robustness. We discuss the changes required in the system, particularly at the level of the image preprocessing and feature extraction. Computational experiments are performed based on different methods for feature extraction, selection and classification. The results indicate an accuracy of 66.95% for the MIAS dataset and 54.1% for DDSM obtained using genetic algorithm based feature selection and Random Forest classification.
      PubDate: 2023-02-06
      DOI: 10.24193/subbi.2022.2.01
      Issue No: Vol. 67, No. 2 (2023)
       
  • Feasibility of using machine learning algorithms for yield prediction of
           corn and sunflower crops based on seeding date

    • Authors: A.D. Călin, H.-B. Mureșan, A.-M. Coroiu
      Pages: 21 - 36
      Abstract: In this research, our objective is to identify the relationship between the date of seeding and the production of corn and sunflower crops. We evaluated the feasibility of using prediction models on a dataset of annual average crop yields and information on plant phenology, from several states of the US. After performing data analysis and preprocessing, we trained a selection of regression models. The best results were obtained for corn using HistGradientRegressor and XGBRegressor with  R^2=0.969 for both algorithms and MAE % = 8.945%, respectively MAE% = 9.423%. These results demonstrate a good potential for the problem of yield prediction based on year, state, average plating day, and crop type. This model will be further used, combined with meteorological data, to build an agricultural crop prediction model.
      PubDate: 2023-02-06
      DOI: 10.24193/subbi.2022.2.02
      Issue No: Vol. 67, No. 2 (2023)
       
  • Coroutines Comunications. Design and Implementation Issues in C++20

    • Authors: Radu Lupșa, Dana Lupșa
      Pages: 37 - 48
      Abstract: This paper explores the communication mechanisms and patterns available to coroutines to cooperate with one another. It investigates the issues in designing and implementing a framework for using C++20 coroutines effectively, for generators, asynchronous function calls, and especially asynchronous generators.
      PubDate: 2023-04-08
      DOI: 10.24193/subbi.2022.2.03
      Issue No: Vol. 67, No. 2 (2023)
       
  • Examining the Social Behavior of Ant Colonies Using Complex Networks

    • Authors: B. Mursa
      Pages: 49 - 64
      Abstract: This paper proposes the use of Complex Network Theory to model the interactions between ants and analyze their social behavior. Specifically, the study focuses on six colonies of ants to investigate whether their behavior is community-oriented or individual-oriented. The research employs various nodes properties that define nodes’ importance to quantify the existence of a social or individual-oriented behavior. The results aim to provide insights into the social behavior of ants and may have implications for understanding other complex social systems.
      PubDate: 2023-05-16
      DOI: 10.24193/subbi.2022.2.04
      Issue No: Vol. 67, No. 2 (2023)
       
  • Comparison of Data Models For Unsupervised Twitter Sentiment Analysis

    • Authors: S. Limboi
      Pages: 65 - 80
      Abstract: Identifying the sentiment of collected tweets has become a challenging and interesting task. In addition, mining and defining relevant features that can improve the quality of a classification system is crucial. The data modeling phase is fundamental for the whole process since it can reveal hidden information from the textual inputs. Two models are defined in the presented paper, considering Twitter-specific concepts: a hashtag-based representation and a text-based one. These models will be compared and integrated into an unsupervised system that determines groups of tweets based on sentiment labels (positive and negative). Moreover, word-embedding techniques (TF-IDF and frequency vectors) are used to convert the representations into a numeric input needed for the clustering methods.  The experimental results show good values for Silhouette and Davies-Bouldin measures in the unsupervised environment. A detailed investigation is presented considering several items (dataset, clustering method, data representation, or word embeddings) for checking the best setup for increasing the quality of detecting the sentiment from Twitter’s messages. The analysis and conclusions show that the first results can be considered for more complex experiments
      PubDate: 2023-05-16
      DOI: 10.24193/subbi.2022.2.05
      Issue No: Vol. 67, No. 2 (2023)
       
 
JournalTOCs
School of Mathematical and Computer Sciences
Heriot-Watt University
Edinburgh, EH14 4AS, UK
Email: journaltocs@hw.ac.uk
Tel: +00 44 (0)131 4513762
 


Your IP address: 34.239.148.127
 
Home (Search)
API
About JournalTOCs
News (blog, publications)
JournalTOCs on Twitter   JournalTOCs on Facebook

JournalTOCs © 2009-