Search

Search Results

• LSI with Support Vector Machine for Text Categorization – a practical example with Python

  18-29

  Joao Henrique Gomes Da Costa Cavalcanti

  József Menyhárt

  Views:

  443

  Artificial intelligence is becoming a powerful tool of modernity science, there is even a science consensus about how our society is turning to a data-driven society. Machine learning is a branch of Artificial intelligence that has the ability to learn from data and understand its behavers. Python programming language aiming the challenges of this new era is becoming one of the most popular languages for general programming and scientific computing. Keeping all this new era circumstances in mind, this article has as a goal to show one example of how to use one supervised machine learning method, Support Vector Machine, and to predict movie’s genre according to its description using the programming language of the moment, python. Firstly, Omdb official API was used to gather data about movies, then tuned Support Vector Machine model for Latent semantic indexing capable of predicting movies genres according to its plot was coded. The performance of the model occurred to be satisfactory considering the small dataset used and the occurrence of movies with hybrid genres. Testing the model with larger dataset and using multi-label classification models were purposed to improve the model.

• Cybersecurity Challenges in Agricultural Digitalization: A Systematic Review with Python-Based Analysis

  1-15.

  Zsanett Porkoláb-Angyalos

  Views:

  63

  The intersection of agriculture and cybersecurity has become a prominent research focus in recent years, driven by the rapid adoption of IoT (Internet of Things) and precision farming technologies. These technological innovations have revolutionized agricultural processes, enhancing efficiency and sustainability while introducing significant security risks. This study conducts a systematic literature review (SLR) to address key cybersecurity issues in agriculture, with a particular emphasis on IoT vulnerabilities and threats. Using Python-based text analysis techniques, the research automated the analysis of abstracts and full texts, enabling rapid filtering and thematic categorization of relevant studies. From an initial pool of 1,039 publications, 40 relevant studies were identified based on rigorous screening criteria. The thematic analysis revealed that 44.9% of the publications focus on IoT device vulnerabilities, 32.7% on agricultural cybersecurity challenges, and 22.4% on the security issues of Agriculture 4.0 and precision farming. Methodological analysis indicated that machine learning, simulation models, and case studies dominate the research landscape, while surveys and experimental studies appear less frequently. The findings highlight the critical importance of developing robust cybersecurity strategies and technologies in the agricultural sector, particularly to mitigate the risks posed by IoT devices.