European Journal of Engineering Science and Technology

A Comparative Study of ECG Leads in Predicting Cardiac Arrhythmias Using Deep Learning Models

Rodrigo Alexandre Dos Santos — 2025-07-01

Cardiac arrhythmias are a group of conditions that have a high incidence and prevalence worldwide, and receive considerable attention from the medical community because they are associated with several risk factors and can cause serious impairment of the individual's cardiac function in more critical cases. The electrocardiogram is the main tool for the diagnosis of cardiac arrhythmias because it is considered flexible, non-invasive, and low-cost. The so-called 12-lead system is the most widely used ECG configuration in clinical practice and has been considered for several years as the gold standard for detecting cardiac arrhythmias. Although this configuration is widely popular, there are situations in which it may be more interesting to use simpler ECG configurations to expand the tool to scenarios other than traditional healthcare environments, such as using mobile devices for cardiac monitoring. These scenarios require using simplified ECG configurations, using a single lead or a subset of leads, due to technical restrictions of the devices or limitations of the scenario itself. Knowing the performance of each lead when considered individually is important for defining which leads are most suitable for use in each scenario. This study presents a comparative analysis of the leads of the 12-lead system for predicting cardiac arrhythmias employing a deep learning-based approach and a large dataset containing diagnoses of 32 types of arrhythmias. A large public dataset well-annotated according to international standards for arrhythmia diagnosis was used. Both individual results on the performance of each lead and patterns involving groups of leads that share common characteristics were highlighted. The results presented allow healthcare professionals to be equipped with quantitative data that can provide a robust basis for decision-making and overall improvement of medical processes. The results demonstrate the feasibility of using technologies based on Artificial Intelligence as tools to support cardiology practice and the expansion of cardiac monitoring practices to environments outside clinics and hospitals.

Automated Development of a Grammatical Dictionary for Georgian Dialects

Liana L Lortkipanidze — 2025-07-01

This paper presents an automated system for compiling grammatical dictionaries of the Georgian language and its dialects. Unlike traditional dictionaries, grammatical dictionaries include not only base word forms but also complete paradigms, offering detailed morphological and syntactic information. This is particularly crucial for agglutinative-inflectional languages such as Georgian, where word forms vary significantly depending on context. The system applies a dictionary-based approach to expand lexical resources by identifying words with shared grammatical markers and integrates an innovative lemmatization algorithm capable of processing unknown words, automatically generating their base forms and paradigms. The methodology builds upon prior research in dialectal lexicography and syntactic annotation within Georgian corpora, while introducing comparative insights from similar linguistic technologies applied to other agglutinative languages. The developed system demonstrated high efficiency in automating the creation of grammatical dictionaries. Testing on Georgian literary corpora revealed that only 2% of non-dictionary word forms required manual correction post-lemmatization. The affix-based algorithm significantly outperformed traditional suffix-only methods, particularly in handling complex morphological structures. These results confirm the system's effectiveness in expanding lexical resources and highlight its adaptability for other Kartvelian languages. The study emphasizes the value of integrating linguistic theory with computational approaches to address challenges in morphological processing and lexicon development, offering both theoretical contributions and practical applications in language technology.

Industrial Heat Pumps and Their Use in Food & Beverage Industry in the US

Sahil Shah — 2025-07-01

This paper examines the implementation of industrial heat pumps in the food and beverage sector, showcasing their potential as an efficient and sustainable energy solution. Heat pumps demonstrate exceptional efficiency, generating up to 3 kW of output energy for every 1 kW of input energy. This high-performance ratio makes them particularly suitable for the food and beverage industry, where many processes require steam and heat within the 150°C to 200°C range. The study highlights how heat pumps can effectively utilize waste energy, which is abundant in food and beverage manufacturing, further enhancing their appeal. Additionally, the research reveals that in most U.S. states, industrial heat pumps offer a favorable payback period of 4-5 years, with minimal infrastructure upgrades required for installation. This combination of efficiency, adaptability, and economic viability positions heat pumps as an ideal renewable energy source for the sector. The paper explores current applications, potential energy savings, and environmental benefits, supported by industry-specific case studies. It concludes with an analysis of future prospects and potential challenges, providing valuable insights for industry professionals and policymakers considering the adoption of this technology.