Machine learning is a sub field of artificial intelligence which allows forecasting through learning past behaviors and rules from old data. In today's world, machine learning is being used almost in any fields such as education, medicine, veterinary, banking, telecommunication, security, and bio-medical sciences. In human health, although machine learning is generally preferred particularly in predicting diseases and identifying respective risk factors, it is obvious that there are a limited number of publications where this method was applied on veterinary or indicates whether it is correct and applicable. In this review, it was observed that the neural network, logistic regression, linear regression, multiple regression, principle component analysis and k-means methods were frequently used in examined publications and machine learning application in veterinary field upward momentum. Additionally, it was observed that recent developments in the field of machine learning (deep learning, ensemble learning, voice recognition, emotion recognition, etc.) is still new in the field of veterinary. In this review, publications are examined under clustering, classification, regression, multivariate data analysis and image processing topics. This review aims at providing basic information on machine learning and to increase the number of multidisciplinary publications on computer sciences/engineering and veterinary field. Keywords: Machine learning, Artificial intelligence, Veterinary, Computer sience Veteriner Hekimlik Alanında Makine Öğrenmesi Uygulamaları Üzerine Bir Derleme ÖzetMakine öğrenmesi yapay zekanın bir alt çalışma alanı olup eski verilerden geçmiş davranışların ve kuralların öğrenilerek ileriye doğru tahminlerin yapılmasına olanak sağlar. Makine öğrenmesi günümüzde eğitim, tıp, veterinerlik, bankacılık, telekomünikasyon, güvenlik, biyomedikal gibi hemen hemen her alanda kullanılmaktadır. İnsan sağlığında özellikle hastalıkların önceden tahmin edilmesi ve ilgili risk faktörlerinin tespit edilmesinde makine öğrenmesi yöntemleri genellikle tercih edilmekle birlikte hayvan sağlığında doğruluğu ve aynı zamanda ilgili alanda kullanılabilir olup olmadığını belirleyen bu yöntemin uygulandığı çalışmaların sınırlı olduğu görülmektedir. Bu derlemede incelenen çalışmalarda sinir ağları, lojistik regresyon, lineer regresyon, çoklu regresyon, temel bileşen analizi ve k-ortalamalar yöntemlerinden sıklıkla yararlanıldığı ve veterinerlik alanında yapılan makine öğrenmesi çalışmalarının son yıllarda ivme kazandığı gözlemlenmiştir. Ayrıca makine öğrenmesi alanındaki son gelişmelerin (derin öğrenme, kolektif öğrenme, ses tanıma, duygu tanıma, vb.) veterinerlikte yeni yeni uygulandığı gözlemlenmiştir. Bu derlemede çalışmalar kümeleme, sınıflandırma, regresyon, çok değişkenli veri analizi ve görüntü işleme başlıkları altında incelenmiştir. Bu derlemenin amacı makine öğrenmesi ile ilgili temel bilgileri vermek ve bilgisayar bilimleri/mühendisliği ile veterinerlik alanındaki ortak çalışmaları arttırmaktır.
Ensuring software quality is an important step towards a successful project. Since software development is a human-oriented process, it is possible to say that any factor affecting people will directly affect software quality and success. The aim of this study is to reveal which factors affect humans. For this purpose, we conducted a systematic literature review. We identified 80 related primary studies from the literature. We defined 7 research questions. For answering research questions, we extracted data from the primary studies. We researched human factors, methods for data collection and data analysis, publication types and years. Factors are grouped into 3 main groups: Personal factors, interpersonal factors, and organizational factors. The results show that personal factors are the most important category of human factors. It is seen that the most researched factors among personal factors are “experience” and “education”.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.