Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Data Mining - Concepts and Techniques.

Data Mining Practical Machine Learning Tools and Techniques

(1991). Applied Linear Regression Models. Journal of Quality Technology: Vol. 23, No. 1, pp. 76-77.

Applied Linear Regression Models

Let's read! We will often find out this sentence everywhere. When still being a kid, mom used to order us to always read, so did the teacher. Some books are fully read in a week and we need the obligation to support reading. What about now? Do you still love reading? Is reading only for you who have obligation? Absolutely not! We here offer you a new book enPDFd preventing chronic diseases a vital investment to read.

Preventing Chronic Diseases: A Vital Investment

The study investigated the prevalence and risk factors of low birth weight (LBW) in 1109 hospital births in Zahedan city, Islamic Republic of Iran. The overall prevalence of LBW was 11.8% (95% Cl: 9.9%-13.7%), similar for boys and girls (11.1% and 12.6% respectively). LBW was significantly associated with mother's ethnic origin (Balouch), birth interval < 3 years, twin birth, no use of supplements during pregnancy, < 4 prenatal care visits, no education, younger age and presence of maternal disease. There was no effect of mother's parity, occupation and smoking status. After logistic regression analysis, the only significant risk factors were: birth interval < 3 years, twin birth, no use of ferrous sulfate and maternal disease.

Prevalence and risk factors of low-birth-weight infants in Zahedan, Islamic Republic of Iran.

Introduction: Hospital triage is part of the emergency department structure which is done by emergency nurses. There is a little information about knowledge level of the nurses about triage. This study aimed to determine knowledge level of the nurses about hospital triage. Methods: This was the descriptive survey using simple random sampling. The researcher made questionnaire included 25 questions in three parts of demographic data, pure triage knowledge (15 questions) and triage decision making (10 questions). Seventy nurses of the emergency department participated in the study from all the hospitals of Sistan-Baluchestan province in 2009. The reliability of the questionnaire obtained 0.60 using test-retest. The data were analyzed using Kappa statistics, independent t-test, Pearson correlation coefficients through software SPSS15. Results: The response rate was equal to 68% (70 out of 102). The nurses had not enough knowledge about the hospital triage; 39.94% of the responses to the knowledge level questions were correct. Only in 3 hospitals (out of 10), special nurses have been dedicated to triage. The nurses who had more than two years experience in emergency department had received a higher average score. The concordance rate of the nurses in triage decision making was average (κ=0.56). Conclusion: Low knowledge of the nurses about hospital triage could be due to lack of formal training courses and lack of obligation of the emergency departments on evidence-base d decision making. Establishing academic courses for triage nursing and developing national triage scale is recommended.

A survey on knowledge level of the nurses about hospital triage

Quality Gap in Educational Services at Zahedan University of Medical Sciences: Students Viewpoints about Current and Optimal Condition

The collection of large volumes of medical data has offered an opportunity to develop prediction models for survival by the medical research community Medical researchers who seek to discover and extract hidden patterns and relationships among large number of variables use knowledge discovery in databases (KDD) to predict the outcome of a disease The study was conducted to develop predictive models and discover relationships between certain predictor variables and survival in the context of breast cancer This study is Cross sectional After data preparation, data of 22,763 female patients, mean age 594 years, stored in the Surveillance Epidemiology and End Results (SEER) breast cancer dataset were analyzed anonymously IBM SPSS Statistics 16, Access 2003 and Excel 2003 were used in the data preparation and IBM SPSS Modeler 142 was used in the model design Support Vector Machine (SVM) model outperformed other models in the prediction of breast cancer survival Analysis showed SVM model detected ten important predictor variables contributing mostly to prediction of breast cancer survival Among important variables, behavior of tumor as the most important variable and stage of malignancy as the least important variable were identified In current study, applying of the knowledge discovery method in the breast cancer dataset predicted the survival condition of breast cancer patients with high confidence and identified the most important variables participating in breast cancer survival

/pdf/prediction-of-breast-cancer-survival-through-knowledge-5gskjywube.pdf

Prediction of breast cancer survival through knowledge discovery in databases.

Introduction: The practice of breastfeeding, an important need for infants, can be affected by several factors that need to be investigated. This study was designed to survey the patterns and period of breastfeeding and its associated factors in women. Methods: The study was performed in Zahedan, southeast Iran, in 2004–2005, with a sample of 450 mothers via a questionnaire to collect information about the period of breastfeeding and some important factors concerning both mothers and children. Results: The exclusive breastfeeding ratio obtained from this study was 98 percent. The proportion of breastfeeding in months 1, 3, 6, 12 and 24 after birth were 92 percent, 85 percent, 69 percent, 56 percent and 8 percent, respectively. The median breastfeeding period was 15 months, with a standard error of 1.17. The period of breastfeeding showed a significant relationship with the age of the children and mothers, the mothers’ education level, night breastfeeding, breastfeeding to an ill child, breastfeeding during a mother’s illness and the frequency of breastfeeding per 24 hours. The Cox regression also confirmed a significant relationship between the period of breastfeeding and the abovementioned variables, except for mother’s education level and breastfeeding to an ill child. Conclusion: Young pregnant women need to be aware of the importance of breastfeeding and of avoiding the reduction or interruption of the breastfeeding period. It is recommended that the health authorities incorporate training and education programmes as well as healthcare measures to their family health programmes in order to overcome the problems of insufficient breastfeeding.

Masoud Roudbari

Papers

Prevalence and risk factors of low-birth-weight infants in Zahedan, Islamic Republic of Iran.

A survey on knowledge level of the nurses about hospital triage

Quality Gap in Educational Services at Zahedan University of Medical Sciences: Students Viewpoints about Current and Optimal Condition

Prediction of breast cancer survival through knowledge discovery in databases.

Factors associated with breastfeeding patterns in women who recourse to health centres in Zahedan, Iran.