Deneshkumar V | Manonmaniam Sundaranar University (original) (raw)

Papers by Deneshkumar V

Low birth weight is a major public health issue in India. LBW leads to an impaired growth of the ... more Low birth weight is a major public health issue in India. LBW leads to an impaired growth of the infant resulting in a higher mortality rate and increased morbidity. In India, nearly 20% of new borns have LBW. Males have less frequency of LBW than females. This study emphasizes the need for improving maternal health, weight gain during pregnancies, prevention, and proper management of risk factors along with improving socioeconomic and educational status of mothers. Logistic regression is a statistical model for analyzing a dataset in which one or more independent variables that determine an outcome. The main objective of this paper is to identify the predictors of low birth weight through bivariate and multivariate logistic regression model.

Allocation of security system is one of the challenging problems of decision makers to take decis... more Allocation of security system is one of the challenging problems of decision makers to take decision about attacks by terrorists. To carry out this task is a complete set of security objectives. In this paper, applying a statistical method to measure the expected live loss for
terrorist attacks by means of binomial distribution and allocate the security forces based on the expected live loss. The results are presented numerically as well as graphically.

Background: Knowledge of antibiotic sensitivity patterns in the critically ill would lead to bett... more Background: Knowledge of antibiotic sensitivity patterns in the critically ill would lead to better outcomes by refinement of empirical therapy. The aim of the study was to analyze the antibiotic sensitivity patterns of pathogens in the critically ill. Methods: Retrospective analytical study of 267 culture samples from critically ill patients was done. Data was collected from hospital medical records department and analyzed. Results: In case of community-acquired infections, carbapenems and piperacillin-tazobactam had high efficacy for UTI; carbapenems, aminoglycosides and levofloxacin had intermediate efficacy for pneumonia; aminoglycosides, piperacillin-tazobactam, carbapenems and quinolones had intermediate efficacy for soft tissue infections; and linezolid and vancomycin had high efficacy for blood borne sepsis of unknown source. In case of hospital acquired infections, carbapenems and aztreonam had intermediate efficacy for UTI; aminoglycosides had intermediate efficacy for blood borne sepsis of unknown source and aminoglycosides had high efficacy for CLABSI. Only colistin and tigecycline demonstrated high efficacy for VAP. Colistin and tigecycline showed high efficacy for community and hospital acquired UTI, pneumonia and soft tissue infections as well as gram negative CLABSI and hospital acquired blood borne sepsis of unknown source.

Heart disease is the number one cause of death in women, as it is in men. Our Hospital records sh... more Heart disease is the number one cause of death in women, as it is in men. Our Hospital records show that wom-
en from Madurai have an increased incidence of Coronary Heart Disease (CHD) requiring CABG. This observa-
tional study aims to observe and analyze the gender differences between Blood lipid levels, Liver span and Body mass index as a prelude
to a major proposed CABG study. Methods. 312 Females and 410 males were included in this study over a period of 8 months. Diabetics,
Hypercholesterolemia, hepatobiliary diseases, myeloproliferative disorders, cardiac diseases and alcoholics were excluded. Blood lipids,
sonographic measurement of the liver span, weight and height were measured. Subjects were divided as Group 1 (age 16 to 30) Group 2
(age 31 to 45) Group 3 (age 46 to 60) Group 4 (more than 60 years). Results: Maximum number of cases with abnormal TC, LDL and
HDL were seen with group 2 and group 3 males. Group 3 females showed the maximum number of abnormal cases with TC, TGL, and
LDL. Liver size significantly correlated well with BMI in all groups of men and females. There was significant correlation between liver
size and TGL in group 2 and VLDL in group 3 and group 4 (p= <0.05) in females. In contrast there was no correlation between liver size
and TGL and VLDL in group 3 and group 4 in the males. A highly significant negative correlation was seen between Liver size and HDL
with group 4 females. This study hypothesizes that dyslipidemia in women from Madurai occurs at an early age and there are significant
gender differences in blood Lipids and women are more prone for dyslipidemias than men from Madurai

Artificial Neural Network (ANN) provides an attractive alternative tool for researchers for agric... more Artificial Neural Network (ANN) provides an attractive alternative tool for researchers for agricultural forecasting. The Multi Layer Feed Forward Neural Net (MLFFNN) is one of the most widely used neural nets. Here, the MLFFNN architecture is examined and compared with time series models such as Autoregressive Integrated Moving Average (ARIMA) model for prediction of agricultural production. Both models were compared using visualization technique and statistical tests and the results were illustrated numerically and graphically.

The outlier detection problem has important applications in the field of medical research. Clinic... more The outlier detection problem has important applications in the field of medical research. Clinical databases have accumulated large quantities of information about patients and their medical conditions. In this study, the data mining techniques are used to search for relationships in a large clinical database. Relationships and patterns within this data could provide new medical knowledge. The main objective of this paper is to detect the outliers and identify the influence factor in the diabetes symptoms of the patient using data mining techniques. Results are illustrated numerically and graphically.

Time series data mining (TSDM) techniques explores large amount of time series data in search of ... more Time series data mining (TSDM) techniques explores large amount of time series data in search of interesting relationships among variables. The TSDM methods overcome limitations including stationarity and linearity requirements of traditional time series analysis by adapting data mining concepts for analyzing time series data. The Feed Forward Neural Net is one of the most widely used neural nets. In this paper, the Feed Forward Neural Nets architecture is examined and compared with Statistical Time Series Auto regressive integrated moving average (ARIMA) model for prediction of agricultural production. The performance by ANN model and Time series model for prediction are examined using visualization technique and statistical test and the results are illustrated numerically and graphically

In the past decades many forecasting methods has been developed for fuzzy time series. Fuzzy time... more In the past decades many forecasting methods has been developed for fuzzy time series. Fuzzy time series is a dynamic method for forecasting with linguistic values. It has been widely used for forecasting the time series data. This study mainly focuses on forecasting the terrorist victims and to enhance the forecasting accuracy based on statistical distribution. The performance of forecasting accuracy is evaluated by Root Mean Square Prediction Error with other existing methods.

Outlier detection is important in many fields. In statistics, an outlier is a observation that is... more Outlier detection is important in many fields. In statistics, an outlier is a observation that is numerically faraway from the rest of the data. The handling of outlying observations in a data set is one of the most important tasks in data preprocessing. The large data base can be classified in an unsupervised manner using clustering and classification algorithms. Fuzzy Cmeans is a method of clustering which was developed by Dunn in (1973) and improved by Bezdek in (1981). This allocates one piece of data in two or more clusters and it is frequently used in pattern recognition. Herein a proposed method based on Fuzzy approach which combines outlier analysis and clustering technique is presented. Clustering validation technique adaptively evaluated the results of a clustering algorithm. A numerical example is provided for illustration using iris data set.

For many data mining applications, finding the outliers is more interesting than finding the comm... more For many data mining applications, finding the outliers is more interesting than finding the common patterns of the data.Outliers are frequently adapted in time series data mining analysis.The main objective of this paper, outliers on forecasting in agricultural production is analyzed. Outliers in time series data was carried out by Fox (1972). Outlier detection has been used for detect and, where appropriate, remove inconsistent observations from data. The original outlier detection methods were arbitrary but new, Principled and systematic techniques are used, drawn from the full scope of computer science and statistics. In agricultural production outliers are initially detected and then forecast using ARIMA model. Predictions made after detecting outliers are compared with numerically and graphically the predictions made before detecting outliers.

Outliers are frequently adapted in time series analysis. The main objectives of this paper, outli... more Outliers are frequently adapted in time series analysis. The main objectives of this paper, outliers on forecasting in agricultural production are analyzed. Outliers in time series data was carried out by Fox (1972). Outlier detection has been used for detect and, where appropriate, remove inconsistent observations from data. The original outlier detection methods were arbitrary but new, Principled and systematic techniques are used, drawn from the full scope of computer science and statistics. In agricultural production outliers are initially detected and then forecast using ARIMA model. The forecasting results show that our method can be efficiently used in time series dataset to identify outlier.