All publications

Product Environmental Footprint for Feed Production in Thailand

Prakaytham Suksatit, Nongnuch Poolsawad, Wanwisa Thanungkano, Jitti Mungkalasiri

Proceedings of the World Congress on Civil, Structural, and Environmental Engineering · 2016

Extended Abstract Food industry in Thailand is one of the high-volume exports. According to the statistics, in 2014, exports accounted for 27% of chicken production, which is ranked fourth in the world and ranked first in the EU (42%) [1], it presents the majority market share. This study aims to prepare and support Thailand industries to export to the EU single market by using product environmental footprint (PEF) to be a tool for evaluating the quality of products on environmental perspective. The study complied with methodology and environmental footprint impact category to conform to the PEF guide [2]. Also this study is a part of the shadow pilot project of the PEF, which led by the National Science Technology and Innovation Policy Office (STI) and National Metal and Materials Technology Center (MTEC) that collaborated with one of the large chicken industries named Betagro Public Company Limited. In a nutshell, the environmental impacts of chicken feed shall be assessed whole life cycle from cradle to grave, which covered from raw materials acquisition stage to disposal stage, by considering the functional unit was 1 kg of chicken feed products. The main ingredients of chicken feed should be provided the protein and energy to improve chicken health as with increasing in size and to produce more eggs. Maize, wheat, rice bran and soy bean meal are majorly used for chicken feed which contain high nutritive values, and therefore most widely used in animal feed industries because they contain less in fat and high in proteins. The composition of feed by each recipe based on age of chicken (breeder and broiler) and the growth stage of the chicken. The mainly environmental impact categories of chicken product has feed production (approximately value more than 50% by weight) and the significant environmental impact categories were climate change, freshwater eutrophication, freshwater ecotoxicity, water resource depletion and land use. The results found that the main contribution to environmental impacts of feed production is raw materials acquisition, especially maize from Thailand and soybean meal from Argentina. In worldwide typically use maize starch for main ingredient of poultry feed because its energy source is highly digestible for poultry. In addition, the plant protein source traditionally used for feed manufacture is soybean meal, which is the preferred source for poultry feed [4]. However, the environmental impact of broiler feed shows higher than breeder feed that because the ratio of maize in boiler feed to tonne feed is 1:0.46 whereas breeder feed 1: 0.54. Thus, this study focuses on the feedstuffs of broiler feed with percentage of protein is retained. The percentage of crude protein in feedstuffs as shown in table 1 [5,6].

Review of LCA datasets in three emerging economies: a summary of learnings

Bruce Vigon, Guido Sonnemann, Anne Asselin, Dieuwertje Schrijvers, Andreas Ciroth, Sau Soon Chen, Tiago Emmanuel Nunes Braga, Nongnuch Poolsawad, Jitti Mungkalasiri, F. Boureima, Llorenç Milà i Canals

The International Journal of Life Cycle Assessment · 2016

Practical approaches to mining of clinical datasets : from frameworks to novel feature selection

Nongnuch Poolsawad

Repository@Hull (Worktribe) (University of Hull) · 2014

Research has investigated clinical data that have embedded within them numerous complexities and uncertainties in the form of missing values, class imbalances and high dimensionality. The research in this thesis was motivated by these challenges to minimise these problems whilst, at the same time, maximising classification performance of data and also selecting the significant subset of variables. As such, this led to the proposal of a data mining framework and feature selection method. The proposed framework has a simple algorithmic framework and makes use of a modified form of existing frameworks to address a variety of different data issues, called the Handling Clinical Data Framework (HCDF). The assessment of data mining techniques reveals that missing values imputation and resampling data for class balancing can improve the performance of classification. Next, the proposed feature selection method was introduced; it involves projecting onto principal component method (FS-PPC) and draws on ideas from both feature extraction and feature selection to select a significant subset of features from the data. This method selects features that have high correlation with the principal component by applying symmetrical uncertainty (SU). However, irrelevant and redundant features are removed by using mutual information (MI). However, this method provides confidence in the selected subset of features that will yield realistic results with less time and effort. FS-PPC is able to retain classification performance and meaningful features while consisting of non-redundant features. The proposed methods have been practically applied to analysis of real clinical data and their effectiveness has been assessed. The results show that the proposed methods are enable to minimise the clinical data problems whilst, at the same time, maximising classification performance of data.

Issues in the Mining of Heart Failure Datasets

Nongnuch Poolsawad, L. Moore, C. Kambhampati, John G.F. Cleland

Machine Intelligence Research · 2014

Handling missing values in data mining - A case study of heart failure dataset

Nongnuch Poolsawad, L. Moore, C. Kambhampati, John G.F. Cleland

2012

In this paper, we investigate the characteristics of a clinical dataset using feature selection and classification techniques to deal with missing values and develop a method to quantify numerous complexities. The research aims to find features that have high effect on mortality time frame, and to design methodologies which will cope with the following challenges: missing values, high dimensionality, and the prediction problem. The experimental results will be extended to develop prediction model for HF This paper also provides a comprehensive evaluation of a set of diverse machine learning schemes for clinical datasets.

Feature Selection Approaches With Missing Values Handling For Data Mining - A Case Study Of Heart Failure Dataset

Nongnuch Poolsawad, C. Kambhampati, John G.F. Cleland

Zenodo (CERN European Organization for Nuclear Research) · 2011

In this paper, we investigated the characteristic of a clinical dataseton the feature selection and classification measurements which deal with missing values problem.And also posed the appropriated techniques to achieve the aim of the activity; in this research aims to find features that have high effect to mortality and mortality time frame. We quantify the complexity of a clinical dataset. According to the complexity of the dataset, we proposed the data mining processto cope their complexity; missing values, high dimensionality, and the prediction problem by using the methods of missing value replacement, feature selection, and classification.The experimental results will extend to develop the prediction model for cardiology.

Dysphonia Measures in Parkinson's Disease and Their use in Prediction of Its Progression .

C. Kambhampati, Mayur Sarangdhar, Nongnuch Poolsawad

Repository@Hull (Worktribe) (University of Hull) · 2010

Parkinson's Disease (PD) is a neurodegenerative disorder that impairs the motor skills, speech and general muscle coordination. The progression of PD is assessed using a clinically defined rating scale known as Unified Parkinson's Disease Rating Scale (UPDRS). Recent studies have shown the use of telemonitoring of PD using simple speech tests which replicate the UPDRS to clinician's accuracy. Regression analysis is performed on a database of speech recordings of 42 PD patients to analyse the relation between dysphonia measures and the UPDRS with the progression of PD. It is observed that there is a strong correlation between the dysphonia measures and the UPDRS and it is possible to predict the UPDRS scores weekly using linear regression techniques. The results also suggest that certain dysphonia measures evolve more significantly with the progression in PD. This is supported by Principle Component Analysis (PCA) which identifies the dysphonia measures that are strongly correlated during the course of PD progression. The data is classed by trials undertaken by the patients and each patient had at least 20 valid trials.