Abstract.Groundwater tables forecasting during implemented river bank infiltration (RBI) method is important to identify adequate storage of groundwater aquifer for water supply purposes. This study illustrates the development and application of artificial neural networks (ANNs) to predict groundwater tables in two vertical wells located in confined aquifer adjacent to the Langat River. ANN model was used in this study is based on the long period forecasting of daily groundwater tables. ANN models were carried out to predict groundwater tables for 1 day ahead at two different geological materials. The input to the ANN models consider of daily rainfall, river stage, water level, stream flow rate, temperature and groundwater level. Two different type of ANNs structure were used to predict the fluctuation of groundwater tables and compared the best forecasting values. The performance of different models structure of the ANN is used to identify the fluctuation of the groundwater table and provide acceptable predictions. Dynamics prediction and time series of the system can be implemented in two possible ways of modelling. The coefficient correlation (R), Mean Square Error (MSE), Root Mean Square Error (RMSE) and coefficient determination (R 2 ) were chosen as the selection criteria of the best model. The statistical values for DW1 are 0.8649, 0.0356, 0.01, and 0.748 respectively. While for DW2 the statistical values are 0.7392, 0.0781, 0.0139, and 0.546 respectively. Based on these results, it clearly shows that accurate predictions can be achieved with time series 1-day ahead of forecasting groundwater table and the interaction between river and aquifer can be examine. The findings of the study can be used to assist policy marker to manage groundwater resources by using RBI method.
Malaysia is currently a rapidly developing country to achieve a 2020 vision. However the development that has been carried out contributed to a negative impact on the environment especially on water quality. Due to the deterioration of water quality, serious management efforts on water quality has been taken. Thus, the aim of this study is to investigate a technique that can automatically classify the water quality. The technique is based on the concept of Artificial Neural Network (ANN). Since the greater part of their methodologies depend on the idea of `pattern recognition’. Thus, it is convenient to inspect its ability in classify water quality. There are six environmental data were used in this study such as pH, total suspended solids (TSS), dissolved oxygen (DO), chemical oxygen demand (COD), biological oxygen demand (BOD), and ammonia. The data was obtained by in-site measurement and laboratory analysis. Then, the data was used as the feeder of input variables in the ANN database system. After training and testing the network of ANN, the result showed that 80.0% of accuracy classification with 0.468 of root mean square error (RMSE). This showed the encouraging results for classification.
Abstract.Malaysia is a country that has abundant rainfall that depends on the seasonal such as monsoon, where,certain areas in peninsular area are expected to receive heavy rain during this monsoon season. This abundant of rain could lead to massive flood if no mitigation actions were taken. One of the factor that contribute to the flood occurrences is type of soils. Type of soils play an important role in determining the rate of infiltration. Thus, this study was conducted to investigate the infiltration rate that effecting the ponding time at the Universiti Tun Hussein Onn Malaysia (UTHM). This area is located at flat topography with thick layer of clay soil beneath the ground surface that indicated low infiltration capacity rate. This condition could causeponding of water that could lead to high surface runoff that could cause flood.This paper was aimed at understanding the effect of soil clay layer on infiltration rate and ponding time. Infiltration test was conducted at four (4) points to make a spatial analysis around the study area. The soil was classified based on soil classification system (USCS), while, ponding time was calculated based on Horton model. Based on the results, the average infiltration rate is ranging from 0.004 mm/s to 0.076 mm/s among the selected locations.Soil samples were sieve and thedominant soil comprises of minimal well graded silty clay and clayey sand which is more than 50% content sand and more than 12% content fines. Lastly, time of ponding was calculated by using Horton model and it shows that the ponding time started between 0.51h to 1.0h. This information could serve a vital information on determining the mitigation measures to tackle a flood problem in this area.
Feature vectors provided by pre-trained deep artificial neural networks have become a dominant source for image representation in recent literature. Their contribution to the performance of image analysis can be improved through finetuning. As an ultimate solution, one might even train a deep network from scratch with the domain-relevant images, a highly desirable option which is generally impeded in pathology by lack of labeled images and the computational expense. In this study, we propose a new network, namely KimiaNet, that employs the topology of the DenseNet with four dense blocks, fine-tuned and trained with histopathology images in different configurations. We used more than 240,000 image patches with 1000×1000 pixels acquired at 20× magnification through our proposed "highcellularity mosaic" approach to enable the usage of weak labels of 7,126 whole slide images of formalin-fixed paraffin-embedded human pathology samples publicly available through the The Cancer Genome Atlas (TCGA) repository. We tested KimiaNet using three public datasets, namely TCGA, endometrial cancer images, and colorectal cancer images by evaluating the performance of search and classification when corresponding features of different networks are used for image representation. As well, we designed and trained multiple convolutional batch-normalized ReLU (CBR) networks. The results show that KimiaNet provides superior results compared to the original DenseNet and smaller CBR networks when used as feature extractor to represent histopathology images.
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.