Kulsawasd Jitkajornwanich

An Enhanced Deep Convolutional Encoder-Decoder Network for Road Segmentation on Aerial Imagery

Object classification from images is among the many practical examples where deep learning algorithms have successfully been applied. In this paper, we present an improved deep convolutional encoder-decoder network (DCED) for segmenting road objects from aerial images. Several aspects of the proposed method are enhanced, incl. incorporation of ELU (exponential linear unit)—as opposed to ReLU (rectified linear unit) that typically outperforms ELU in most object classification cases; amplification of datasets by adding incrementally-rotated images with eight different angles in the training corpus (this eliminates the limitation that the number of training aerial images is usually limited), thus the number of training datasets is increased by eight times; and lastly, adoption of landscape metrics to further improve the overall quality of results by removing false road objects. The most recent DCED approach for object segmentation, namely SegNet, is used as one of the benchmarks in evaluating our method. The experiments were conducted on a well-known aerial imagery, Massachusetts roads dataset (Mass. Roads), which is publicly available. The results showed that our method outperforms all of the baselines in terms of precision, recall, and F1 scores.

Adapting K-means clustering to identify spatial patterns in storms

This paper extends our previous work on deriving meaningful storm patterns from very large rainfall data. In an earlier work, we described MapReduce-based algorithms to identify three types of the storms: local, hourly and overall storms. In general, local storms have temporal characteristics of the storms at a particular site, hourly storms have spatial characteristics of the storms at a particular hour and overall storms have both spatial and temporal characteristics of the storm. We aim to find meaningful patterns and predict trajectories in the spatio-temporal data (i.e. overall storms which are sets of geographically overlapping, consecutive hourly storms). In this paper, we adapt K-Means clustering to find different types of hourly storms based on their shapes and sizes. Since the rainfall data are typically larger than the memory capacity of a single computer, we have implemented this clustering algorithm in Apache Spark, which is a distributed data processing framework, and have run our experiments on a computer cluster.

A Survey of Spatio-Temporal Database Research.

The main purpose of spatio-temporal database systems is combining the spatial and temporal features of data. Almost all spatio-temporal applications—such as mobile communication systems, traffic control systems, and GIS with moving objects—have a common basis, which is the requirement to handle both space and time characteristics of the data. Similar to other data types, spatio-temporal data are required to be accurately modeled, structured, and queried efficiently. In this paper, we survey data models, related operations, data structures and access methods for spatial, temporal, and spatio-temporal data types. These access methods basically are enhanced variations of the well-known R-tree.

Microcorona Discharge-Mediated Nonthermal Atmospheric Plasma for Seed Surface Modification

By exploiting the physical effect of a highly nonuniform localized electric field and electron-initiated impact ionization on space charge, we generated homogeneous nonthermal plasma under ambient atmosphere. We evaluated the physical characteristics and evolution of microcorona discharge-induced nonthermal atmospheric plasma (NAP) based on a point-to-plane electrode in open air with two distinct configurations. High-voltage pulses were employed as the primary power source of corona discharge generation to reveal the fundamental mechanism, polarity effect and feasibility of using NAP for organic surface modification. Consequently, we employed NAP to modify the surface of rice (Oryza sativa L.) seeds to improve their wettability. The surface modification of the rice seeds was investigated via water apparent contact angle (ACA) and water imbibition (WI) measurements. The ACA and WI measurements revealed not only the improvement in the wetting properties but also the mutual relationships between and limitations of ACA and WI analysis. We found that the WI time reached saturation after a certain treatment time, called the threshold treatment time. Because vacuum conditions are not required, well-established NAP technology will garner interest in many fields, ranging from the life, environmental, and biomedical sciences to solid-state electronics applications.

Temporal kNN for short-term ocean current prediction based on HF radar observations

Ocean surface current prediction is at the core of various marine operational routines, including disaster monitoring, oil-spill backtracking, sea navigation and search-and-rescue operations. More accurate prediction can yield significant improvement to the overall system. Most existing short-term prediction methods applied numerical models based on physical processes. In this paper, we propose an alternative approach in predicting the surface current by utilizing temporal k-nearest-neighbor technique, which can predict the future surface current up to 24 hours in advance. Our model incorporates several pre-processing methods, e.g. feature extraction and data transformation, in order to capture the seasonal and temporal characteristics of the HF (high frequency) radar observation data. The developed model was implemented, validated and compared with the existing models using the same historical datasets collected from the HF coastal radar stations located along the Gulf of Thailand. Our experimental results indicate that the proposed model can achieve the highest accuracy among all methods, including ARIMA, exponential smoothing, and LSTM; and satisfy the oil-spill backtracking application requirements. In addition, we found that our system requires little to none maintenance and can easily be adapted to other coastal radar locations where the amount of historical HF radar observations is limited.

Polarity effect of pulsed corona discharge plasma on seed surface modification

This paper presents an experimental analysis and underlying mechanism of positive and negative pulsed corona discharge induced atmospheric non-thermal plasma. We designed a system based on point-plane configuration to produce direct corona discharge plasma (DCP) and hybrid corona discharge plasma (HCP) systems. The polarity effect of corona discharge for surface modification application on rice seeds was investigated under atmospheric dry air ambient. The reactive species under negative and positive corona discharge plasma were also studied for optimization design. The results show that only negative pulsed corona discharge is feasible for DCP system while both positive and negative pulsed corona discharge can be employed for in HCP system.

Proving completeness of OpenGIS SQL spatial relationships and operations

OpenGIS SQL is a standard for incorporating GIS and spatial concepts into SQL. Two types of methods are part of OpenGIS SQL: (1) boolean methods for topological relationships among spatial objects, and (2) methods for specifying spatial operations. We prove that the complete set of 2-dimensional spatial relationships defined by Egenhofer can all be specified using OpenGIS SQL operations and relationships. Our proof shows how each spatial relationship can be specified using OpenGIS SQL and thus provides users with the means of determining how each spatial relationship can be written in SQL. This provides users with enhanced usability and flexibility by providing the specific OpenGIS conditions for every possible 2-dimensional spatial relationship.