The surveillance and reports on accidents for the current traffic management are carried out by viewing and inspecting CCTV footage. This method is slow to detect incidents and requires a lot of manpower. Since nowadays communication technology and social media play a role in reporting such incidents this research has been conducted to investigate accidents of interest from text messages reported on social media in Thai. There is currently no research or platform that supports this type of work clearly. This research presented the development of a neuron network memory-learning model to solve the problem of incidence pattern classification and incidence severity identification from social media messages in Thai. Using deep learning models such as MLP CNN Bi-LSTM and LSTM+CNN the study was designed and divided into three experimental patterns. This included examining patterns to identify traffic incidents that may be reported as general news or traffic reporting; examining patterns to indicate the type of incidents such as traffic accidents disasters damaged roads or others other than those mentioned; and examining patterns to specify the severity levels of the incidents such as normal intermediate traffic lane blocking or immovable. The experiments demonstrated the capability of CNN+LSTM learning models with the best incidence detection result at 93.44 %. The CNN model gave the best result in identifying a pattern of incidence at 85.29 % and the LSTM model was best able to determine the severity levels of the incidence at 88.53 %.

The aim of this study was to investigate the microbiological quality of milk-shaked drinks including Bacillus cereus Escherichia coli Salmonella spp. Staphylococcus aureus yeast and molds in unsealed containers sold in market fair roadside and stall around Mahasarakham university. The analytical results revealed that microbiological quality of 30 samples of milk-shaked drinks in unsealed containers that did not pass the criteria of department of medicine ministry of public health Thailand were 50 % of total samples. Bacteriological counts of Bacillus cereus Escherichia coli Salmonella spp. And Staphylococcus aureus of milk-based drinks that did not pass the criteria were 13.3 10 13.3 and 10% of total samples respectively. Yeasts and molds counts of milk-based drinks that did not pass the criteria were 3.3 and 30% of total samples respectively. Microbiological contamination of milk-shaked drinks was related to the hygiene of the shop and the supplier. It was found that the location of stall which high dust particles and animal carriers also contributed to the contamination of microorganisms. Moreover the hygiene of the supplier may cause the milk-shaked drinks to be contaminated with microorganisms.

The objective of this research is to develop the concrete flooring tile product from old asphalt road waste. The 6 ratios of Portland cement type1: coarse sand: old asphalt road waste: water reducer type A: tap water were designed including: 1: 5: 0: 0.02: 0.4 1: 4.5: 0.5: 0.02: 0.4 1: 4: 1: 0.02: 0.4 1: 3.5: 1.5: 0.02: 0.4 1: 3: 2: 0.02: 0.4 and 1: 2.5: 2.5: 0.02: 0.4 by weight. The concrete flooring tile casted with the compressive machine. The property tests followed the TIS.378 - 1988 (concrete flooring tiles). According to the result it was found that the 1: 2.5: 2.5: 0.02: 0.4 was the proper ratio of the concrete flooring tile. The increasing of old asphalt road waste in concrete flooring tile effected to decrease the water absorption and thermal conductivity properties. In term of the density and bending strength properties there were not many differences. The developed concrete flooring tile product from old asphalt road waste can use as same as the common concrete flooring tile product in market.

The objectives of this special project were to develop printed media for public relations in the form of Augmented Reality books and to evaluate the appropriateness of printed media for public Make Collecting data from advertising and public relations officers The State Railway of Thailand 10 people and 15 grade 6 teachers statistics used in data analysis were frequency percentage mean and standard deviation. The results showed that 1) has created the media print Railroad Cut Point Augmented Reality 2) The media is appropriate and is distributed to the public at the highest level. (𝑥̅= 4.50 SD = 0.50).

This research aims to develop a road accident prevention system to reduce the risk of accident a case study of Kamsakasang Junction Non-Thai District Nakhon Ratchasima Province. The target audiences are: traffic experts and 15 civil engineers to evaluated the developed system. From the study of traffic problem and risk areas there are 7 aspects to be improved: 1) Installation of traffic light 2) Installation of lighting and changing control cabinet 3) Improvement of the traffic island 4) Changing lower traffic island to higher one 5) Painting reflecting colour and reflecting light on the edge of the island 6) Drawing traffic line 7) Installation of warning signs. From the development of accident prevention system and evaluated by the experts; the overall evaluation of the system was the best (x = 4.66 SD = 0.41). There were 6 highest rated aspects and 1 very good aspect. The highest rated were installation of Vehicle Actuated traffic light (x = 4.92 SD = 0.15). As result of the development of road accident prevention system in 2014 the accident statistics were reduced by 53.85% compared to the pre-installation period. The statistics are reduced so it can be concluded that the road accident prevention system can be used effectively and it can be applied to other risk areas.