During the late Longshan period (ca. 4200–3900 BP) settlements on the Central Plains of China underwent a diversification in food production technologies, which set the stage for rapid economic and social development. The introduction of novel domesticates such as rice, wheat, cattle, and sheep not only provided more food choices, but also changed ideas concerning land use, farming techniques, and the use and mobilization of large scale labor forces. To better understand the contribution that these new dietary items and practices made to shaping the late Longshan period societies, a stable isotope ratio study of humans (n = 12) and animals (n = 42) was conducted at the late Longshan period site of Wadian. The human δ13C and δ15N values are clustered into two distinct groups. One group of nine individuals (δ13C = −9.9 ± 0.7‰; δ15N = 7.5 ± 0.5‰) had a predominately C4 diet based on millet grains with little protein input from the domestic animals. The other group of three individuals (δ13C = −14.3 ± 0.8‰; δ15N = 10.2 ± 0.3‰) had a mixed C3/C4 diet of millets and rice and were consuming sheep and cattle. The animals also displayed dietary diversity with the pigs (δ13C = −11.3 ± 2.5‰; δ15N = 6.9 ± 1.0‰, n = 10) and dogs (δ13C = −10.1 ± 1.0‰; δ15N = 7.2 ± 1.1‰, n = 7) having mostly a C4 plant based diet (millets). In contrast, the cattle (δ13C = −12.8 ± 2.1‰; δ15N = 7.6 ± 0.7‰, n = 9), sheep (δ13C = −16.7 ± 0.9‰; δ15N = 7.6 ± 0.1‰, n = 2), and cervids (δ13C = −20.8 ± 0.9‰; δ15N = 5.0 ± 1.2‰, n = 10) had diets with a greater contribution from C3 sources such as rice and wild plants. The discovery that humans and animals had different subsistence patterns indicates dietary complexity at Wadian and that rice agriculture, and cattle and sheep husbandry practices were already an important part of the local economy by the late Longshan period in the southern region of the Central Plains of China. Copyright © 2015 John Wiley & Sons, Ltd.

No abstract

The scale of weather monitoring is limited by the cost of the automatic weather stations (AWS), which is mainly the cost of high precision instruments and long-distance wireless telecommunication equipments. We propose a wireless sensor network (WSN) based AWS, which takes advantage of the low-cost, real-time and infrastructure-free characteristics of WSN [1]. We can therefore extend the scale of weather monitoring without increasing the number of telecommunication equipments. This WSN-based AWS is able to cover a plane and gather multiple sets of weather measurements in real-time at a better data resolution.

Traffic speed forecasting in the short term is one of the most critical parts of any intelligent transportation system (ITS). Accurate speed forecasting can support travelers’ route choices, traffic guidance, and traffic control. This study proposes a deep learning approach using long short-term memory (LSTM) network with tuning hyper-parameters to forecast short-term traffic speed on an arterial parallel multi-lane road in a developing country such as Vietnam. The challenge of mishandling the location data of vehicles on small and adjacent multi-lane roads will be addressed in this study. To test the accuracy of the proposed forecasting model, its application is illustrated using historical voyage GPS-monitored data on the Le Hong Phong urban arterial road in Haiphong city of Vietnam. The results indicate that in comparison with other models (e.g., traditional models and convolutional neural network), the best performance in terms of root mean square error (RMSE), mean absolute error (MAE), and median absolute error (MDAE) is obtained by using the proposed model.

In regular convolutional neural networks (CNN), fully-connected layers act as classifiers to estimate the probabilities for each instance in classification tasks. The accuracy of CNNs can be improved by replacing fully connected layers with gradient boosting algorithms. In this regard, this study investigates three robust classifiers, namely XGBoost, LightGBM, and Catboost, in combination with a CNN for a land cover study in Hanoi, Vietnam. The experiments were implemented using SPOT7 imagery through (1) image segmentation and extraction of features, including spectral information and spatial metrics, (2) normalization of attribute values and generation of graphs, and (3) using graphs as the input dataset to the investigated models for classifying six land cover classes, namely House, Bare land, Vegetation, Water, Impervious Surface, and Shadow. The results show that CNN-based XGBoost (Overall accuracy = 0.8905), LightGBM (0.8956), and CatBoost (0.8956) outperform the other methods used for comparison. It can be seen that the combination of object-based image analysis and CNN-based gradient boosting algorithms significantly improves classification accuracies and can be considered as alternative methods for land cover analysis.

No abstract

No abstract

This article investigates the use of the galactic swarm optimization algorithm in searching for parameters of a convolutional neural network for flood susceptibility mapping. Ha Giang province, the mountainous area of Vietnam, was chosen as a case study because of the frequent occurrence of floods. From this study area, 11 predictor variables and historical flood locations were selected to build up the training datasets, in which each sample is prepared in the 3D form of (height × width × channels or variables) = (5 × 5 × 11), (7 × 7 × 11), and (9 × 9 × 11), respectively for three experiments. The model performance was assessed by root mean square error, area under the receiver operating characteristic (AUC), and overall accuracy (OA). The results showed that the examined model significantly improved the classification accuracies: OA = 83.093, AUC = 0.917; OA = 83.726, AUC = 0.923; and OA = 82.791, AUC = 0.908 for the three training datasets in comparison to benchmarked classifiers, and this model can be considered as an alternative solution for flood susceptibility mapping.