Road traffic surveys determine the number and type of vehicles passing by a specific point over a certain period of time. The manual estimation of the number and type of vehicles from images captured by a camera is the most commonly used method. However, this method has the disadvantage of requiring high amounts of manpower and cost. Recently, methods of automating traffic volume surveys using sensors or deep learning have been widely attempted, but there is the disadvantage that a person must finally manually verify the data in order to ensure that they are reliable. In order to address these shortcomings, we propose a method for efficiently conducting road traffic volume surveys and obtaining highly reliable data. The proposed method detects vehicles on the road from CCTV (Closed-circuit television) images and classifies vehicle types using deep learning or a similar method. After that, it automatically informs the user of candidates with a high probability of error and provides a method for efficient verification. The performance of the proposed method was tested using a data set collected by an actual road traffic survey company. As a result, we proved that our method shows better accuracy than the previous method. The proposed method can reduce the labor and cost in road traffic volume surveys, and increase the reliability of the data due to more accurate results.

Skeleton-based action recognition has gained increasing attention due to its robustness to background variations and privacy-preserving properties. However, real-world skeleton datasets often exhibit severe class imbalance, leading to long-tailed data distributions that significantly degrade recognition performance, especially for tail classes. Existing mix-based skeleton augmentation methods partially alleviate this issue by increasing data diversity, but they often generate physically implausible skeletons and fail to explicitly account for class imbalance during augmentation. In this paper, we propose a long-tailed augmentation framework with two key components: (i) realistic skeleton mixing in the relative bone vector space and (ii) class-aware sampling that increases effective augmentation frequency of underrepresented classes. Specifically, we perform mixing in the relative bone vector space rather than joint coordinate space to preserve kinematic consistency and further enforce bone-wise length alignment to prevent unrealistic limb deformations. To mitigate class imbalance, we introduce a class-aware weighting mechanism that biases sampling toward tail classes. Extensive experiments on the long-tailed NTU RGB+D and NTU RGB+D 120 benchmarks show that the proposed method consistently outperforms existing approaches across various imbalance factors, delivering substantial improvements on the tail classes while remaining robust across different backbone architectures.

This paper proposes a method for short-term weekly water-demand forecasting combining various statistical techniques. In the proposed method, training datasets are prepared through exploratory data analysis, several data preprocessing steps, and an input selection step; also, forecasting models are constructed by support vector regression. After this, weekly water-demand forecasts are calculated using iterated and direct strategies. To verify the performance, the proposed method is applied to urban hourly water-demand datasets provided by the Battle of Water Demand Forecasting organized in the 3rd WDSA-CCWI Joint Conference.