Short-term traffic state prediction has become an integral component of an advanced traveler information system (ATIS) in intelligent transportation systems (ITS). Accurate modeling and short-term traffic prediction are quite challenging due to its intricate characteristics, stochastic, and dynamic traffic processes. Existing works in this area follow different modeling approaches that are focused to fit speed, density, or the volume data. However, the accuracy of such modeling approaches has been frequently questioned, thereby traffic state prediction over the short-term from such methods inflicts an overfitting issue. We address this issue to accurately model short-term future traffic state prediction using state-of-the-art models via hyperparameter optimization. To do so, we focused on different machine learning classifiers such as local deep support vector machine (LD-SVM), decision jungles, multi-layers perceptron (MLP), and CN2 rule induction. Moreover, traffic states are evaluated using traffic attributes such as level of service (LOS) horizons and simple if-then rules at different time intervals. Our findings show that hyperparameter optimization via random sweep yielded superior results. The overall prediction performances obtained an average improvement by over 95%, such that the decision jungle and LD-SVM achieved an accuracy of 0.982 and 0.975, respectively. The experimental results show the robustness and superior performances of decision jungles (DJ) over other methods.

中文翻译：

---

通过基于超参数优化的分类器进行短期交通状态预测。

短期交通状况预测已成为智能交通系统（ITS）中高级旅行者信息系统（ATIS）的组成部分。准确的建模和短期流量预测由于其复杂的特性，随机和动态的流量过程而具有很大的挑战性。该领域中的现有作品采用了不同的建模方法，这些方法专注于适应速度，密度或体积数据。然而，这种建模方法的准确性经常受到质疑，因此，从这种方法短期内的交通状态预测会引起过度拟合的问题。我们解决了这个问题，以通过超参数优化使用最新模型来对短期未来交通状态预测进行准确建模。为此，我们专注于不同的机器学习分类器，例如局部深度支持向量机（LD-SVM），决策丛林，多层感知器（MLP）和CN2规则归纳。此外，使用流量属性（例如服务水平（LOS）范围和不同时间间隔的简单if-then规则）来评估流量状态。我们的发现表明，通过随机扫描进行的超参数优化产生了出色的结果。总体预测性能平均提高了95％以上，因此决策丛林和LD-SVM的精度分别为0.982和0.975。实验结果表明，决策丛林（DJ）的鲁棒性和优越的性能优于其他方法。使用流量属性（例如服务水平（LOS）范围和不同时间间隔的简单if-then规则）评估流量状态。我们的发现表明，通过随机扫描进行的超参数优化产生了出色的结果。总体预测性能平均提高了95％以上，因此决策丛林和LD-SVM的精度分别为0.982和0.975。实验结果表明，决策丛林（DJ）的鲁棒性和优越的性能优于其他方法。使用流量属性（例如服务水平（LOS）范围和不同时间间隔的简单if-then规则）评估流量状态。我们的发现表明，通过随机扫描进行的超参数优化产生了出色的结果。总体预测性能平均提高了95％以上，因此决策丛林和LD-SVM的精度分别为0.982和0.975。实验结果表明，决策丛林（DJ）的鲁棒性和优越的性能优于其他方法。因此，决策丛林和LD-SVM的精度分别为0.982和0.975。实验结果表明，决策丛林（DJ）的鲁棒性和优越的性能优于其他方法。因此，决策丛林和LD-SVM的精度分别为0.982和0.975。实验结果表明，决策丛林（DJ）的鲁棒性和优越的性能优于其他方法。