Based on the multi-source data available for bus operations, this paper proposes a health diagnosis system for single-line bus operation systems from two aspects: The operation efficiency and stability. Firstly, the i...
详细信息
Based on the multi-source data available for bus operations, this paper proposes a health diagnosis system for single-line bus operation systems from two aspects: The operation efficiency and stability. Firstly, the index weight has been defined and calculated based on the Entropy Method. The composite index of bus operation has been obtained, and the health classification standards that pertain to efficient and effective bus operations have also been constructed (Very Healthy, Healthy, Sub-Healthy, and Unhealthy). Secondly, the more efficient machine learning method has been used in order to establish the classification algorithm training set. The effect of the k-Nearest Neighbour and decision tree classification model has also been compared and analysed in this particular study. Finally, a bus line in Foshan is taken as a case study to verify the effectiveness of the method. This paper can effectively improve the diagnosis efficiency and accuracy by introducing the artificial intelligence algorithm into bus operation diagnosis. It provides a foundation for the development of bus operation health diagnosis decision support system with the function of "bus disease" prevention and treatment.
This paper presents an automated learning process to train the mountain car game model. It proposes an Enhanced Dyna-QPC model to effectively train the mountain car model in the stipulated time, based on their perceiv...
详细信息
ISBN:
(纸本)9781665438414
This paper presents an automated learning process to train the mountain car game model. It proposes an Enhanced Dyna-QPC model to effectively train the mountain car model in the stipulated time, based on their perceived environmental conditions. decisiontree (DT) classificationmodel along with Neural Network (NN)) model is used in this research to frame decision rules and self-train the game model respectively. Discrete Finite Deterministic Automata (DFA) concepts are included to finalize the state transition of the training model. Moreover, the Erdos-Renyi Random graph-generating model is used to generate dynamic state transition graphs to minimize the number of states. To increase the range of conditions and to derive meaningful decision rules, fuzzy concepts are used in this paper. Various simulation experiments have been conducted to evaluate the efficiency of the proposed training process. Simulation results reveal better performance over 3 popular models in the literature.
It is difficult to mine online buying behavior data by ignoring the classification of online buying behavior data, and the precision and recall are both on the low side. The training set of online buying behavior data...
详细信息
It is difficult to mine online buying behavior data by ignoring the classification of online buying behavior data, and the precision and recall are both on the low side. The training set of online buying behavior data is processed by top-down recursion, and a single decisiontree is created recursively, and a decision tree classification model is constructed. Based on the classification results of behavior data, the regular estimation of online shopping features is calculated by preprocessing customer behavior features, and the deep mining algorithm is designed. Experimental results show that the decisiontreemodel has good data clustering effect. Based on this, the precision and recall of online shopping behavior data mining are high, and the application performance is ideal.
暂无评论