The application of an ensemble of boosted elman networks to time series prediction : a benchmark study

In this paper, the application of multiple Elman neural networks to time series data regression problems is studied. An ensemble of Elman networks is formed by boosting to enhance the performance of the individual networks. A modified version of the AdaBoost algorithm is employed to integrate the predictions from multiple networks. Two benchmark time series data sets, i.e., the Sunspot and Box-Jenkins gas furnace problems, are used to assess the effectiveness of the proposed system. The simulation results reveal that an ensemble of boosted Elman networks can achieve a higher degree of generalization as well as performance than that of the individual networks. The results are compared with those from other learning systems, and implications of the performance are discussed.

Incorporating differences in marginal utilities of time across activities in a time allocation model

Most existing activity time allocation models assume that individuals allocate their time to different activities over a period in such a way that the marginal utilities of time across activities are equal. Their argument is that, if not equal, an individual is free to allocate more time to those activities whose marginal utilities of time are higher and, finally allocates the optimal time to each activity with equal marginal utility. However, such an ideal situation may not always prevail in reality, especially when an individual is under income constraint and/or under intense time pressure. In order to incorporate such differences in marginal utilities of time across activities, we enrich the traditional activity time allocation model by explicitly including income constraint and by adding marginal extension activity choice model. As an application, the developed integrated model is used to estimate the value of activity time during weekends in Tokyo. The results are encouraging in that they forecast the individual time allocation more accurately and estimate realistically the value of activity time for each activity in a set of different activities than do by existing traditional models.

Faster and parameter-free discord search in quasi-periodic time series

Time series discord has proven to be a useful concept for time-series anomaly identification. To search for discords, various algorithms have been developed. Most of these algorithms rely on pre-building an index (such as a trie) for subsequences. Users of these algorithms are typically required to choose optimal values for word-length and/or alphabet-size parameters of the index, which are not intuitive. In this paper, we propose an algorithm to directly search for the top-K discords, without the requirement of building an index or tuning external parameters. The algorithm exploits quasi-periodicity present in many time series. For quasi-periodic time series, the algorithm gains significant speedup by reducing the number of calls to the distance function.

Time series analysis of air transportation service quality and travel demand in Japan

The evolution of domestic air travel service in Japan is a product of many factors including airline responses to the changing aviation market, government interventions in terms of regulatory/deregulatory policies, infrastructure investments, and changes in market structure. This paper presents an empirical investigation of the changing quality of passenger airline service and its implications in the domestic aviation market in Japan using qualitative review and a time series analysis of the domestic airline markets from 1986 to 2003. The results show that to meet the ultimate aim of deregulation to increase air passengers’ welfare gain, there is a need to instill measures to correct service imbalance and to create innovative airport demand-capacity management measures.

Parameter-free search of time-series discord

Time-series discord is widely used in data mining applications to characterize anomalous subsequences in time series. Compared to some other discord search algorithms, the direct search algorithm based on the recurrence plot shows the advantage of being fast and parameter free. The direct search algorithm, however, relies on quasi-periodicity in input time series, an assumption that limits the algorithm's applicability. In this paper, we eliminate the periodicity assumption from the direct search algorithm by proposing a reference function for subsequences and a new sampling strategy based on the reference function. These measures result in a new algorithm with improved efficiency and robustness, as evidenced by our empirical evaluation.