Water jet based autonomous surface vehicle for coastal waters operations

This paper presents the design of low cost, small autonomous surface vehicle for missions in the coastal waters and specifically for the challenging surf zone. The main objective of the vehicle design described in this paper is to address both the capability of operation at sea in relative challenging conditions and maintain a very low set of operational requirements (ease of deployment). This vehicle provides a first step towards being able to perform general purpose missions (such as data gathering or patrolling) and to at least in a relatively short distances to be able to be used in rescue operations (with very low handling requirements) such as carrying support to humans on the water. The USV is based on a commercially available fiber glass hull, it uses a directional waterjet powered by an electrical brushless motor for propulsion, thus without any protruding propeller reducing danger in rescue operations. Its small dimensions (1.5 m length) and weight allow versatility and ease of deployment. The vehicle design is described in this paper both from a hardware and software point of view. A characterization of the vehicle in terms of energy consumption and performance is provided both from test tank and operational scenario tests. An example application in search and rescue is also presented and discussed with the integration of this vehicle in the European ICARUS (7th framework) research project addressing the development and integration of robotic tools for large scale search and rescue operations.

Performance of state space and ARIMA models for consumer retail sales forecasting

Forecasting future sales is one of the most important issues that is beyond all strategic and planning decisions in effective operations of retail businesses. For profitable retail businesses, accurate demand forecasting is crucial in organizing and planning production, purchasing, transportation and labor force. Retail sales series belong to a special type of time series that typically contain trend and seasonal patterns, presenting challenges in developing effective forecasting models. This work compares the forecasting performance of state space models and ARIMA models. The forecasting performance is demonstrated through a case study of retail sales of five different categories of women footwear: Boots, Booties, Flats, Sandals and Shoes. On both methodologies the model with the minimum value of Akaike's Information Criteria for the in-sample period was selected from all admissible models for further evaluation in the out-of-sample. Both one-step and multiple-step forecasts were produced. The results show that when an automatic algorithm the overall out-of-sample forecasting performance of state space and ARIMA models evaluated via RMSE, MAE and MAPE is quite similar on both one-step and multi-step forecasts. We also conclude that state space and ARIMA produce coverage probabilities that are close to the nominal rates for both one-step and multi-step forecasts.