Search

Place recognition searches the closest map node to the query node, which is an important task for vehicle localization. Traditional visual place recognition methods for underground parking lots require the deployment of additional location signals, such as WiFi, Bluetooth. This paper utilizes only front-view images to realize place recognition. First, we employ a random coefficient to reduce the dimensionality of the ConvNet features to obtain the CCFs (Condense ConvNet Features). Second, we average the CCFs of a regional zone to obtain the RACF (Regional Aggregating ConvNet Feature). Compared with WiFi, Bluetooth, RACF is extracted from the front-view image and has a superior ability to represent regional zones. Third, we propose a multiscale place recognition method that adopts a coarse-to-fine strategy that greatly reduces time consumption and accelerates precision. Finally, we evaluate the proposed method on the data collected in the underground parking lot of Hubei University of Technology. The experimental results illustrate that the proposed method has high precision with a fast speed. [ABSTRACT FROM AUTHOR]

This paper focuses on the modeling of automatic pricing and replenishment strategies for perishable products with time-varying deterioration rates based on an improved SVR-LSTM-ARIMA hybrid model. This research aims to support supermarkets in planning future strategies, optimizing category structure, reducing loss rates, and improving profit margins and service quality. Specifically, the paper selects perishable vegetables as the research category and calculates the cost-plus ratio for each vegetable category. Correlation analysis is conducted with total sales, and a non-parametric relationship curve is obtained using support vector regression for nonlinear fitting. The long and short memory recurrent neural network is then used to predict sales volume, and a pricing strategy is calculated based on the fitting curve. Additionally, the paper establishes a correlation between loss rate and shelf life, corrects the daily average sales volume index, and solves the problem of quantity and category of replenishment using a backpack problem approach. By considering multiple constraints, a quantitative category replenishment volume and pricing strategy is obtained. The mathematical model proposed in this paper addresses the replenishment and pricing challenges faced by supermarkets, aiming to improve revenue and reduce loss while meeting market requirements. [ABSTRACT FROM AUTHOR]

Since cooling and heating loads are recognized as key characteristics for evaluating the energy efficiency of buildings, it appears indisputable that they must be predicted and analyzed for residential structures. Accordingly, the multi-layer perceptron neural network is applied for predicting the heating and cooling loads using the experimental dataset. The used dataset is obtained by monitoring the impact of the building's dimensions on energy consumption. To optimize the training process of the multi-layer perceptron neural network, several optimizers are employed. Besides, different statistical performance indicators are considered to see which selected optimizer outperforms the rest in terms of accuracy and authenticity. The obtained results emphasize the remarkable performance of adaptive chaotic grey wolf optimization, which can be used to train the multi-layer perceptron neural network and forecast the buildings' energy consumption with the highest accuracy. According to the obtained results, the hybrid multi-layer perceptron neural network- adaptive chaotic grey wolf optimization method demonstrates the best performance. The optimum number of neurons in the hidden layer is obtained to be 15. Also, based on the statistical performance indicators, the selected method reveals an R2 of 0.9123 and 0.9419 for cooling and heating loads, respectively. [ABSTRACT FROM AUTHOR]

This study examines changes in the local oceanographic and atmospheric conditions over the southern Bay of Bengal and adjacent Indian Ocean waters after the 2004 Indian Ocean tsunami based on satellite remote sensing data and atmospheric reanalysis fields. After the tsunami that occurred on 26 December 2004, the accumulated rainfall had a notably increase (600 mm per month) in January of 2005 over deep waters to the southeast of Sri Lanka. This rainfall increase after the tsunami was accompanied with cooling in the sea surface temperature (SST) (up to −2 °C). Four-day averaged SST anomalies had a noticeable increase (1-4 °C) after the tsunami over the deep waters to the southwest of the epicenter. Series of ocean atmospheric and biological variables changed successively after the change of SST. The chain of causality between the tsunami and the changes in the local atmospheric conditions is suggested. [ABSTRACT FROM AUTHOR]