Search

Background: Machine learning (ML) represents a powerful tool to capture relationships between molecular alterations and cancer types and to extract biological information. Here, we developed a plain ML model aimed at distinguishing cancer types based on genetic lesions, providing an additional tool to improve cancer diagnosis, particularly for tumors of unknown origin. Methods: TCGA data from 9,927 samples spanning 32 different cancer types were downloaded from cBioportal. A vector space model type data transformation technique was designed to build consistently homogeneous new datasets containing, as predictive features, calls for somatic point mutations and copy number variations at chromosome arm-level, thus allowing the use of the XGBoost classifier models. Considering the imbalance in the dataset, due to large difference in the number of cases for each tumor, two preprocessing strategies were considered: i) setting a percentage cut-off threshold to remove less represented cancer types, ii) dividing cancer types into different groups based on biological criteria and training a specific XGBoost model for each of them. The performance of all trained models was mainly assessed by the out-of-sample balanced accuracy (BACC) and the AUC scores. Results: The XGBoost classifier achieved the best performance (BACC 77%; AUC 97%) on a dataset containing the 10 most represented tumor types. Moreover, dividing the 18 most represented cancers into three different groups (endocrine-related carcinomas, other carcinomas and other cancers),such analysis models achieved 78%, 71% and 86% BACC, respectively, with AUC scores greater than 96%. In addition, the model capable of linking each group to a specific cancer type reached 81% BACC and 94% AUC. Overall, the diagnostic potential of our model was comparable/higher with respect to others already described in literature and based on similar molecular data and ML approaches. Conclusions: A boosted ML approach able to accurately discriminate different cancer types was developed. The methodology builds datasets simpler and more interpretable than the original data, while keeping enough information to accurately train standard ML models without resorting to sophisticated Deep Learning architectures. In combination with histopathological examinations, this approach could improve cancer diagnosis by using specific DNA alterations, processed by a replicable and easy-to-use automated technology. The study encourages new investigations which could further increase the classifier's performance, for example by considering more features and dividing tumors into their main molecular subtypes. [ABSTRACT FROM AUTHOR]

Forecasting volumes of incoming calls is the first step of the workforce planning process in call centers and represents a prominent issue from both research and industry perspectives. We investigate the application of Neural Networks to predict incoming calls 24 hours ahead. In particular, a Machine Learning deep architecture known as Echo State Network, is compared with a completely different rolling horizon shallow Neural Network strategy, in which the lack of recurrent connections is compensated by a careful input selection. The comparison, carried out on three different real world datasets, reveals better predictive performance for the shallow approach. The latter appears also more robust and less demanding, reducing the inference time by a factor of 2.5 to 4.5 compared to Echo State Networks. [ABSTRACT FROM AUTHOR]

The forecasts of electricity and heating demands are key inputs for the efficient design and operation of energy systems serving urban districts, buildings, and households. Their accuracy may have a considerable effect on the selection of the optimization approach and on the solution quality. In this work, we describe a supervised learning approach based on shallow Artificial Neural Networks to develop an accurate model for predicting the daily hourly energy consumption of an energy district 24 h ahead. Predictive models are generated for each one of the two considered energy types, namely electricity and heating. Single-layer feedforward neural networks are trained with the efficient and robust decomposition algorithm DEC proposed by Grippo et al. on a data set of historical data, including, among others, carefully selected information related to the hourly energy consumption of the energy district and the hourly weather data of the region where the district is located. Three different case studies are analyzed: a medium-size hospital located in the Emilia-Romagna Italian region, the whole Politecnico di Milano University campus, and a single building of a department belonging to the latter. The computational results indicate that the proposed method with enriched data inputs compares favorably with the benchmark forecasting and Machine Learning techniques, namely, ARIMA, Support Vector Regression and long short-term memory networks. [ABSTRACT FROM AUTHOR]