a-machine-learning-approach-to-design-an-efficient-selective

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Mild cognitive impairment (MCI) is the first sign of dementia among elderly populations and its early detection is crucial in our aging societies. Common ...

Universidad CEU Cardenal Herrera

Time series forecasting is an important predictive methodology which can be applied to a wide range of problems. Particularly, forecasting the indoor temperature permits an improved utilization of the HVAC (Heating, Ventilating and Air Conditioning) systems in a home and thus a better energy efficiency. With such purpose the paper describes how to implement an Artificial Neural Network (ANN) algorithm in a low cost system-on-chip to develop an autonomous intelligent wireless sensor network. The present paper uses a Wireless Sensor Networks (WSN) to monitor and forecast the indoor temperature in a smart home, based on low resources and cost microcontroller technology as the 8051MCU. An on-line learning approach, based on Back-Propagation (BP) algorithm for ANNs, has been developed for real-time time series learning. It performs the model training with every new data that arrive to the system, without saving enormous quantities of data to create a historical database as usual, i.e., without previous knowledge. Consequently to validate the approach a simulation study through a Bayesian baseline model have been tested in order to compare with a database of a real application aiming to see the performance and accuracy. The core of the paper is a new algorithm, based on the BP one, which has been described in detail, and the challenge was how to implement a computational demanding algorithm in a simple architecture with very few hardware resources. 

Online learning algorithm for time series forecasting suitable for low cost wireless sensor networks nodes.

Nearly 1% of the global population has Epilepsy. Forecasting epileptic seizures with an acceptable confidence level, could improve the disease treatment and thus the lifestyle of the people who suffer it. To do that the electroencephalogram (EEG) signal is usually studied through spectral power band filtering, but this paper proposes an alternative novel method of preprocessing the EEG signal based on supervised filters. Such filters have been employed in a machine learning algorithm, such as the K-Nearest Neighbor (KNN), to improve the prediction of seizures. The proposed solution extends with this novel approach an algorithm that was submitted to win the third prize of an international Data Science challenge promoted by Kaggle contest platform and the American Epilepsy Society, the Epilepsy Foundation, National Institutes of Health (NIH) and Mayo Clinic. A formal description of these preprocessing methods is presented and a detailed analysis in terms of Receiver Operating Characteristics (ROC) curve and Area Under ROC curve is performed. The obtained results show statistical significant improvements when compared with the spectral power band filtering (PBF) typical baseline. A trend between performance and the dataset size is observed, suggesting that the supervised filters bring better information, compared to the conventional PBF filters, as the dataset grows in terms of monitored variables (sensors) and time length. The paper demonstrates a better accuracy in forecasting when new filters are employed and its main contribution is in the field of machine learning algorithms to develop more accurate predictive systems.

Supervised filters for EEG signal in naturally occurring epilepsy forecasting.

 The early detection of Mild Cognitive Impairment (MCI) is essential in aging societies where dementia is becoming a common manifestation among the elderly. Thus our aim is to develop a decision tree to discriminate individuals at risk of MCI among non-institutionalized elderly users of community pharmacy. A more clinically and patient-oriented role of the community pharmacist in primary care makes the dispensation of medication an adequate situation for an effective, rapid, easy, and reproducible screening of MCI.  A cross-sectional study was conducted with 728 non-institutionalized participants older than 65. A total of 167 variables were collected such as age, gender, educational attainment, daily sleep duration, reading frequency, subjective memory complaint, and medication. Two screening tests were used to detect possible MCI: Short Portable Mental State Questionnaire (SPMSQ) and the Mini-Mental State Examination (MMSE). Participants classified as positive were referred to clinical diagnosis. A decision tree and predictive models are presented as a result of applying techniques of machine learning for a more efficient enrollment.  One hundred and twenty-eight participants (17.4%) scored positive on MCI tests. A recursive partitioning algorithm with the most significant variables determined that the most relevant for the decision tree are: female sex, sleeping more than 9 h daily, age higher than 79 years as risk factors, and reading frequency. Moreover, psychoanaleptics, nootropics, and antidepressants, and anti-inflammatory drugs achieve a high score of importance according to the predictive algorithms. Furthermore, results obtained from these algorithms agree with the current research on MCI.  Lifestyle-related factors such as sleep duration and the lack of reading habits are associated with the presence of positive in MCI test. Moreover, we have depicted how machine learning provides a sound methodology to produce tools for early detection of MCI in community pharmacy.  The community of pharmacists provided with adequate tools could develop a crucial task in the early detection of MCI to redirect them immediately to the specialists in neurology or psychiatry. Pharmacists are one of the most accessible and regularly visited health care professionals and they can play a vital role in early detection of MCI.

Juan Pardo

Embedded Systems and Artificial Intelligence Group

Universidad CEU Cardenal Herrera

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Juan Pardo

.css-o250i3{font-size:18px;font-family:Open Sans,sans-serif;line-height:21.6px;}Embedded Systems and Artificial Intelligence Group

Universidad CEU Cardenal Herrera

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Embedded Systems and Artificial Intelligence Group