Cookies Policy
The website need some cookies and similar means to function. If you permit us, we will use those means to collect data on your visits for aggregated statistics to improve our service. Find out More
Accept Reject
  • Menu
Publications

2021

Deep learning for drug response prediction in cancer

Authors
Baptista, D; Ferreira, PG; Rocha, M;

Publication
Briefings in Bioinformatics

Abstract
Abstract Predicting the sensitivity of tumors to specific anti-cancer treatments is a challenge of paramount importance for precision medicine. Machine learning(ML) algorithms can be trained on high-throughput screening data to develop models that are able to predict the response of cancer cell lines and patients to novel drugs or drug combinations. Deep learning (DL) refers to a distinct class of ML algorithms that have achieved top-level performance in a variety of fields, including drug discovery. These types of models have unique characteristics that may make them more suitable for the complex task of modeling drug response based on both biological and chemical data, but the application of DL to drug response prediction has been unexplored until very recently. The few studies that have been published have shown promising results, and the use of DL for drug response prediction is beginning to attract greater interest from researchers in the field. In this article, we critically review recently published studies that have employed DL methods to predict drug response in cancer cell lines. We also provide a brief description of DL and the main types of architectures that have been used in these studies. Additionally, we present a selection of publicly available drug screening data resources that can be used to develop drug response prediction models. Finally, we also address the limitations of these approaches and provide a discussion on possible paths for further improvement. Contact:mrocha@di.uminho.pt

2021

Experimental investigation of a strain gauge sensor based on Fiber Bragg Grating for diameter measurement

Authors
Cardoso, VHR; Caldas, P; Giraldi, MTR; Frazao, O; de Carvalho, CJR; Costa, JCWA; Santos, JL;

Publication
Optical Fiber Technology

Abstract
A strain gauge sensor based on Fiber Bragg Grating (FBG) for diameter measurement is proposed and experimentally demonstrated. The sensor is easily fabricated inserting the FBG on the strain gauge—it was fabricated using a 3D printer—and fixing the FBG in two points of this structure. The idea is to vary the diameter of the structure. We developed two experimental setups, the first one is used to evaluate the response of the FBG to strain and the second one to assess the possibility of using the structure developed to monitor the desired parameter. The results demonstrated that the structure can be used as a way to monitor the diameter variation in some applications. The sensor presented a sensitivity of 0.5361 nm/mm and a good linear response of 0.9976 using the Strain Gauge with FBG and fused taper. © 2020 Elsevier Inc.

2021

Elderly Monitoring – An EPS@ISEP 2020 Project

Authors
Priebe, J; Swiatek, K; Vidinha, M; Vaduva, MR; Tiits, M; Sorescu, TG; Malheiro, B; Ribeiro, C; Justo, J; Silva, MF; Ferreira, P; Guedes, P;

Publication
Advances in Intelligent Systems and Computing - Trends and Applications in Information Systems and Technologies

Abstract

2021

A Dijkstra-Inspired Graph Algorithm for Fully Autonomous Tasking in Industrial Applications

Authors
Lotfi, M; Osorio, GJ; Javadi, MS; Ashraf, A; Zahran, M; Samih, G; Catalao, JPS;

Publication
IEEE Transactions on Industry Applications

Abstract

2021

Integrated Demand Response programs and energy hubs retail energy market modelling

Authors
Aghamohammadloo, H; Talaeizadeh, V; Shahanaghi, K; Aghaei, J; Shayanfar, H; Shafie khah, M; Catalao, JPS;

Publication
ENERGY

Abstract
The present research aims to formulate competition in a retail energy market in the presence of an Integrated Demand Response (IDR) program to reduce prosumer costs and increase retailer profits. This gives prosumers more degrees of freedom to reduce their energy costs. The retail energy market includes retailers and prosumers equipped with an energy hub containing a boiler for producing heat and combined heat and power (CHP). Retailers aim to maximize profit, whereas prosumers seek to minimize their costs. Hence, a multi-leader-follower game with a bi-level program emerges in which the upper level deals with the profit maximization of each retailer while the lower level considers the cost minimization of each prosumer. The strategic behaviour of each retailer is modelled as a Mathematical Program with Equilibrium Constraints (MPEC) problem. Simultaneously solving all MPECs, which leads to an Equilibrium Problem with Equilibrium Constraints (EPEC), determines the market equilibrium point. The equilibrium point is achieved using mathematical, analytical methods and linearization of nonlinear constraints by accurate techniques. Two different case studies are developed to investigate how the number of retailers influences the market equilibrium point. The first case includes two retailers, while the second case considers an increase in the number of retailers. The results demonstrate that with an increase in retailers' number, their competition increases, causing the prosumers costs to reduce. Furthermore, our results suggest the IDR impact on reduced prosumers cost and increased retailers profit.

2021

Explainability Metrics of Deep Convolutional Networks for Photoplethysmography Quality Assessment

Authors
Zhang, O; Ding, C; Pereira, T; Xiao, R; Gadhoumi, K; Meisel, K; Lee, RJ; Chen, YR; Hu, X;

Publication
IEEE Access

Abstract

  • 2
  • 2426