Abstract

Abstract
Physically-based synthesis of high quality imagery, including global illumination light transport phenomena, results in a significant workload, which makes interactive rendering a very challenging task. We propose a VPL-based ray tracing approach that runs entirely in the GPU and achieves interactive frame rates while handling global illumination light transport phenomena. This approach is based on clustering both shading points and VPLs and computing visibility only among clusters' representatives. A new massively parallel K-means clustering algorithm, enables efficient execution in the GPU. Rendering artifacts, that could result from the piecewise constant approximation of the VPLs/shading points visibility function introduced by the clustering, are smoothed away by resorting to an innovative approach based on fuzzy clustering and weighted interpolation of the visibility function. The effectiveness of the proposed approach is experimentally verified for a collection of scenes, with frame rates larger than 3 fps and up to 25 fps being demonstrated.(c) 2022 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Abstract
This article introduces the E-MANAFA energy profiler, a plug-and-play, device-independent, model-based profiler capable of obtaining fine-grained energy measurements on Android devices. Besides having the capability to calculate performance metrics such as the energy consumed and runtime during a time interval, E-MANAFA also allows to estimate the energy consumed by each device component (e.g. CPU, WI-FI, screen). In this article, we present the main elements that compose this framework, as well as its workflow. In order to present the power of this tool, we demonstrate how the tool can measure the overhead of the instrumentation technique used in the PyAnaDroid application benchmarking pipeline, which already supports E-MANAFA to monitor power consumption in its Android application automatic execution process. Video demo: shorturl.at/hmyz5 © 2022 ACM.

Abstract
When developing mobile applications, developers often have to decide when to acquire and when to release resources. This leads to resource leaks, a kind of bug where a resource is acquired but never released. This is a common problem in Android applications that can degrade energy efficiency and, in some cases, can cause resources to not function properly. In this paper, we present an extension of EcoAndroid, an Android Studio plugin that improves the energy efficiency of Android applications, with an inter-procedural static analysis that detects resource leaks. Our analysis is implemented using Soot, FlowDroid, and Heros, which provide a static-analysis environment capable of processing Android applications and performing inter-procedural analysis with the IFDS framework. It currently supports the detection of leaks related to four Android resources: Cursor, SQLite-Database, Wakelock, and Camera. We evaluated our tool with the DroidLeaks benchmark and compared it with 8 other resource leak detectors. We obtained a precision of 72.5% and a recall of 83.2%. Our tool was able to uncover 191 previously unidentified leaks in this benchmark. These results show that our analysis can help developers identify resource leaks.

Abstract
Continuous ambulatory peritoneal dialysis (CAPD) is a treatment used by patients in the end-stage of chronic kidney diseases. Those patients need to be monitored using blood tests and those tests can present some patterns or correlations. It could be meaningful to apply data mining (DM) to the data collected from those tests. To discover patterns from meaningless data, it becomes crucial to use DM techniques. DM is an emerging field that is currently being used in machine learning to train machines to later aid health professionals in their decision-making process. The classification process can found patterns useful to understand the patients' health development and to medically act according to such results. Thus, this study focuses on testing a set of DM algorithms that may help in classifying the values of serum creatinine in patients undergoing CAPD procedures. Therefore, it is intended to classify the values of serum creatinine according to assigned quartiles. The better results obtained were highly satisfactory, reaching accuracy rate values of approximately 95%, and low relative absolute error values.

Abstract
The Portuguese General Directorate for Book, Archives and Libraries (DGLAB) has selected CIDOC CRM as the basis for its next-generation digital archive management software. Given the ontological foundations of the Conceptual Reference Model (CRM), a graph database or a triplestore was seen as the best candidate to represent a CRM-based data model for the new software. We thus decided to compare several of these databases, based on their maturity, features, performance in standard tasks and, most importantly, the Object-Graph Mappers (OGM) available to interact with each database in an object-oriented way. Our conclusions are drawn not only from a systematic review of related works but from an experimental scenario. For our experiment, we designed a simple CRM-compliant graph designed to test the ability of each OGM/database combination to tackle the so-called diamond-problem in Object-Oriented Programming (OOP) to ensure that property instances follow domain and range constraints. Our results show that (1) ontological consistency enforcement in graph databases and triplestores is much harder to achieve than in a relational database, making them more suited to an analytical rather than a transactional role; (2) OGMs are still rather immature solutions; and (3) neomodel, an OGM for the Neo4j graph database, is the most mature solution in the study as it satisfies all requirements, although it is also the least performing.