Current Issue : April - June Volume : 2020 Issue Number : 2 Articles : 5 Articles
This paper describes the development of an application for mobile devices under the iOS\nplatform which has the objective of monitoring patients with alterations or affections from cardiac\npathologies. The software tool developed for mobile devices provides a patient and a specialist\ndoctor the ability to handle and treat disease remotely while monitoring through the technique of\nnon-contact photoplethysmography (PPG). The mobile application works by processing red, green,\nand blue (RGB) color video images on a specific region of the face, thus obtaining the intensity of the\npixels in the green channel. The results are then processed using mathematical algorithms and Fourier\ntransform, moving from the time domain to the frequency domain to ensure proper interpretation and\nto obtain the pulses per minute (PPM). The results are favorable because a comparison of the results\nwas made with respect to the application of a medical-grade pulse-oximeter, where an error rate of 3%\nwas obtained, indicating the acceptable performance of our application. The present technological\ndevelopment provides an application tool with significant potential in the area of health....
Software trustworthiness is an important research field in software engineering.\nIn order to appropriately evaluate it, some different measurement approaches have been proposed,\nwhich have important guiding significance for improving software trustworthiness. Recently, we have\ninvestigated attributes-based approaches. That is, how to maximize trustworthy degree of some\nsoftware satisfying a given threshold by adjusting every attribute value such that the cost is minimal,\ni.e., the sum of all attribute values is as small as possible. The work is helpful to improve the software\nquality under the same cost. This paper continues this work and considers a reallocation approach to\ndealing with the problem that the threshold and the minimal constraints of every attribute values\ndynamically increase. In this process, the costs of trustworthiness improvement should be ensured to\nbe minimal. For this purpose, we firstly define a reallocation model by mathematical programming.\nThen we introduce the notion of growth function. Based on this, a polynomial reallocation algorithm\nis designed to solve the above reallocation model. Finally, we verify our work on spacecraft softwares\nand the results show that this work is valid....
To improve the safety of vessels in the offshore wind farms, this paper develops the design and implementation of a multiclient\nmonitoring system that is a ship monitoring system software (SMSS). The design is based on automatic identification system (AIS)\nand geographic information system (GIS). The data of the target ships around the offshore wind farm zone will be displayed on a\nGIS map and monitored in the implemented software system in real time. The localization method and the warning zone\njudgment algorithm are used to carry out the vessel position around the offshore wind farm area. The software system includes\nsome unavoidable features, namely, AIS encoding and decoding and automatic sending of short messages to ships arriving in the\nwarning area. The tests of the SMSS show that in real time, the software system performs properly by detecting the target ships\naround the warning zone and sends short messages to these ships, which makes the SMSS more effective and reliable....
Energy consumption information for devices, as available in the literature, is typically obtained with ad hoc approaches, thus\nmaking replication and consumption data comparison difficult. We propose a process for measuring the energy consumption of a\nsoftware application. The process contains four phases, each providing a structured deliverable that reports the information\nrequired to replicate the measurement. The process also guides the researcher on a threat to validity analysis to be included in each\ndeliverable. This analysis ensures better reliability, trust, and confidence to reuse the collected consumption data. Such a process\nproduces a structured consumption data for any kind of electronic device (IoT devices, mobile phones, personal computers,\nservers, etc.), which can be published and shared with other researchers fostering comparison or further investigations. A real case\nexample demonstrates how to apply the process and how to create the required deliverables....
Extracting fine-grained information from social media is traditionally a challenging\ntask, since the language used in social media messages is usually informal,\nwith creative genre-specific terminology and expression. How to handle\nsuch a challenge so as to automatically understand the opinions that people\nare communicating has become a hot subject of research. In this paper, we\naim to show that leveraging the pre-learned knowledge can help neural network\nmodels understand the creative language in Tweets. In order to address\nthis idea, we present a transfer learning model based on BERT. We fine-turned\nthe pre-trained BERT model and applied the customized model to two downstream\ntasks described in SemEval-2018: Irony Detection task and Emoji Prediction\ntask of Tweets. Our model could achieve an F-score of 38.52 (ranked\n1/49) in Emoji Prediction task and 67.52 (ranked 2/43) and 51.35 (ranked\n1/31) in Irony Detection subtask A and subtask B. The experimental results\nvalidate the effectiveness of our idea....
Loading....