| 1. |
- Oss Boll, Heloísa, et al.
(författare)
-
Graph neural networks for clinical risk prediction based on electronic health records : A survey
- 2024
-
Ingår i: Journal of Biomedical Informatics. - Maryland Heights, MO : Academic Press. - 1532-0464 .- 1532-0480. ; 151
-
Forskningsöversikt (refereegranskat)abstract
- Objective: This study aims to comprehensively review the use of graph neural networks (GNNs) for clinical risk prediction based on electronic health records (EHRs). The primary goal is to provide an overview of the state-of-the-art of this subject, highlighting ongoing research efforts and identifying existing challenges in developing effective GNNs for improved prediction of clinical risks. Methods: A search was conducted in the Scopus, PubMed, ACM Digital Library, and Embase databases to identify relevant English-language papers that used GNNs for clinical risk prediction based on EHR data. The study includes original research papers published between January 2009 and May 2023. Results: Following the initial screening process, 50 articles were included in the data collection. A significant increase in publications from 2020 was observed, with most selected papers focusing on diagnosis prediction (n = 36). The study revealed that the graph attention network (GAT) (n = 19) was the most prevalent architecture, and MIMIC-III (n = 23) was the most common data resource. Conclusion: GNNs are relevant tools for predicting clinical risk by accounting for the relational aspects among medical events and entities and managing large volumes of EHR data. Future studies in this area may address challenges such as EHR data heterogeneity, multimodality, and model interpretability, aiming to develop more holistic GNN models that can produce more accurate predictions, be effectively implemented in clinical settings, and ultimately improve patient care. © 2024 The Authors
|
|
| 2. |
- Vicenzi, Julio Costella, et al.
(författare)
-
Dynamic Offloading for Improved Performance and Energy Efficiency in Heterogeneous IoT-Edge-Cloud Continuum
- 2023
-
Ingår i: 2023 IEEE Computer Society Annual Symposium on VLSI (ISVLSI). - : IEEE. - 9798350327694 - 9798350327700
-
Konferensbidrag (refereegranskat)abstract
- While machine learning applications in IoT devices are getting more widespread, the computational and power limitations of these devices pose a great challenge. To handle this increasing computational burden, edge, and cloud solutions emerge as a means to offload computation to more powerful devices. However, the unstable nature of network connections constantly changes the communication costs, making the offload process (i.e., when and where to transfer data) a dynamic trade-off. In this work, we propose DECOS: a framework to automatically select at run-time the best offloading solution with minimum latency based on the computational capabilities of devices and network status at a given moment. We use heterogeneous devices for edge and Cloud nodes to evaluate the framework's performance using MobileNetV1 CNN and network traffic data from a real-world 4G bandwidth dataset. DECOS effectively selects the best processing node to maintain the minimum possible latency, reducing it up to 29% compared to Cloud-exclusive processing while reducing the energy consumption by 1.9times compared to IoT-exclusive execution. © 2023 IEEE.
|
|
| 3. |
- Marinho, Marco A. M., et al.
(författare)
-
Array interpolation based on multivariate adaptive regression splines
- 2016
-
Ingår i: 2016 IEEE Sensor Array and Multichannel Signal Processing Workshop (SAM). - Piscataway, NJ : Institute of Electrical and Electronics Engineers (IEEE).
-
Konferensbidrag (refereegranskat)abstract
- Many important signal processing techniques such as Spatial Smoothing, Forward Backward Averaging and Root-MUSIC, rely on antenna arrays with specific and precise structures. Arrays with such ideal structures, such as a centro-hermitian structure, are often hard to build in practice. Array interpolation is used to enable the usage of these techniques with imperfect (not having a centro-hermitian structure) arrays. Most interpolation methods rely on methods based on least squares (LS) to map the output of a perfect virtual array based on the real array. In this work, the usage of Multivariate Adaptive Regression Splines (MARS) is proposed instead of the traditional LS to interpolate arrays with responses largely different from the ideal.
|
|
| 4. |
- Pedrollo, Guilherme, et al.
(författare)
-
Using smart virtual-sensor nodes to improve the robustness of indoor localization systems
- 2021
-
Ingår i: Sensors. - Basel : MDPI AG. - 1424-8220. ; 21:11
-
Tidskriftsartikel (refereegranskat)abstract
- Young, older, frail, and disabled individuals can require some form of monitoring or assistance, mainly when critical situations occur, such as falling and wandering. Healthcare facilities are increasingly interested in e-health systems that can detect and respond to emergencies on time. Indoor localization is an essential function in such e-health systems, and it typically relies on wireless sensor networks (WSN) composed of fixed and mobile nodes. Nodes in the network can become permanently or momentarily unavailable due to, for example, power failures, being out of range, and wrong placement. Consequently, unavailable sensors not providing data can compromise the system’s overall function. One approach to overcome the problem is to employ virtual sensors as replacements for unavailable sensors and generate synthetic but still realistic data. This paper investigated the viability of modelling and artificially reproducing the path of a monitored target tracked by a WSN with unavailable sensors. Particularly, the case with just a single sensor was explored. Based on the coordinates of the last measured positions by the unavailable node, a neural network was trained with 4 min of not very linear data to reproduce the behavior of a sensor that become unavailable for about 2 min. Such an approach provided reasonably successful results, especially for areas close to the room’s entrances and exits, which are critical for the security monitoring of patients in healthcare facilities. © 2021 by the authors.
|
|
| 5. |
- Schwarzrock, Janaína, et al.
(författare)
-
Solving task allocation problem in multi Unmanned Aerial Vehicles systems using Swarm intelligence
- 2018
-
Ingår i: Engineering applications of artificial intelligence. - Oxford : Elsevier. - 0952-1976 .- 1873-6769. ; 72, s. 10-20
-
Tidskriftsartikel (refereegranskat)abstract
- The envisaged usage of multiple Unmanned Aerial Vehicles (UAVs) to perform cooperative tasks is a promising concept for future autonomous military systems. An important aspect to make this usage a reality is the solution of the task allocation problem in these cooperative systems. This paper addresses the problem of tasks allocation among agents representing UAVs, considering that the tasks are created by a central entity, in which the decision of which task will be performed by each agent is not decided by this central entity, but by the agents themselves. The assumption that tasks are created by a central entity is a reasonable one, given the way strategic planning is carried up in military operations. To enable the UAVs to have the ability to decide which tasks to perform, concepts from swarm intelligence and multi-agent system approach are used. Heuristic methods are commonly used to solve this problem, but they present drawbacks. For example, many tasks end up not begin performed even if the UAVs have enough resources to execute them. To cope with this problem, this paper proposes three algorithm variants that complement each other to form a new method aiming to increase the amount of performed tasks, so that a better task allocation is achieved. Through experiments in a simulated environment, the proposed method was evaluated, yielding enhanced results for the addressed problem compared to existing methods reported in the literature. © 2018 Elsevier Ltd
|
|
| 6. |
- Agnoletto, Daniel, et al.
(författare)
-
Time slot transmission scheme with packet prioritization for Bluetooth low energy devices used in real-time applications
- 2020
-
Ingår i: International Journal of Wireless Information Networks. - New York, NY : Springer Science+Business Media B.V.. - 1068-9605 .- 1572-8129. ; 27:4, s. 518-534
-
Tidskriftsartikel (refereegranskat)abstract
- Bluetooth Low Energy (BLE) is one of the most important technologies that feed the growing field of Internet of Things and Wireless Sensor Networks. Due to its flexibility and unique low power-consumption, an increasing number of industrial devices, household appliances and wearables are being designed using it. However, the real-time demands of these networks such as timing and Quality of Service are not fully covered by the protocol itself. To help improve and offer some control over these characteristics, this paper presents a time slot transmission scheme with packet prioritization. It is based on the division and allocation of the connection interval to two types of messages: real-time and ordinary. The goal is to offer the lowest packet loss and time guarantees for real-time messages, while providing acceptable throughput for ordinary ones. Since the probability of a BLE connection to close increases with the number of packets sent through it, the position where a real-time packet is being sent as well as the number of ordinary messages in a connection represent key factors. The use of the first and last slot for real-time packets with ordinary flow restricted to the space between them decreases the transmission delay uncertainty and allows probability tuning based on the number of ordinary messages. Simulations were performed using the proposed scheme and a reduction of more than 100 times in the delay variance was observed for real-time transmissions. Regarding reliability, around 5% of the packets were lost for a bit error rate of 10−3. © 2020, Springer Science+Business Media, LLC, part of Springer Nature.
|
|
| 7. |
- Allgayer, Rodrigo, et al.
(författare)
-
Analysis of distributed control system using remote method invocation in wireless network
- 2011
-
Ingår i: IECON 2011 Proceedings. - New York : IEEE. - 9781612849720 ; , s. 346-351
-
Konferensbidrag (refereegranskat)abstract
- This work presents the temporal analysis for a distributed differential control system for a mobile robot deployed on a wireless network using the SunSPOT platform. The system is programmed in Java and each of its part is executed in a distinct processor which cooperates via a wireless network. The communication between the network nodes is made by remote procedure calls, which are implemented by a minimum version of the Java RMI (mRMI), presented in this work. Simulation results are compared to experimental data acquired by the deployment of the system on real devices, the SunSPOTs. The comparisons reveal that the distributed solution presents fairly good results besides the inserted errors due to the wireless communication. © 2011 IEEE.
|
|
| 8. |
- Binotto, Alécio Pedro Delazari, et al.
(författare)
-
Towards Dynamic Task Scheduling and Reconfiguration using an Aspect Oriented Approach applied on Real-time concerns of Industrial Systems
- 2009
-
Ingår i: Elsevier IFAC Publications / IFAC Proceedings series. - Frankfurt : Elsevier. - 1474-6670. ; 13:PART 1, s. 1423-1428
-
Tidskriftsartikel (refereegranskat)abstract
- High performance computational platforms are required by industries that make use of automatic methods to manage modern machines, which are mostly controlled by high-performance specific hardware with processing capabilities. It usually works together with CPUs, forming a powerful execution platform. On an industrial production line, distinct tasks can be assigned to be processed by different machines depending on certain conditions and production parameters. However, these conditions can change at run-time influenced mainly by machine failure and maintenance, priorities changes, and possible new better task distribution. Therefore, self-adaptive computing is a potential paradigm as it can provide flexibility to explore the machine resources and improve performance on different execution scenarios of the production line. One approach is to explore scheduling and run-time task migration among machines’ hardware towards a balancing of tasks, aiming performance and production gain. This way, the monitoring of time requirements and its crosscutting behaviour play an important role for task (re)allocation decisions. This paper introduces the use of software aspect-oriented paradigms to perform machines’ monitoring and a self-rescheduling strategy of tasks to address nonfunctional timing constraints. As case study, tasks for a production line of aluminium ingots are designed. © 2009 IFAC.
|
|
| 9. |
- Binotto, Alécio P. D., et al.
(författare)
-
Towards task dynamic reconfiguration over asymmetric computing platforms for UAVs surveillance systems
- 2009
-
Ingår i: Scalable computing. - Timisoara : Universitatea de Vest din Timisoara / West University of Timisoara. - 1895-1767. ; 10:3, s. 277-289
-
Tidskriftsartikel (refereegranskat)abstract
- High-performance platforms are required by modern applications that make use of massive calculations. Actually, low-cost and high-performance specific hardware (e.g. GPU) can be a good alternative along with CPUs, which turned to multiple cores, forming powerful heterogeneous desktop execution platforms. Therefore, self-adaptive computing is a promising paradigm as it can provide flexibility to explore different computing resources, on which heterogeneous cluster can be created to improve performance on different execution scenarios. One approach is to explore run-time tasks migration among node's hardware towards an optimal system load-balancing aiming at performance gains. This way, time requirements and its crosscutting behavior play an important role for task (re)allocation decisions. This paper presents a self-rescheduling task strategy that makes use of aspect-oriented paradigms to address non-functional application timing constraints from earlier design phases. A case study exploring Radar Image Processing tasks is presented to demonstrate the proposed approach. Simulations results for this case study are provided in the context of a surveillance system based on Unmanned Aerial Vehicles (UAVs). © 2009 SCPE.
|
|
| 10. |
- Boeira, Felipe, 1992-, et al.
(författare)
-
Effects of Colluding Sybil Nodes in Message Falsification Attacks for Vehicular Platooning
- 2017
-
Ingår i: 2017 IEEE Vehicular Networking Conference (VNC). - : IEEE. - 9781538609866 - 9781538609859 - 9781538609873
-
Konferensbidrag (refereegranskat)abstract
- This paper studies the impact of vulnerabilities associated with the Sybil attack (through falsification of multiple identities) and message falsification in vehicular platooning. Platooning employs Inter-Vehicular Communication (IVC) to control a group of vehicles. It uses broadcast information such as acceleration, position, and velocity to operate a longitudinal control law. Cooperation among vehicles allows platoons to reduce fuel consumption and risks associated with driver mistakes. In spite of these benefits, the use of network communication to control vehicles exposes a relevant attack surface that can be exploited by malicious actors. To carry out this study, we evaluate five scenarios to quantify the potential impact of such attacks, identifying how platoons behave under varying Sybil attack conditions and what are the associated safety risks. This research also presents the use of location hijacking attack. In this attack, innocent vehicles that are not part of a platoon are used as a way to create trust bond between the false identities and the physical vehicles. We demonstrate that the ability to create false identities increases the effectiveness of message falsification attacks by making them easier to deploy and harder to detect in time.
|
|
