| 1. |
- Afifi, Haitham, et al.
(författare)
-
Reinforcement learning for autonomous vehicle movements in wireless multimedia applications
- 2023
-
Ingår i: Pervasive and Mobile Computing. - : Elsevier. - 1574-1192 .- 1873-1589. ; 92
-
Tidskriftsartikel (refereegranskat)abstract
- We develop a Deep Reinforcement Learning (DeepRL)-based, multi-agent algorithm to efficiently control autonomous vehicles that are typically used within the context of Wireless Sensor Networks (WSNs), in order to boost application performance. As an application example, we consider wireless acoustic sensor networks where a group of speakers move inside a room. In a traditional setup, microphones cannot move autonomously and are, e.g., located at fixed positions. We claim that autonomously moving microphones improve the application performance. To control these movements, we compare simple greedy heuristics against a DeepRL solution and show that the latter achieves best application performance. As the range of audio applications is broad and each has its own (subjective) per-formance metric, we replace those application metrics by two immediately observable ones: First, quality of information (QoI), which is used to measure the quality of sensed data (e.g., audio signal strength). Second, quality of service (QoS), which is used to measure the network's performance when forwarding data (e.g., delay). In this context, we propose two multi-agent solutions (where one agent controls one microphone) and show that they perform similarly to a single-agent solution (where one agent controls all microphones and has a global knowledge). Moreover, we show via simulations and theoretical analysis how other parameters such as the number of microphones and their speed impacts performance.
|
|
| 2. |
|
|
| 3. |
- Boytsov, Andrey, et al.
(författare)
-
Formal verification of context and situation models in pervasive computing
- 2013
-
Ingår i: Pervasive and Mobile Computing. - : Elsevier BV. - 1574-1192 .- 1873-1589. ; 9:1, s. 98-117
-
Tidskriftsartikel (refereegranskat)abstract
- Pervasive computing is a paradigm that focuses on availability of computer resources anytime anywhere for any application and supports non-intrusive integration of computing services into everyday life. Context awareness is the core feature of pervasive computing. High-level context awareness can be enhanced by situation awareness that represents the ability to detect and reason about the real-life situations. In this article we propose, analyze and validate the formal verification method for situation definitions and demonstrate its feasibility and efficiency. Situations are often defined manually by domain experts and are, therefore, susceptible to definition inconsistencies and possible errors, which in turn can cause situation reasoning problems. The proposed method takes as an input properties of situations and dependencies among them as well as situation definitions in terms of low-level context features, and then either formally proves that the definitions do comply with the expected properties, or provides a complete set of counterexamples — context parameters that prove situation inconsistency. Evaluation and complexity analysis of the proposed approach are also presented and discussed. Examples and evaluation results demonstrate that the proposed approach can be used to verify real-life situation definitions, and detect non-obvious errors in situation specifications.
|
|
| 4. |
- Christin, Delphine, et al.
(författare)
-
IncogniSense: An anonymity-preserving reputation framework for participatory sensing applications
- 2013
-
Ingår i: 2012 IEEE International Conference on Pervasive Computing and Communications (PerCom). - : Elsevier. ; 9:3, s. 353-371
-
Konferensbidrag (refereegranskat)abstract
- Reputation systems are fundamental for assessing the quality of user contributions in participatory sensing. However, naively associating reputation scores to contributions allows adversaries to establish links between multiple contributions and thus de-anonymize users. We present the IncogniSense framework as a panacea to these privacy threats. IncogniSense utilizes periodic pseudonyms generated using blind signature and relies on reputation transfer between these pseudonyms. Simulations are used to analyze various reputation cloaking schemes that address the inherent trade-off between anonymity protection and loss in reputation. Our threat analysis confirms the robustness of IncogniSense and a prototype demonstrates that associated overheads are minimal.
|
|
| 5. |
- Cirillo, Marcello, 1978-, et al.
(författare)
-
Human-aware planning for robots embedded in ambient ecologies
- 2012
-
Ingår i: Pervasive and Mobile Computing. - : Elsevier. - 1574-1192 .- 1873-1589. ; 8:4, s. 542-561
-
Tidskriftsartikel (refereegranskat)abstract
- We address the issue of human-robot cohabitation in smart environments. In particular, the presence of humans in a robot's work space has a profound influence on how the latter should plan its actions. We propose the use of Human-Aware Planning, an approach in which the robot exploits the capabilities of a sensor-rich environment to obtain information about the (current and future) activities of the people in the environment, and plans its tasks accordingly.Here, we formally describe the planning problem behind our approach, we analyze its complexity and we detail the algorithm of our planner. We then show two application scenarios that could benefit from the techniques described. The first scenario illustrates the applicability of human-aware planning in a domestic setting, while the second one illustrates its use for a robotic helper in a hospital. Finally, we present a five hour-long test run in a smart home equipped with real sensors, where a cleaning robot has been deployed and where a human subject is acting. This test run in a real setting is meant to demonstrate the feasibility of our approach to human-robot interaction.
|
|
| 6. |
- Davies, R.J., et al.
(författare)
-
A user driven approach to develop a cognitive prosthetic to address the unmet needs of people with mild dementia
- 2009
-
Ingår i: Pervasive and Mobile Computing. - : Elsevier BV. - 1574-1192 .- 1873-1589. ; 5:3, s. 253-267
-
Tidskriftsartikel (refereegranskat)abstract
- This paper aims to provide the details of the approach adopted in the development of a cognitive prosthetic aimed to help address the unmet needs of people with mild dementia. The approach adopted is based on a waterfall style approach consisting of a series of three phases each of which contributes to the progression and improvement of a cognitive prosthetic-based solution. Within each phase, distinct stages of design, development and evaluation of the cognitive solution are conducted. The current paper discusses the distinct stages conducted in the first phase of the project which resulted in the design and development of a user driven solution based on the needs of 17 patient/carer dyads across three trial sites.
|
|
| 7. |
- Farag, Hossam, et al.
(författare)
-
Soft Decision Cooperative Spectrum Sensing with Noise Uncertainty Reduction
- 2017
-
Ingår i: Pervasive and Mobile Computing. - : Elsevier BV. - 1574-1192 .- 1873-1589. ; 35, s. 146-164
-
Tidskriftsartikel (refereegranskat)abstract
- Cognitive radio (CR) is a potential strategy for opportunistic access of idle resources to solve the conflicts between spectrum scarcity and underutilization. Spectrum sensing (SS) constitutes the most critical part in CR systems since the CR needs to detect the presence of primary signals reliably and quickly. Energy detection (ED) based SS is considered as the most preferable SS technique due to its simplicity and applicability. However, it is influenced by the effect of noise uncertainty which highly degrades its sensing performance. Cooperative spectrum sensing (CSS) is also introduced to mitigate some sensing problems such as multipath fading, shadowing, and hidden node problems. In this paper, we propose an enhanced fusion center (FC) rule for soft decision CSS using ED, which highly alleviates the noise uncertainty effect and enhances the sensing performance of cognitive radio networks (CRNs). In the proposed fusion rule, to increase the probability of detection and decrease the probability of false alarm, two dynamic thresholds are utilized by the FC. These thresholds are toggled based on predicting the current activity of the primary user (PU), and their values are dynamically changed based on estimating the noise uncertainty factor of the collected energy measurements from the CRs. To effectively predict (estimate) the current PU activity (the noise uncertainty factor), simple successive averaging processes over the collected energy measurements (the estimated noise variances) are performed by the FC, respectively. Theoretical analysis is performed on the proposed fusion rule for soft decision CSS to evaluate its enhanced false alarm and detection probabilities using different data combining schemes. Performance evaluations are also investigated to confirm the theoretical claims and to prove the effectiveness of the proposed scheme over the conventional ED based soft decision CSS.
|
|
| 8. |
- Fernandes Carvalho, D., et al.
(författare)
-
A test methodology for evaluating architectural delays of LoRaWAN implementations
- 2019
-
Ingår i: Pervasive and Mobile Computing. - : Elsevier B.V.. - 1574-1192 .- 1873-1589. ; 56:May, s. 1-17
-
Tidskriftsartikel (refereegranskat)abstract
- The Low Power Wide Area Networks (LPWANs) have been proposed as viable wireless connection method for the implementation of the Internet of Things (IoT), thanks to their wide coverage, low complexity and low power consumption. In this scenario, LoRaWAN emerged as a de-facto leading technology, because of its openness and the current availability of many devices (like sensors and gateways). Several implementations of the LoRaWAN specifications have appeared in the market, each one showing support for different hardware, different software architectures, and different operating systems. Thus, the need of test procedures for comparing them is evident. In this paper, a test methodology for the experimental assessment of architectural delays of LoRaWAN implementations is presented. The new approach is composed of: a mapping phase, needed for highlighting the LoRaWAN blocks inside the implementation under test; followed by a measurement phase, in which the relevant timestamps are taken along the information path from LoRaWAN node to LoRaWAN customer application. The use and the effectiveness of the proposed methodology are shown by means of use cases that involve different LoRaWAN implementations and several hardware platforms. The experiments described in the paper are not intended to evaluate particular implementations but they are aimed to assess the suitability of the proposed methodology. The results demonstrate that the proposed approach can be used to compare the performance of entire LoRaWAN systems, helping the owner of the infrastructure and the user in making choices and optimizations. © 2019 Elsevier B.V.
|
|
| 9. |
- Kranz, Matthias, et al.
(författare)
-
The mobile fitness coach : towards individualized skill assessment using personalized mobile devices
- 2013
-
Ingår i: Pervasive and Mobile Computing. - : Elsevier BV. - 1574-1192 .- 1873-1589. ; 9:2, s. 203-215
-
Tidskriftsartikel (refereegranskat)abstract
- We report on our extended research on GymSkill, a smartphone system for comprehensive physical exercising support, from sensor data logging, activity recognition to on-top skill assessment, using the phone’s built-in sensors. In two iterations, we used principal component breakdown analysis (PCBA) and criteria-based scores for individualized and personalized automated feedback on the phone, with the goal to track training quality and success and give feedback to the user, as well as to engage and motivate regular exercising. Qualitative feedback on the system was collected in a user study, and the system showed good evaluation results in an evaluation against manual expert assessments of video-recorded trainings.
|
|
| 10. |
- Murmann, Patrick, et al.
(författare)
-
Reconciling the what, when and how of privacy notifications in fitness tracking scenarios
- 2021
-
Ingår i: Pervasive and Mobile Computing. - : Elsevier. - 1574-1192 .- 1873-1589. ; 77
-
Tidskriftsartikel (refereegranskat)abstract
- The increasing number of fitness tracking wearables deployed worldwide poses challenges to the privacy of their users, esp. in terms of transparency. Privacy notifications facilitate transparency by providing users with situational awareness about the pro-cessing of their personal data. We present the results of two online surveys including English-speaking (n(Eng) = 154) and German-speaking (n(Ger) = 150) users of fitness track-ing devices from Europe, conducted to elicit determinants of notification settings. We found evidence for the perceived usefulness of privacy notifications, and for concordant predictors in terms of when and how users prefer to be notified about personal data processing in 12 scenarios related to fitness tracking.
|
|
