110,126 research outputs found
Long–term information collection with energy harvesting wireless sensors: a multi–armed bandit based approach
No full textThis paper reports on the development of a multi–agent approach to long-term information collection in networks of energy harvesting wireless sensors. In particular, we focus on developing energy management and data routing policies that adapt their behaviour according to the energy that is harvested, in order to maximise the amount of information collected given the available energy budget. In so doing, we introduce a new energy management technique, based on multi–armed bandit learning, that allows each agent to adaptively allocate its energy budget across the tasks of data sampling, receiving and transmitting. By using this approach, each agent can learn the optimal energy budget settings that give it efficient information collection in the long run. Then, we propose two novel decentralised multi–hop algorithms for data routing. The first proveably maximises the information throughput in the network, but can sometimes involve high communication cost. The second algorithm provides near–optimal performance, but with reduced computational and communication costs. Finally, we demonstrate that, by using our approaches for energy management and routing, we can achieve a 120% improvement in long term information collection against state–of–the–art benchmarks
Multi–Armed Bandit Models for Efficient Long–Term Information Collection in Wireless Sensor Networks
No full textWe are entering a new age in the evolution of computer systems, in which pervasive computing technologies seamlessly interact with human users. These technologies serve people in their everyday lives at home and work by functioning invisibly in the background, creating a smart environment around them. For example, this could be an intelligent building or a smart traffic control system. Now, since such smart environments need information about their surroundings to function effectively, they rely first and foremost on sensory data from the real world. More accurately, this data is typically provided by wireless sensor networks, which are networks of small, autonomous sensor devices. The advantages of wireless sensor networks, such as flexibility, low cost and ease of deployment, have ensured they have gained significant attention from both researchers and manufacturers. However, due to the limited resource constraints of such sensors (e.g. hardware limitations, low computational capacity, or limited energy budget), there are still a number of significant and specific research challenges to be addressed in this domain. To overcome these challenges, we believe an efficient solution for long–term information collection in wireless sensor network should be able to fulfill the following requirements: (i) adaptivity to environmental changes; (ii) robustness and flexibility; (iii) computational feasibility; and (iv) limited use of communication. In more detail, wireless sensor networks are typically deployed in dynamic environments, we must take environmental changes into account, and thus, it must be able to adapt to those changes. Furthermore, since future changes of the environment are typically unknown a priori, we cannot accurately predict these changes. Thus, in order to efficiently adapt to the environment, a good solution must be on–line, so that it can quickly react to environmental changes. Besides, we must be aware of topological and physical changes (e.g. node or communication failures) as well. Finally, due to the limited resources of the sensors, communication and computational cost should not be significant, compared to the size of the network. Previous work of information collection in wireless sensor networks has typically focused on optimising data sampling, routing, information valuation and energy management in order to achieve efficient information collection. However, it usually fail to provide all of the aforementioned requirements. Specifically, existing solutions are typically not designed for long–term operation, since they cannot adapt to environmental changes. That is, they do not have the ability of modifying their behaviour so that they could efficiently adapt to the new characteristics of the environment. Other algorithms follow the concept of centralised control mechanism (i.e. a central unit is responsible for all the calculations and decision making). These solutions, however, are not robust and flexible, since the central unit may represent a computational bottleneck. Against this background, this transfer report focuses on the challenge of developing decentralised adaptive on–line algorithms for efficient long–term information collection in the wireless sensor network domain. In particular, we focus on developing energy management and information–centric data routing policies that adapt their behaviour according to the energy that is harvested, in order to achieve efficient performance. In so doing, we introduce two new energy management techniques, based on multi–armed bandit learning, that allow each sensor to adaptively allocate its energy budget across the tasks of data sampling, receiving and transmitting. These approaches are devised in order to deal with the following different situations: (i) when the sensors can harvest energy from the environment; and (ii) when energy harvesting from the environment is not possible. By using this approaches, each sensor can learn the optimal energy budget settings that gives it efficient information collection in the long run. In addition, we propose a novel decentralised algorithm for information–centric routing. In more detail, we first tackle the energy management problem with energy–harvesting sensors from the multi–armed bandit perspective. That is, we reduce the energy management problem to a non–stochastic multi–armed bandit model. Then through extensive simulations, we demonstrate that the performance of this approach outperforms other state–of–the–art non–learning algorithms. For the case of energy management with non–harvesting sensors, we show that existing multi–armed bandit models are not suitable for modelling this problem. Given this, we introduce a new bandit model, the budgeted multi–armed bandit with pulling cost, in order to efficiently tackle the energy management problem. Following this, we propose an epsilon–first approach for this new bandit problem, in which the first epsilon portion of the total budget is allocated to exploration (i.e. learning which actions are the most efficient). Finally, for the routing, we introduce an information–centric routing problem, the maximal information throughput routing problem. Existing routing algorithms, however, are not suitable to solve this problem. Thus, we devise a simple, but proveably optimal decentralised algorithm, that maximises the information throughput in the network
Attack strategies and analysis for trust and reputation systems
No full textDataset supports: Gunes, T. D., Tran-Thanh, L., & Norman, T. (2019). Identifying vulnerabilities in trust and reputation systems. Paper presented at International Joint Conference on Artificial Intelligence, Macao, China.
This software package contains the implementation of following components: (1) Implementation of several popular and state-of-the-art trust and reputation systems; (2) two attack search mechanisms that can treat models as a blackbox. (3) a simulation environment for generating populations for benchmarking. The license for the use of this software is based on BSD, and a free commercial license is available; details provided in the source code. Details are provided in the source code. Please see the README.txt file for further information.
File size: 81039403 bytes
SHA256 checksum: 3804b83f1968a157eb4603ec870a3eeb30613d702dc2495b7f077c6a1b6490c0</span
Dataset for "Optimising Resource Management for Embedded Machine Learning"
No full textDataset supports: Xun, L., Tran-Thanh, L., Al-Hashimi, B., & Merrett, G. (2019). Optimising resource management for embedded machine learning. In Design, Automation and Test in Europe Conference 2020 (DATE'20).</span
Dataset for "Incremental Training and Group Convolution Pruning for Runtime DNN Performance Scaling on Heterogeneous Embedded Platforms"
No full textDataset supports: Xun, L., Tran-Thanh, L., Al-Hashimi, B., & Merrett, G. (2019). Incremental Training and Group Convolution Pruning for Runtime DNN Performance Scaling on Heterogeneous Embedded Platforms. In ACM/IEEE Workshop on Machine Learning for CAD 2019 (MLCAD'19).</span
Rhyacobates anderseni Tran & Yang 2006
No full textRhyacobates anderseni Tran & Yang, 2006 Rhyacobates anderseni Tran & Yang, 2006: 14 –16, Figs. 7 –16, 27 (type locality: Vu Quang, Ha Tinh Prov., Vietnam). Material examined. For holotype and paratypes, see Tran & Yang (2006). Size. Males, length 6.0– 6.1 (allotype 6.0), width 1.83–1.85 (allotype 1.83) (apterous), length 6.1–6.2, width 1.85–1.88 (macropterous); females, length 6.8 –7.0 (holotype 6.8), width 2.52–2.57 (holotype 2.52) (apterous). Remarks. The followings are diagnostic characteristics of R. anderseni: the mesonotum of the male has a slender yellow stripe on the posterior half; the mesonotum of the female has a broader yellow median marking on the posterior three-fifths; the abdomen of the male is relatively short; in lateral view, abdominal segment 8 of the male has a concave ventral surface; the male proctiger has round angular projections on each side (see Tran & Yang 2006: Fig. 12); the male paramere is falciform, slightly broad, long, and not conspicuously setose (see Tran & Yang 2006: Figs. 13, 14); the metanotum of the female has a pointed median process on the posterior margin (see Tran & Yang 2006: Fig. 7); the abdomen of the female is short (length about 0.2 times body length), sternum 7 is long, almost enclosing the genital segments with its connexival margin raised slightly upwards, with a pair of long posterior projections pointing outwards and downwards (see Tran & Yang 2006: Figs. 8, 9), and its posterior margin is almost straight, bearing two short lateral processes (see Tran & Yang 2006: Fig. 10). For detailed comparisons of Rhyacobates anderseni with its congeners and other ptilomerine genera (Andersenius and Pleciobates), refer to Tran & Yang (2006: 16). Habitats. See Tran & Yang (2006: 16). Distribution. Vietnam: Ha Tinh. China: Yunnan.Published as part of Tran, A. D. & Nguyen, X. Q., 2016, Three new species of the water strider genus Rhyacobates Esaki, 1923 (Hemiptera: Gerridae) from Vietnam, pp. 501-516 in Zootaxa 4121 (5) on pages 512-513, DOI: 10.11646/zootaxa.4121.5.1, http://zenodo.org/record/27168
Knapsack based optimal policies for budget-limited multi-armed bandits
No full textIn budget-limited multi-armed bandit (MAB) problems, the learner’s actions are costly and constrained by a fixed budget. Consequently, an optimal exploitation policy may not be to pull the optimal arm repeatedly, as is the case in other variants of MAB, but rather to pull the sequence of different arms that maximises the agent’s total reward within the budget. This difference from existing MABs means that new approaches to maximising the total reward are required. Given this, we develop two pulling policies, namely: (i) KUBE; and (ii) fractional KUBE. Whereas the former provides better performance up to 40% in our experimental settings, the latter is computationally less expensive. We also prove logarithmic upper bounds for the regret of both policies, and show that these bounds are asymptotically optimal (i.e. they only differ from the best possible regret by a constant factor)
Xiangqi: User Interaction with Beckhoff PLC Visualization
No full textThe aim of this project is to explore the extends of user interactions with visualization implementation in PLC application. It studies closely from how such visualization will be configured, the backend logic to keep things running and the data flow between the two entities can be organized. This will require a theme that would generate user interactivities, preferably intensive or a focal point of such theme. A Chess game, Chinese chess game or Xiangqi specifically, is henceforth chosen as the main theme for this application. The game by default requires its players to interact with itself by moving its pieces around the chessboard, the pieces’ positions streaming to the backend logic and correctly configuring the layout of the visualization for such interactivities. The experience gained from designing and implementing such application will translate into other industrial-based projects
Rhyacobates gongvo Tran & Yang 2006
No full textRhyacobates gongvo Tran & Yang, 2006 (Figs. 41, 42) Rhyacobates gongvo Tran & Yang, 2006: 16 –19, Figs. 17 –25, 28 (type locality: Sa Pa, Lao Cai Prov., Vietnam). Material examined. For holotype and paratypes, see Tran & Yang (2006). Others: VIETNAM: Lao Cai Prov.: 1 female (apterous), Sa Pa, Nam Sai, Seo Nam Sai stream 1, 22° 15.761 ’N 103 ° 55.909 ’E, 844 m asl., coll. Dinh N.H. et al., 24 October 2012, DNH 12.09 (ZMHU); 1 female (apterous), Sa Pa, Nam Sai, Seo Nam Sai stream 2, 22° 14.67 ’N 103 ° 59.541 ’E, 469 m asl., coll. Dinh N.H. et al., 24 October 2012, DNH 12.10 (ZNHU); 6 males, 5 females (apterous), 2 males (macropterous, de-alated), Sa Pa, Ban Ho, Ban Den, Nam Pu stream (feeder stream of Muong Hoa stream), 22 ° 15.709 ’N 103 ° 58.054 ’E, 416 m asl., coll. Tran A.D. et al., 29 May 2013, TAD 1316 (ZMHU); 1 male, 2 females (apterous), Sa Pa, Thanh Phu, Nam Cang stream, 22 ° 15.401 ’N 103 ° 58.866 ’E, 398 m asl., coll. Tran A.D. et al., 26 October 2013, TAD 1359 (ZMHU); 13 males, 4 females (apterous), Sa Pa, Ban Ho, Nam Pu stream (feeder stream of Muong Hoa stream), site 1, at lower section, 22 ° 15.778 ’N 103 ° 58.270 ’E, 404 m asl., coll. Tran A.D. et al., 26 October 2013, TAD 1361 (ZMHU); 1 female (apterous), Sa Pa, Cat Cat, Ho stream (feeder stream of Muong Hoa stream), 22 ° 19.546 ’N 103 ° 49.880 ’E, 1233 m asl., coll. Tran A.D. et al., 27 October 2013, TAD 1366 (ZMHU). Size. Males, length 6.2–6.5 (allotype 6.5), width 1.88–2.20 (apterous), length 6.4, width 1.97 (macropterous, de-alated); females, length 7.8–8.3 (holotype 8.3), width 2.52–2.67 (holotype 2.52) (apterous), length 7.5, width 2.44 (macropterous, de-alated). Remarks. Rhyacobates gongvo differs from other species of Rhyacobates by the following diagnostic characteristics: in the apterous morph, the mesonotum has a median yellow stripe on the posterior three quarters; the male proctiger has small angular projections on each side (see Tran & Yang 2006: Fig. 22); the male paramere is relatively long and slender, not setose (see Tran & Yang 2006: Figs. 24, 25); the abdomen of the female is elongate and straight (length about 0.4 times body length), the posterior part of sternum 7 is slightly depressed dorsoventrally (see Tran & Yang 2006: Fig. 17); sternum 7 of the female does not totally enclose the genital segments, the posterior margin is straight and without a process, and the connexival projections are long, straight, and flat (see Tran & Yang 2006: Figs. 18–20). Rhyacobates gongvo is relatively similar to R. malaisei Andersen & Chen, 1995, but can be separated from the latter by the diagnosis above (for a comparison between these two species, see Tran & Yang 2006: 18–19). Habitats. See Fig. 40; also see Tran & Yang (2006: 18). Distribution. Vietnam: Lao Cai.Published as part of Tran, A. D. & Nguyen, X. Q., 2016, Three new species of the water strider genus Rhyacobates Esaki, 1923 (Hemiptera: Gerridae) from Vietnam, pp. 501-516 in Zootaxa 4121 (5) on page 513, DOI: 10.11646/zootaxa.4121.5.1, http://zenodo.org/record/27168
- …
