Search

Your search keyword '"Hou, Ming"' showing total 6,242 results
Start Over Author "Hou, Ming"
6,242 results on '"Hou, Ming"'

1. A unified uncertainty-aware exploration: Combining epistemic and aleatory uncertainty

Author

Malekzadeh, Parvin, Hou, Ming, and Plataniotis, Konstantinos N.

Subjects
Computer Science - Machine Learning
Abstract

Exploration is a significant challenge in practical reinforcement learning (RL), and uncertainty-aware exploration that incorporates the quantification of epistemic and aleatory uncertainty has been recognized as an effective exploration strategy. However, capturing the combined effect of aleatory and epistemic uncertainty for decision-making is difficult. Existing works estimate aleatory and epistemic uncertainty separately and consider the composite uncertainty as an additive combination of the two. Nevertheless, the additive formulation leads to excessive risk-taking behavior, causing instability. In this paper, we propose an algorithm that clarifies the theoretical connection between aleatory and epistemic uncertainty, unifies aleatory and epistemic uncertainty estimation, and quantifies the combined effect of both uncertainties for a risk-sensitive exploration. Our method builds on a novel extension of distributional RL that estimates a parameterized return distribution whose parameters are random variables encoding epistemic uncertainty. Experimental results on tasks with exploration and risk challenges show that our method outperforms alternative approaches., Comment: Accepted by ICASSP2023

Published
2024
Full Text
View/download PDF

2. Switching from eltrombopag to hetrombopag in patients with primary immune thrombocytopenia: a post-hoc analysis of a multicenter, randomized phase III trial

Author

Mei, Heng, Liu, Xiaofan, Li, Yan, Zhou, Hu, Feng, Ying, Gao, Guangxun, Cheng, Peng, Huang, Ruibin, Yang, Linhua, Hu, Jianda, Hou, Ming, Yao, Yazhou, Liu, Li, Wang, Yi, Wu, Depei, Shen, Xuliang, Jin, Jie, Luo, Jianmin, Zeng, Yun, Zhou, Xin, Xia, Ruixiang, Jiang, Zhongxing, Bai, Yuansong, Niu, Ting, Yang, Renchi, and Hu, Yu

Published
2024
Full Text
View/download PDF

8. Uncertainty-aware transfer across tasks using hybrid model-based successor feature reinforcement learning

Author

Malekzadeh, Parvin, Hou, Ming, and Plataniotis, Konstantinos N.

Subjects
Computer Science - Machine Learning, Electrical Engineering and Systems Science - Signal Processing
Abstract

Sample efficiency is central to developing practical reinforcement learning (RL) for complex and large-scale decision-making problems. The ability to transfer and generalize knowledge gained from previous experiences to downstream tasks can significantly improve sample efficiency. Recent research indicates that successor feature (SF) RL algorithms enable knowledge generalization between tasks with different rewards but identical transition dynamics. It has recently been hypothesized that combining model-based (MB) methods with SF algorithms can alleviate the limitation of fixed transition dynamics. Furthermore, uncertainty-aware exploration is widely recognized as another appealing approach for improving sample efficiency. Putting together two ideas of hybrid model-based successor feature (MB-SF) and uncertainty leads to an approach to the problem of sample efficient uncertainty-aware knowledge transfer across tasks with different transition dynamics or/and reward functions. In this paper, the uncertainty of the value of each action is approximated by a Kalman filter (KF)-based multiple-model adaptive estimation. This KF-based framework treats the parameters of a model as random variables. To the best of our knowledge, this is the first attempt at formulating a hybrid MB-SF algorithm capable of generalizing knowledge across large or continuous state space tasks with various transition dynamics while requiring less computation at decision time than MB methods. The number of samples required to learn the tasks was compared to recent SF and MB baselines. The results show that our algorithm generalizes its knowledge across different transition dynamics, learns downstream tasks with significantly fewer samples than starting from scratch, and outperforms existing approaches., Comment: 40 pages

Published
2023
Full Text
View/download PDF

12. Efficacy and safety of generic pomalidomide plus low-dose dexamethasone in relapsed or refractory multiple myeloma: a multicenter, open-label, single-arm trial

Author

Zhou, Huixing, Wang, Yafei, Chen, Jiao, He, Aili, Jin, Jie, Lu, Quanyi, Zhao, Ying, Li, Junjun, Hou, Ming, Su, Liping, Lai, Xun, Wang, Wei, Liu, Lihong, Ma, Yanping, Gao, Da, Lai, Wenhong, Zhou, Xin, Jing, Hongmei, Zhang, Jinqiao, Yang, Wei, Ran, Xuehong, Lin, Congmeng, Hao, Jianping, Xiao, Taiwu, Huang, Zhenqian, Zhu, Zhigang, Wang, Qing, Fang, Baijun, Wang, Binghua, Song, Yanping, Cai, Zhen, Liu, Bo, Zhu, Yanan, Yang, Xinai, Kang, Xiaoyan, Li, Juan, and Chen, Wenming

Published
2024
Full Text
View/download PDF

14. ViT-CAT: Parallel Vision Transformers with Cross Attention Fusion for Popularity Prediction in MEC Networks

Author

HajiAkhondi-Meybodi, Zohreh, Mohammadi, Arash, Hou, Ming, Abouei, Jamshid, and Plataniotis, Konstantinos N.

Subjects
Computer Science - Machine Learning, Computer Science - Networking and Internet Architecture, Electrical Engineering and Systems Science - Signal Processing
Abstract

Mobile Edge Caching (MEC) is a revolutionary technology for the Sixth Generation (6G) of wireless networks with the promise to significantly reduce users' latency via offering storage capacities at the edge of the network. The efficiency of the MEC network, however, critically depends on its ability to dynamically predict/update the storage of caching nodes with the top-K popular contents. Conventional statistical caching schemes are not robust to the time-variant nature of the underlying pattern of content requests, resulting in a surge of interest in using Deep Neural Networks (DNNs) for time-series popularity prediction in MEC networks. However, existing DNN models within the context of MEC fail to simultaneously capture both temporal correlations of historical request patterns and the dependencies between multiple contents. This necessitates an urgent quest to develop and design a new and innovative popularity prediction architecture to tackle this critical challenge. The paper addresses this gap by proposing a novel hybrid caching framework based on the attention mechanism. Referred to as the parallel Vision Transformers with Cross Attention (ViT-CAT) Fusion, the proposed architecture consists of two parallel ViT networks, one for collecting temporal correlation, and the other for capturing dependencies between different contents. Followed by a Cross Attention (CA) module as the Fusion Center (FC), the proposed ViT-CAT is capable of learning the mutual information between temporal and spatial correlations, as well, resulting in improving the classification accuracy, and decreasing the model's complexity about 8 times. Based on the simulation results, the proposed ViT-CAT architecture outperforms its counterparts across the classification accuracy, complexity, and cache-hit ratio.

Published
2022

15. Multi-Content Time-Series Popularity Prediction with Multiple-Model Transformers in MEC Networks

Author

HajiAkhondi-Meybodi, Zohreh, Mohammadi, Arash, Hou, Ming, Rahimian, Elahe, Heidarian, Shahin, Abouei, Jamshid, and Plataniotis, Konstantinos N.

Subjects
Computer Science - Machine Learning, Computer Science - Networking and Internet Architecture, Electrical Engineering and Systems Science - Signal Processing
Abstract

Coded/uncoded content placement in Mobile Edge Caching (MEC) has evolved as an efficient solution to meet the significant growth of global mobile data traffic by boosting the content diversity in the storage of caching nodes. To meet the dynamic nature of the historical request pattern of multimedia contents, the main focus of recent researches has been shifted to develop data-driven and real-time caching schemes. In this regard and with the assumption that users' preferences remain unchanged over a short horizon, the Top-K popular contents are identified as the output of the learning model. Most existing datadriven popularity prediction models, however, are not suitable for the coded/uncoded content placement frameworks. On the one hand, in coded/uncoded content placement, in addition to classifying contents into two groups, i.e., popular and nonpopular, the probability of content request is required to identify which content should be stored partially/completely, where this information is not provided by existing data-driven popularity prediction models. On the other hand, the assumption that users' preferences remain unchanged over a short horizon only works for content with a smooth request pattern. To tackle these challenges, we develop a Multiple-model (hybrid) Transformer-based Edge Caching (MTEC) framework with higher generalization ability, suitable for various types of content with different time-varying behavior, that can be adapted with coded/uncoded content placement frameworks. Simulation results corroborate the effectiveness of the proposed MTEC caching framework in comparison to its counterparts in terms of the cache-hit ratio, classification accuracy, and the transferred byte volume.

Published
2022

16. JUNO: Jump-Start Reinforcement Learning-based Node Selection for UWB Indoor Localization

Author

Hajiakhondi-Meybodi, Zohreh, Hou, Ming, and Mohammadi, Arash

Subjects
Electrical Engineering and Systems Science - Signal Processing, Computer Science - Machine Learning
Abstract

Ultra-Wideband (UWB) is one of the key technologies empowering the Internet of Thing (IoT) concept to perform reliable, energy-efficient, and highly accurate monitoring, screening, and localization in indoor environments. Performance of UWB-based localization systems, however, can significantly degrade because of Non Line of Sight (NLoS) connections between a mobile user and UWB beacons. To mitigate the destructive effects of NLoS connections, we target development of a Reinforcement Learning (RL) anchor selection framework that can efficiently cope with the dynamic nature of indoor environments. Existing RL models in this context, however, lack the ability to generalize well to be used in a new setting. Moreover, it takes a long time for the conventional RL models to reach the optimal policy. To tackle these challenges, we propose the Jump-start RL-based Uwb NOde selection (JUNO) framework, which performs real-time location predictions without relying on complex NLoS identification/mitigation methods. The effectiveness of the proposed JUNO framework is evaluated in term of the location error, where the mobile user moves randomly through an ultra-dense indoor environment with a high chance of establishing NLoS connections. Simulation results corroborate the effectiveness of the proposed framework in comparison to its state-of-the-art counterparts.

Published
2022

19. AKF-SR: Adaptive Kalman Filtering-based Successor Representation

Author

Malekzadeh, Parvin, Salimibeni, Mohammad, Hou, Ming, Mohammadi, Arash, and Plataniotis, Konstantinos N.

Subjects
Computer Science - Neural and Evolutionary Computing, Computer Science - Artificial Intelligence, Computer Science - Machine Learning
Abstract

Recent studies in neuroscience suggest that Successor Representation (SR)-based models provide adaptation to changes in the goal locations or reward function faster than model-free algorithms, together with lower computational cost compared to that of model-based algorithms. However, it is not known how such representation might help animals to manage uncertainty in their decision-making. Existing methods for SR learning do not capture uncertainty about the estimated SR. In order to address this issue, the paper presents a Kalman filter-based SR framework, referred to as Adaptive Kalman Filtering-based Successor Representation (AKF-SR). First, Kalman temporal difference approach, which is a combination of the Kalman filter and the temporal difference method, is used within the AKF-SR framework to cast the SR learning procedure into a filtering problem to benefit from the uncertainty estimation of the SR, and also decreases in memory requirement and sensitivity to model's parameters in comparison to deep neural network-based algorithms. An adaptive Kalman filtering approach is then applied within the proposed AKF-SR framework in order to tune the measurement noise covariance and measurement mapping function of Kalman filter as the most important parameters affecting the filter's performance. Moreover, an active learning method that exploits the estimated uncertainty of the SR to form the behaviour policy leading to more visits to less certain values is proposed to improve the overall performance of an agent in terms of received rewards while interacting with its environment.

Published
2022
Full Text
View/download PDF

20. Incorporating progesterone receptor expression into the PREDICT breast prognostic model

Author

Grootes, Isabelle, Keeman, Renske, Blows, Fiona M, Milne, Roger L, Giles, Graham G, Swerdlow, Anthony J, Fasching, Peter A, Abubakar, Mustapha, Andrulis, Irene L, Anton-Culver, Hoda, Beckmann, Matthias W, Blomqvist, Carl, Bojesen, Stig E, Bolla, Manjeet K, Bonanni, Bernardo, Briceno, Ignacio, Burwinkel, Barbara, Camp, Nicola J, Castelao, Jose E, Choi, Ji-Yeob, Clarke, Christine L, Couch, Fergus J, Cox, Angela, Cross, Simon S, Czene, Kamila, Devilee, Peter, Dörk, Thilo, Dunning, Alison M, Dwek, Miriam, Easton, Douglas F, Eccles, Diana M, Eriksson, Mikael, Ernst, Kristina, Evans, D Gareth, Figueroa, Jonine D, Fink, Visnja, Floris, Giuseppe, Fox, Stephen, Gabrielson, Marike, Gago-Dominguez, Manuela, García-Sáenz, José A, González-Neira, Anna, Haeberle, Lothar, Haiman, Christopher A, Hall, Per, Hamann, Ute, Harkness, Elaine F, Hartman, Mikael, Hein, Alexander, Hooning, Maartje J, Hou, Ming-Feng, Howell, Sacha J, Investigators, ABCTB, Investigators, kConFab, Ito, Hidemi, Jakubowska, Anna, Janni, Wolfgang, John, Esther M, Jung, Audrey, Kang, Daehee, Kristensen, Vessela N, Kwong, Ava, Lambrechts, Diether, Li, Jingmei, Lubiński, Jan, Manoochehri, Mehdi, Margolin, Sara, Matsuo, Keitaro, Taib, Nur Aishah Mohd, Mulligan, Anna Marie, Nevanlinna, Heli, Newman, William G, Offit, Kenneth, Osorio, Ana, Park, Sue K, Park-Simon, Tjoung-Won, Patel, Alpa V, Presneau, Nadege, Pylkäs, Katri, Rack, Brigitte, Radice, Paolo, Rennert, Gad, Romero, Atocha, Saloustros, Emmanouil, Sawyer, Elinor J, Schneeweiss, Andreas, Schochter, Fabienne, Schoemaker, Minouk J, Shen, Chen-Yang, Shibli, Rana, Sinn, Peter, Tapper, William J, Tawfiq, Essa, Teo, Soo Hwang, Teras, Lauren R, Torres, Diana, Vachon, Celine M, van Deurzen, Carolien HM, Wendt, Camilla, and Williams, Justin A

Subjects
Cancer, Breast Cancer, Breast Neoplasms, Female, Humans, Progesterone, Prognosis, Receptor, ErbB-2, Receptors, Progesterone, PREDICT Breast, breast cancer, Progesterone receptor, ABCTB Investigators, kConFab Investigators, Receptor, erbB-2, Oncology and Carcinogenesis, Public Health and Health Services, Oncology & Carcinogenesis
Abstract

BackgroundPredict Breast (www.predict.nhs.uk) is an online prognostication and treatment benefit tool for early invasive breast cancer. The aim of this study was to incorporate the prognostic effect of progesterone receptor (PR) status into a new version of PREDICT and to compare its performance to the current version (2.2).MethodThe prognostic effect of PR status was based on the analysis of data from 45,088 European patients with breast cancer from 49 studies in the Breast Cancer Association Consortium. Cox proportional hazard models were used to estimate the hazard ratio for PR status. Data from a New Zealand study of 11,365 patients with early invasive breast cancer were used for external validation. Model calibration and discrimination were used to test the model performance.ResultsHaving a PR-positive tumour was associated with a 23% and 28% lower risk of dying from breast cancer for women with oestrogen receptor (ER)-negative and ER-positive breast cancer, respectively. The area under the ROC curve increased with the addition of PR status from 0.807 to 0.809 for patients with ER-negative tumours (p = 0.023) and from 0.898 to 0.902 for patients with ER-positive tumours (p = 2.3 × 10-6) in the New Zealand cohort. Model calibration was modest with 940 observed deaths compared to 1151 predicted.ConclusionThe inclusion of the prognostic effect of PR status to PREDICT Breast has led to an improvement of model performance and more accurate absolute treatment benefit predictions for individual patients. Further studies should determine whether the baseline hazard function requires recalibration.

Published
2022

23. Aponermin or placebo in combination with thalidomide and dexamethasone in the treatment of relapsed or refractory multiple myeloma (CPT-MM301): a randomised, double-blinded, placebo-controlled, phase 3 trial

Author

Xia, Zhongjun, Leng, Yun, Fang, Baijun, Liang, Yang, Li, Wei, Fu, Chengcheng, Yang, Linhua, Ke, Xiaoyan, Jiang, Hua, Weng, Jianyu, Liu, Li, Zhao, Yaozhong, Zhang, Xuejun, Huang, Zhongxia, Liu, Aichun, Shi, Qingzhi, Gao, Yuhuan, Chen, Xiequn, Pan, Ling, Cai, Zhen, Wang, Zhao, Wang, Yafei, Fan, Yaqun, Hou, Ming, Ma, Yigai, Hu, Jianda, Liu, Jing, Zhou, Jianfeng, Zhang, Xiaohong, Meng, Haitao, Lu, Xuzhang, Li, Fei, Ren, Hanyun, Huang, Bintao, Shao, Zonghong, Zhou, Hebing, Hu, Yu, Yang, Shifang, Zheng, Xiangjun, Wei, Peng, Pang, Hongyan, Yu, Wei, Liu, Yuzhang, Gao, Sujun, Yan, Lingzhi, Ma, Yanping, Jing, Hongmei, Du, Juan, Ling, Wei, Zhang, Jingyi, Sui, Weiwei, Wang, Fuxu, Li, Xin, and Chen, Wenming

Published
2023
Full Text
View/download PDF

30. Feasibility and Accessibility of Human-Centered AI-Based Simulation System for Improving the Occupational Safety of Clinical Workplace

Author

Wang, Pin-Hsuan, Huang, Anna YuQing, Huang, Yen-Hsun, Yang, Ying-Ying, Lirng, JiingFeng, Li, Tzu-Hao, Hou, Ming-Chih, Chen, Chen-Huan, Yang, Albert ChihChieh, Lin, Chi-Hung, and Sheu, Wayne Huey-Herng

Abstract

Medical personnel need to learn occupational safety knowledge in clinical workplaces, not only to ensure their own safety, but also to further ensure patients safety. Based on Human-centered artificial intelligence (HAI) technology, this study will provide HAI-based occupational safety training system for two training topics, Needle Stick/Sharps Injury (NSSI) prevention and appropriate Clinical Waste Management (CWM). From April 2018 to December 2021, this clinical occupational safety HAI training is used by 342 medical personnel (doctors and non-doctors). This study aims to investigate the learning performance and effectiveness including decreasing anxiety and increasing mastering level of users. This study shows that, for the first-time and feel-friendly users of this HAI training system, not only can they achieve significant learning improvement, but they can also effectively decrease their anxiety and increase their mastery level of clinical work safety knowledge and skill. In terms of learning performance and effectiveness, this study found that doctors are significantly benefited by the HAI training system in contrast to non-doctors.

Published
2023

38. Four-year overall survival update from the phase III HIMALAYA study of tremelimumab plus durvalumab in unresectable hepatocellular carcinoma

Author

Azevedo, Sergio, Braghiroli, Maria Ignez, Girotto, Gustavo, Bragagnoli, Arinilda, Branco, Ricardo, Faccio, Adilson, Moretto, Andrea, Skare, Nils, Dutra, Jamille, Viola, Luciana, Vianna, Karina, Meton, Fernando, Sette, Claudia, Faulhaber, Amanda, Tam, Vincent C., Couture, Felix, Biagi, Jim, Castel, Helene, Mulder, Karen, Ko, Yoo-Joung, Zbuk, Kevin, Welch, Stephen, Beaudoin, Annie, Heurgué, Alexandra, Assenat, Eric, Archambeaud, Isabelle, Tougeron, David, Peron, Jean-Marie, Gilabert, Marine, Bronowicki, Jean-Pierre, Cattan, Stephane, Blanc, Jean-Frederic, Bouattour, Mohamed, Phelip, Jean-Marc, Boige, Valerie, Michel, Pierre, Frin, Anne-Claire, De Toni, Enrico N., Berres, Marie-Luise, Vogel, Arndt, Berg, Thomas, Ettrich, Thomas, Waldschmidt, Dirk, Wedemeyer, Hans Heinrich, Worns, Marcus-Alexander, Bitzer, Michael, Weiss, Karl-Heinz, Lau, George, Chan, Stephen L., Yau, Thomas, Tai, Yin Ping, Lee, Ann Shing, Thungappa, Satheesh Chiradoni, N, Lokesh K., Sureshchand Ostwal, Vikas, Ashok, Kattimani Kiran, Mittal, Sushant, Goyal, Hari, Srinivasan, Sankar, Biswas, Ghanashyam, Mohan, Mallavarapu, Limaye, Sewanti, Asarawala, Nirav, Rimassa, Lorenza, Falcone, Alfredo, Gianni, Luca, Gasbarrini, Antonio, Daniele, Bruno, Avallone, Antonio, Paolo Frassineti, Giovanni Luca, Roila, Fausto, Kudo, Masatoshi, Kawaoka, Tomokazu, Morimoto, Manabu, Takikawa, Yasuhiro, Kato, Naoya, Yamashita, Tatsuya, Osaki, Yukio, Motomura, Kenta, Tateishi, Ryosuke, Ohkawa, Kazuyoshi, Wada, Yoshiyuki, Onishi, Hideki, Sasahira, Naoki, Inaba, Yoshitaka, Kurosaki, Masayuki, Tsuji, Kunihiko, Takei, Yoshiyuki, Aramaki, Takeshi, Hagihara, Atsushi, Furuse, Junji, Kioka, Kiyohide, Koga, Hironori, Sasaki, Yutaka, Numata, Kazushi, Tada, Toshifumi, Kawaguchi, Yasunori, Nadano, Seijin, Vasilyev, Alexander, Breder, Valery, Lipatov, Oleg, Dvorkin, Mikhail, Zarubenkov, Oleg, Kutukova, Svetlana, Ponomarev, Roman, Shostka, Kirill, Alyasova, Anna, Topuzov, Eldar, Severtsev, Alexey, Petrov, Yuryi, Erygin, Dmitriy, Berdov, Boris, Kang, Yoon-Koo, Tak, Won-Young, Park, Joong-Won, Lim, Ho Yeong, Heo, Jeong, Kim, Jee Hyun, Kim, Tae-You, Choi, Hye Jin, Varela, María, Reig Monzon, María Elisa, Sangro, Bruno, Martin, Carlos Gómez, Ponce, Carmen Guillén, López, Carlos, Cheng, Ann-Lii, Chao, Yee, Feng, Yin-Hsun, Jeng, Long-Bin, Hung, Chao-Hung, Hou, Ming-Mo, Wang Tsang-En Wang, Jing-Houng, Yen, Chia-Jui, Sukeepaisarnjaroen, Wattana, Sunpaweravong, Patrapim, Charoentum, Chaiyut, Tanasanvimon, Suebpong, Sirachainan, Ekaphop, Ungtrakul, Teerapat, Prasongsook, Naiyarat, Maneenil, Kunlatida, Jitpewngarm, Wittawat, Ostapenko, Yurii, Skoryi, Denys, Bondarenko, Igor, Shparyk, Yaroslav, Trukhin, Dmytro, Hotko, Yevhen, Ursol, Grygorii, Kryzhanivska, Anna, Abou-Alfa, Ghassan K., Mody, Kabir, Dayyani, Farshid, Al-Rajabi, Raed, Yarchoan, Mark, Gandhi, Sunil, Crysler, Oxana, He, Aiwu Ruth, Reeves, James, Bahary, Nathan, Mahipal, Amit, Kelley, Robin Kate, Dasgupta, Anirudha, Rowe, Julie, Thota, Ramya, Beg, Muhammad, Morse, Michael, Choi, Sung-hee, Crocenzi, Todd, Somer, Bradley, Abrams, Thomas, Denlinger, Crystal, Zhang, Yue, Sharma, Nisha, Dao, Tu V., Thinh, Nguyen Tien, Tuyet Phuong, Le Thi, Sangro, B., Chan, S.L., Kelley, R.K., Lau, G., Kudo, M., Sukeepaisarnjaroen, W., Yarchoan, M., De Toni, E.N., Furuse, J., Kang, Y.K., Galle, P.R., Rimassa, L., Heurgué, A., Tam, V.C., Van Dao, T., Thungappa, S.C., Breder, V., Ostapenko, Y., Reig, M., Makowsky, M., Paskow, M.J., Gupta, C., Kurland, J.F., Negro, A., and Abou-Alfa, G.K.

Published
2024
Full Text
View/download PDF

43. DQLEL: Deep Q-Learning for Energy-Optimized LoS/NLoS UWB Node Selection

Author

Hajiakhondi-Meybodi, Zohreh, Mohammadi, Arash, Hou, Ming, and Plataniotis, Konstantinos N.

Subjects
Computer Science - Networking and Internet Architecture, Computer Science - Machine Learning, Electrical Engineering and Systems Science - Signal Processing
Abstract

Recent advancements in Internet of Things (IoTs) have brought about a surge of interest in indoor positioning for the purpose of providing reliable, accurate, and energy-efficient indoor navigation/localization systems. Ultra Wide Band (UWB) technology has been emerged as a potential candidate to satisfy the aforementioned requirements. Although UWB technology can enhance the accuracy of indoor positioning due to the use of a wide-frequency spectrum, there are key challenges ahead for its efficient implementation. On the one hand, achieving high precision in positioning relies on the identification/mitigation Non Line of Sight (NLoS) links, leading to a significant increase in the complexity of the localization framework. On the other hand, UWB beacons have a limited battery life, which is especially problematic in practical circumstances with certain beacons located in strategic positions. To address these challenges, we introduce an efficient node selection framework to enhance the location accuracy without using complex NLoS mitigation methods, while maintaining a balance between the remaining battery life of UWB beacons. Referred to as the Deep Q-Learning Energy-optimized LoS/NLoS (DQLEL) UWB node selection framework, the mobile user is autonomously trained to determine the optimal set of UWB beacons to be localized based on the 2-D Time Difference of Arrival (TDoA) framework. The effectiveness of the proposed DQLEL framework is evaluated in terms of the link condition, the deviation of the remaining battery life of UWB beacons, location error, and cumulative rewards. Based on the simulation results, the proposed DQLEL framework significantly outperformed its counterparts across the aforementioned aspects.

Published
2021
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results