Energy Conservation for Internet of Things Tracking Applications Using Deep Reinforcement Learning

Sultan, Salman Md; Waleed, Muhammad; Pyun, Jae-Young; Um, Tai-Won

doi:10.3390/s21093261

Cited by 16 publications

(4 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3. The LSTM unit is essential for maintaining longterm dependencies, thereby improving overall outcomes [51]. Both the discriminator and the generator employ the rectified linear unit (ReLU) activation function for all layers, except the last one, to disregard the negative weighted values.…”

Section: System Modeling a System Overviewmentioning

confidence: 99%

Augmentation of Fingerprints for Indoor BLE Localization Using Conditional GANs

Junoh,

Pyun

2024

IEEE Access

Self Cite

View full text Add to dashboard Cite

Location estimation in indoor environments using radiofrequency (RF) has garnered considerable attention in recent years owing to the widespread adoption of mobile devices. RF-based fingerprinting-a direct approach that allows location estimation based on observed signals-relies on manual surveys during the offline phase to create a radio map with coordinates and RF measurements at multiple locations. The accuracy of RF fingerprint-based localization is proportional to the number of reference points. However, conventional site survey procedures incur substantial expenses. To alleviate the workload of site surveys and address the challenge of incomplete fingerprint databases, we propose a data-augmentation method to complement existing fingerprint data. Our approach leverages a conditional generative adversarial network with long short-term memory (CGAN-LSTM) prediction model to effectively learn the intricate patterns inherent in the initial training data and generate high-quality synthetic data that align with the underlying data distribution. In an experimental evaluation conducted on a real testbed, our data augmentation framework increased the average localization accuracy by 15.74% compared with fingerprinting without data augmentation. Compared with linear interpolation, inverse distance weighting, and Gaussian process regression, the proposed approach demonstrates an average accuracy improvement ranging from 1.84% to 14.04%, achieving average accuracies of 1.065 and 1.956 m in both scenarios. In experiments conducted in two typical indoor environments using sparse data, the proposed approach substantially reduced localization error and proved comparable to state-of-the-art data-augmentation methods. INDEX TERMSBluetooth low energy (BLE), fingerprint, data augmentation, generative adversarial network (GAN), location estimation. SUHARDI AZLIY JUNOH (Graduate Student Member, IEEE) received the B.Eng. degree in electronics (telecommunications) from Multimedia University, Malaysia, and the master's degree in electrical engineering from Universiti Tun Hussein Onn Malaysia (UTHM), Malaysia. He is currently pursuing the Ph.D. degree in information and communication engineering with Chosun University, South Korea. He was with Infineon Technologies as an Engineer. His current research interests include indoor positioning and navigation, the Internet of Things, mobile computing, and wireless communication systems. JAE-YOUNG PYUN (Member, IEEE) received the B.S. and M.

show abstract

Section: System Modeling a System Overviewmentioning

confidence: 99%

Augmentation of Fingerprints for Indoor BLE Localization Using Conditional GANs

Junoh,

Pyun

2024

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the proposed DUPT, we used a binary reward strategy [22] to evaluate the performance of the DQN-based UAV agent. The main reason for using binary reward is that it is simple to estimate without any computational complexity.…”

Section: Reward Spacementioning

confidence: 99%

Powering UAV with Deep Q-Network for Air Quality Tracking

Mohammed

Sultan²,

Cho³

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

Tracking the source of air pollution plumes and monitoring the air quality during emergency events in real-time is crucial to support decision-makers in making an appropriate evacuation plan. Internet of Things (IoT) based air quality tracking and monitoring platforms have used stationary sensors around the environment. However, fixed IoT sensors may not be enough to monitor the air quality in a vast area during emergency situations. Therefore, many applications consider utilizing Unmanned Aerial Vehicles (UAVs) to monitor the air pollution plumes environment. However, finding an unhealthy location in a vast area requires a long navigation time. For time efficiency, we employ deep reinforcement learning (Deep RL) to assist UAVs to find air pollution plumes in an equal-sized grid space. The proposed Deep Q-network (DQN) based UAV Pollution Tracking (DUPT) is utilized to guide the multi-navigation direction of the UAV to find the pollution plumes’ location in a vast area within a short duration of time. Indeed, we deployed a long short-term memory (LSTM) combined with Q-network to suggest a particular navigation pattern producing minimal time consumption. The proposed DUPT is evaluated and validated using an air pollution environment generated by a well-known Gaussian distribution and kriging interpolation. The evaluation and comparison results are carefully presented and analyzed. The experiment results show that our proposed DUPT solution can rapidly identify the unhealthy polluted area and spends around 28% of the total time of the existing solution.

show abstract

“…But the easiest scheme to do is harvesting like Solar because energy sources can be taken from anywhere and the most difficult is to save energy using transfer. Review Network Energy conservation Optimization techniques [43] Sensor Energy conservation Best sensor selection [44] Ambient electric field Energy harvesting Self-configuring [45] Solar Energy harvesting WSN lifetime [46] Solar Energy harvesting Utilize MPPT [10] Solar Energy harvesting Charging solar and wireless [11] Energy-aware Energy harvesting Help Lorawan transmit data [47] Wind Energy harvesting Changing wind direction [48] Thermal Energy harvesting Enhance efficiency [50] Power loss shifted Energy transfer Design inductive Energy Transfer [49] Data transmission Energy transfer Transmission contactless [51] Time scheduling and transmission Energy harvesting Effectiveness [52] Electrical devices Energy harvesting Maximizing MPPT…”

Section: Schemes Energy Savingsmentioning

confidence: 99%

Energy saving on IoT using LoRa: a systematic literature review

Widianto

Ramadhan

Trisetyarso

et al. 2022

IJRES

View full text Add to dashboard Cite

<span lang="EN-US">The development of devices connected to the internet is very significant, encouraging the creation of the internet of things (IoT). With remote systems, IoT is not enough to use in case of internet instability. By using long range (LoRa), IoT systems can now solve this problem. Millions of data make IoT-LoRa have to spend a lot of energy. This paper helps discover where recent studies offer a broad perspective on energy savings using the systematic literature review (SLR). The paper extracted 252 articles from IEEE, ACM, MDPI, Springer, Hindawi, ScienceDirect, and IAES. 44 articles passed the specified inclusion and exclusion criteria. The article focuses on knowledge about IoT-Lora, energy saving needs, energy saving factors, and the paper demographics. The author synthesizes studies for that purpose on IoT applications using LoRa.</span>

show abstract

Energy Conservation for Internet of Things Tracking Applications Using Deep Reinforcement Learning

Cited by 16 publications

References 46 publications

Augmentation of Fingerprints for Indoor BLE Localization Using Conditional GANs

Augmentation of Fingerprints for Indoor BLE Localization Using Conditional GANs

Powering UAV with Deep Q-Network for Air Quality Tracking

Energy saving on IoT using LoRa: a systematic literature review

Contact Info

Product

Resources

About