Sensors

Research

16 pages, 753 KiB

Open AccessArticle

Natural-Language-Driven Multimodal Representation Learning for Audio-Visual Scene-Aware Dialog System

by Yoonseok Heo, Sangwoo Kang and Jungyun Seo

Sensors 2023, 23(18), 7875; https://doi.org/10.3390/s23187875 - 14 Sep 2023

Cited by 1 | Viewed by 1217

With the development of multimedia systems in wireless environments, the rising need for artificial intelligence is to design a system that can properly communicate with humans with a comprehensive understanding of various types of information in a human-like manner. Therefore, this paper addresses [...] Read more.

With the development of multimedia systems in wireless environments, the rising need for artificial intelligence is to design a system that can properly communicate with humans with a comprehensive understanding of various types of information in a human-like manner. Therefore, this paper addresses an audio-visual scene-aware dialog system that can communicate with users about audio-visual scenes. It is essential to understand not only visual and textual information but also audio information in a comprehensive way. Despite the substantial progress in multimodal representation learning with language and visual modalities, there are still two caveats: ineffective use of auditory information and the lack of interpretability of the deep learning systems’ reasoning. To address these issues, we propose a novel audio-visual scene-aware dialog system that utilizes a set of explicit information from each modality as a form of natural language, which can be fused into a language model in a natural way. It leverages a transformer-based decoder to generate a coherent and correct response based on multimodal knowledge in a multitask learning setting. In addition, we also address the way of interpreting the model with a response-driven temporal moment localization method to verify how the system generates the response. The system itself provides the user with the evidence referred to in the system response process as a form of the timestamp of the scene. We show the superiority of the proposed model in all quantitative and qualitative measurements compared to the baseline. In particular, the proposed model achieved robust performance even in environments using all three modalities, including audio. We also conducted extensive experiments to investigate the proposed model. In addition, we obtained state-of-the-art performance in the system response reasoning task. Full article

(This article belongs to the Special Issue Next-Generation Wireless Systems for the Internet of Things (IoT))

► Show Figures

Figure 1

17 pages, 1781 KiB

Open AccessArticle

Interference Aware Resource Control for 6G-Enabled Expanded IoT Networks

by Ashu Taneja, Nayef Alqahtani and Ali Alqahtani

Sensors 2023, 23(12), 5649; https://doi.org/10.3390/s23125649 - 16 Jun 2023

Cited by 3 | Viewed by 1200

Abstract

Emerging consumer devices rely on the next generation IoT for connected support to undergo the much-needed digital transformation. The main challenge for next-generation IoT is to fulfil the requirements of robust connectivity, uniform coverage and scalability to reap the benefits of automation, integration [...] Read more.

Emerging consumer devices rely on the next generation IoT for connected support to undergo the much-needed digital transformation. The main challenge for next-generation IoT is to fulfil the requirements of robust connectivity, uniform coverage and scalability to reap the benefits of automation, integration and personalization. Next generation mobile networks, including beyond 5G and 6G technology, play an important role in delivering intelligent coordination and functionality among the consumer nodes. This paper presents a 6G-enabled scalable cell-free IoT network that guarantees uniform quality-of-service (QoS) to the proliferating wireless nodes or consumer devices. By enabling the optimal association of nodes with the APs, it offers efficient resource management. A scheduling algorithm is proposed for the cell-free model such that the interference caused by the neighbouring nodes and neighbouring APs is minimised. The mathematical formulations are obtained to carry out the performance analysis with different precoding schemes. Further, the allocation of pilots for obtaining the association with minimum interference is managed using different pilot lengths. It is observed that the proposed algorithm offers an improvement of 18.9% in achieved spectral efficiency using partial regularized zero-forcing (PRZF) precoding scheme at pilot length

τ_{p} = 10

. In the end, the performance comparison with two other models incorporating random scheduling and no scheduling at all is carried out. As compared to random scheduling, the proposed scheduling shows improvement of 10.9% in obtained spectral efficiency by 95% of the user nodes. Full article

(This article belongs to the Special Issue Next-Generation Wireless Systems for the Internet of Things (IoT))

► Show Figures

Figure 1

14 pages, 901 KiB

Open AccessCommunication

Lightweight LSTM-Based Adaptive CQI Feedback Scheme for IoT Devices

by Noel Han, Il-Min Kim and Jaewoo So

Sensors 2023, 23(10), 4929; https://doi.org/10.3390/s23104929 - 20 May 2023

Cited by 4 | Viewed by 1718

Abstract

As the number of Internet of things (IoT) devices increases exponentially, scheduling and managing the radio resources for IoT devices has become more important. To efficiently allocate radio resources, the base station (BS) needs the channel state information (CSI) of devices every time. [...] Read more.

As the number of Internet of things (IoT) devices increases exponentially, scheduling and managing the radio resources for IoT devices has become more important. To efficiently allocate radio resources, the base station (BS) needs the channel state information (CSI) of devices every time. Hence, each device needs to periodically (or aperiodically) report its channel quality indicator (CQI) to the BS. The BS determines the modulation and coding scheme (MCS) based on the CQI reported by the IoT device. However, the more a device reports its CQI, the more the feedback overhead increases. In this paper, we propose a long short-term memory (LSTM)-based CQI feedback scheme, where the IoT device aperiodically reports its CQI relying on an LSTM-based channel prediction. Additionally, because the memory capacity of IoT devices is generally small, the complexity of the machine learning model must be reduced. Hence, we propose a lightweight LSTM model to reduce the complexity. The simulation results show that the proposed lightweight LSTM-based CSI scheme dramatically reduces the feedback overhead compared with that of the existing periodic feedback scheme. Moreover, the proposed lightweight LSTM model significantly reduces the complexity without sacrificing performance. Full article

(This article belongs to the Special Issue Next-Generation Wireless Systems for the Internet of Things (IoT))

► Show Figures

Figure 1

18 pages, 5953 KiB

Open AccessArticle

Design of Meat Product Safety Information Chain Traceability System Based on UHF RFID

by Jiping Qiao, Minghui Hao and Meicen Guo

Sensors 2023, 23(7), 3372; https://doi.org/10.3390/s23073372 - 23 Mar 2023

Cited by 6 | Viewed by 2139

Abstract

As a result of the current imperfection of the meat traceability system, there have been numerous food safety events with serious consequences. In this paper, a meat product information traceability system is designed to efficiently prevent such problems. This system develops an identification [...] Read more.

As a result of the current imperfection of the meat traceability system, there have been numerous food safety events with serious consequences. In this paper, a meat product information traceability system is designed to efficiently prevent such problems. This system develops an identification tag information reader based on ultra-high frequency (UHF) Radio Frequency Identification (RFID). It is compatible with LoRa wireless, USB serial port, RS485, and RJ45 Ethernet connection. Among them, the efficiency analysis of the Q-value algorithm finds that the recognition rate of the system reaches a maximum of about 0.367 when the number of tags n is about the frame length. The multi-tag anti-collision algorithm design based on the algorithm improves the efficiency of information collection in production and distribution links. The traceability code identification scheme is designed to effectively match various links, and the platform of system is built using LabVIEW2014 software, which has five sub-modules including user management, farm management, slaughter management, logistics management, and sales management. The system uses MySQL databases to store traceability information so that users can complete their queries by entering the traceability code on the system platform. The system not only has a low cost and a broad range of applications, but it also realizes the tracking record of meat product traceability information from breeding to selling, completes the function from information collection to information inquiry, and solves the problem of the incomplete traceability information chain. In addition, the system not only enhances the informational transparency of meat products in the product supply chain but also provides information for the regulatory authorities to effectively monitor safety. Full article

(This article belongs to the Special Issue Next-Generation Wireless Systems for the Internet of Things (IoT))

► Show Figures

Figure 1

13 pages, 5092 KiB

Open AccessArticle

NetAP-ML: Machine Learning-Assisted Adaptive Polling Technique for Virtualized IoT Devices

by Hyunchan Park, Younghun Go, Kyungwoon Lee and Cheol-Ho Hong

Sensors 2023, 23(3), 1484; https://doi.org/10.3390/s23031484 - 29 Jan 2023

Viewed by 1871

Abstract

To maximize the performance of IoT devices in edge computing, an adaptive polling technique that efficiently and accurately searches for the workload-optimized polling interval is required. In this paper, we propose NetAP-ML, which utilizes a machine learning technique to shrink the search space [...] Read more.

To maximize the performance of IoT devices in edge computing, an adaptive polling technique that efficiently and accurately searches for the workload-optimized polling interval is required. In this paper, we propose NetAP-ML, which utilizes a machine learning technique to shrink the search space for finding an optimal polling interval. NetAP-ML is able to minimize the performance degradation in the search process and find a more accurate polling interval with the random forest regression algorithm. We implement and evaluate NetAP-ML in a Linux system. Our experimental setup consists of a various number of virtual machines (2–4) and threads (1–5). We demonstrate that NetAP-ML provides up to 23% higher bandwidth than the state-of-the-art technique. Full article

(This article belongs to the Special Issue Next-Generation Wireless Systems for the Internet of Things (IoT))

► Show Figures

Figure 1

12 pages, 1250 KiB

Open AccessArticle

Accurate Crack Detection Based on Distributed Deep Learning for IoT Environment

by Youngpil Kim, Shinuk Yi, Hyunho Ahn and Cheol-Ho Hong

Sensors 2023, 23(2), 858; https://doi.org/10.3390/s23020858 - 11 Jan 2023

Cited by 7 | Viewed by 2196

Abstract

Defects or cracks in roads, building walls, floors, and product surfaces can degrade the completeness of the product and become an impediment to quality control. Machine learning can be a solution for detecting defects effectively without human experts; however, the low-power computing device [...] Read more.

Defects or cracks in roads, building walls, floors, and product surfaces can degrade the completeness of the product and become an impediment to quality control. Machine learning can be a solution for detecting defects effectively without human experts; however, the low-power computing device cannot afford that. In this paper, we suggest a crack detection system accelerated by edge computing. Our system consists of two: Rsef and Rsef-Edge. Rsef is a real-time segmentation method based on effective feature extraction that can perform crack image segmentation by optimizing conventional deep learning models. Then, we construct the edge-based system, named Rsef-Edge, to significantly decrease the inference time of Rsef, even in low-power IoT devices. As a result, we show both a fast inference time and good accuracy even in a low-powered computing environment. Full article

(This article belongs to the Special Issue Next-Generation Wireless Systems for the Internet of Things (IoT))

► Show Figures

Figure 1

15 pages, 4518 KiB

Open AccessArticle

Dynamic Design of a Quad-Stable Piezoelectric Energy Harvester via Bifurcation Theory

by Qichang Zhang, Yucheng Yan, Jianxin Han, Shuying Hao and Wei Wang

Sensors 2022, 22(21), 8453; https://doi.org/10.3390/s22218453 - 3 Nov 2022

Cited by 4 | Viewed by 1678

Abstract

The parameter tuning of a multi-stable energy harvester is crucial to enhancing harvesting efficiency. In this paper, the bifurcation theory is applied to quantitatively reveal the effects of structural parameters on the statics and dynamics of a quad-stable energy harvester (QEH). Firstly, a [...] Read more.

The parameter tuning of a multi-stable energy harvester is crucial to enhancing harvesting efficiency. In this paper, the bifurcation theory is applied to quantitatively reveal the effects of structural parameters on the statics and dynamics of a quad-stable energy harvester (QEH). Firstly, a novel QEH system utilizing the geometric nonlinearity of springs is proposed. Static bifurcation analysis is carried out to design quad-stable working conditions. To investigate the cross-well and high-energy vibration, the complex dynamic frequency (CDF) method, suitable for both weakly and strongly nonlinear dynamic problems, is then applied to deduce the primary response solution. By using the unfolding analysis in singularity theory, four steady-state properties and dozens of primary resonance modes are demonstrated. Based on the transition set, the effective bandwidth for energy harvesting can be customized to adapt well to various vibration environments by parametric adjustment. Finally, the experimental tests verify that the output power can reach up to 1 mW. The proposed QEH and its mechanics optimization can guide energy supply for next-generation wireless systems and low-power sensors under magnetic forbidding environments. Full article

(This article belongs to the Special Issue Next-Generation Wireless Systems for the Internet of Things (IoT))

► Show Figures

Figure 1

17 pages, 1685 KiB

Open AccessArticle

Reinforcement Learning Based Multipath QUIC Scheduler for Multimedia Streaming

by Seunghwa Lee and Joon Yoo

Sensors 2022, 22(17), 6333; https://doi.org/10.3390/s22176333 - 23 Aug 2022

Cited by 8 | Viewed by 2548

Abstract

With the recent advances in computing devices such as smartphones and laptops, most devices are equipped with multiple network interfaces such as cellular, Wi-Fi, and Ethernet. Multipath TCP (MPTCP) has been the de facto standard for utilizing multipaths, and Multipath QUIC (MPQUIC), which [...] Read more.

With the recent advances in computing devices such as smartphones and laptops, most devices are equipped with multiple network interfaces such as cellular, Wi-Fi, and Ethernet. Multipath TCP (MPTCP) has been the de facto standard for utilizing multipaths, and Multipath QUIC (MPQUIC), which is an extension of the Quick UDP Internet Connections (QUIC) protocol, has become a promising replacement due to its various advantages. The multipath scheduler, which determines the path to which each packet should be transmitted, is a key function that affects the multipath transport performance. For example, the default minRTT scheduler typically achieves good throughput, while the redundant scheduler gains low latency. While the legacy schedulers may generally give a desirable performance in some environments, however, each application renders different requirements. For example, Web applications target low latency, while video streaming applications require low jitter and high video quality. In this paper, we propose a novel MPQUIC scheduler based on deep reinforcement learning using the Deep Q-Network (DQN) that enhances the quality of multimedia streaming. Our proposal first takes into account both delay and throughput as a reward for reinforcement learning to achieve a low video chunk download time. Second, we propose a chunk manager that informs the scheduler of the video chunk information, and we also tune the learning parameters to explore new random actions adequately. Finally, we implement our new scheduler on the Linux kernel and give results using the Mininet experiments. The evaluation results show that our proposal outperforms legacy schedulers by at least 20%. Full article

(This article belongs to the Special Issue Next-Generation Wireless Systems for the Internet of Things (IoT))

► Show Figures

Figure 1

Journal Menu

Journal Browser

Next-Generation Wireless Systems for the Internet of Things (IoT)

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Related Special Issue

Published Papers (8 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI