Semantic Coding Based on Semantic Segmentation Map for Image Compression

Published: Jan. 1, 2025

With the dramatic growth of multimedia volume, semantic-oriented image representation and compression methods have proved to be important approaches improve efficiency in 6G scenarios. Semantic segmentation maps become carriers for semantic compressive coding due explicit description spatial categorical semantics core objects. This letter proposes an framework based on maps, which efficient flexible adjustment bit-rates are realized by controllable maps. Specifically, region-based map is proposed polygon-based sketch redundancy elimination. In addition, with variable adjusting fitting threshold filtering regions. Experiments conducted ADE20k Cityscapes datasets validate performances compression. Results show that method achieves superior performance compared classical at low bit rates. The achieved average 0.237 0.176 MIoU improvement over BPG, respectively.

Language: Английский

---

Deep Reinforcemnet Learning for Robust Beamforming in Integrated Sensing, Communication and Power Transmission Systems

Sensors, Journal Year: 2025, Volume and Issue: 25(2), P. 388 - 388

Published: Jan. 10, 2025

A communication network integrating multiple modes can effectively support the sustainable development of next-generation wireless communications. Integrated sensing, communication, and power transfer (ISCPT) represents an emerging technological paradigm that not only facilitates information transmission but also enables environmental sensing transfer. To achieve optimal beamforming in transmission, it is crucial to satisfy constraints, including quality service (QoS), radar accuracy, efficiency, while ensuring fundamental system performance. The presence parametric constraints makes problem a non-convex optimization challenge, underscoring need for solution balances low computational complexity with high precision. Additionally, accuracy channel state (CSI) pivotal determining achievable rate, as imperfect or incomplete CSI significantly degrade performance efficiency. Deep reinforcement learning (DRL), machine technique where agent learns by interacting its environment, offers promising approach dynamically optimize through adaptive decision-making strategies. In this paper, we propose DRL-based ISCPT framework, which manages complex states continuously adjusts variables related energy harvesting enhance overall efficiency reliability. rate upper bound be inferred robust, learnable system. Our results demonstrate algorithms improve resource allocation, management, particularly dynamic uncertain environments CSI.

Language: Английский

---

A neural coding method based on feature sensing

IET Communications, Journal Year: 2025, Volume and Issue: 19(1)

Published: Jan. 1, 2025

Abstract The novel network contains many sensors, which greatly heightens data transmission burdens. Some networks require the perceived by sensors for a period to make decisions. Drawing inspiration from human neural conduction mechanism, waveform encoding method called feature sensing coding (FSNC) is proposed enhance efficiency. It involves decomposition of information and subsequent non‐linear coefficients transmission. This approach exploits unique neuronal responses diverse stimuli inherent characteristics coding. Finally, taking speech signal seismic wave as examples, effectiveness FSNC verified simulating auditory nerve process with frequency according mechanism travelling motion basilar membrane in cochlea. Moreover, experiments on signals have demonstrated wide applicability FSNC. Compared traditional schemes, bit rate only 6.4 kbps, reduces amount transmitted. Not that, also has certain fault tolerance, parallel can increase rate. research provides new ideas efficient over networks.

Language: Английский

---

Introduction and overview

Elsevier eBooks, Journal Year: 2025, Volume and Issue: unknown, P. 3 - 9

Published: Jan. 1, 2025

Language: Английский

---

Learning to optimize via knowledge guidance

Elsevier eBooks, Journal Year: 2025, Volume and Issue: unknown, P. 141 - 156

Published: Jan. 1, 2025

Language: Английский

---

Scalable Semantic Adaptive Communication for Task Requirements in WSNs

Sensors, Journal Year: 2025, Volume and Issue: 25(9), P. 2823 - 2823

Published: April 30, 2025

Wireless Sensor Networks (WSNs) have emerged as an efficient solution for numerous real-time applications, attributable to their compactness, cost effectiveness, and ease of deployment. The rapid advancement the Internet Things (IoT), Artificial Intelligence (AI), sixth-generation mobile communication technology (6G) Mobile Edge Computing (MEC) in recent years has catalyzed transition towards large-scale deployment WSN devices, changed image sensing understanding novel modes (such machine-to-machine or human-to-machine interactions). However, resulting data proliferation dynamics environments introduce new challenges communication: (1) ensuring robust adverse (2) effectively alleviating bandwidth pressure from massive transmission. To address these issues, this paper proposes a Scalable Semantic Adaptive Communication (SSAC) task requirement. Firstly, we design Attention Mechanism-based Joint Source Channel Coding (AMJSCC) order fully exploit correlation among semantic features, channel conditions, tasks. Then, Prediction Generator (PSSG) is constructed implement scalable semantics, allowing flexible adjustments achieve adaptation. experimental results show that proposed SSAC more than traditional other algorithms classification tasks, achieves compression rates without sacrificing performance, while improving utilization system.

Language: Английский

---

Joint Source-Channel Coding System for 6G Communication: Design, Prototype and Future Directions

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 17708 - 17724

Published: Jan. 1, 2024

The emergence of the AI era signifies a shift in future landscape global communication networks, wherein robots are expected to play more prominent role compared humans. establishment novel paradigm for development next-generation 6G is utmost importance semantics task-oriented empowered communications. goal semantic lies integration collaborative efforts between intelligence transmission source and joint design coding channel coding. This characteristic represents significant benefit source-channel (JSCC), as it enables generation alphabets with diverse lengths achieves code rate unity. Therefore, we leverage not only quasi-cyclic (QC) characteristics facilitate utilization flexible structural hardware but also Unequal Error Protection (UEP) ensure recovery importance. In this study, feasibility using encoder/decoder that aware UEP can be explored based on existing JSCC system. approach aimed at protecting significance information. Additionally, deployment system facilitated by employing QC-Low-Density Parity-Check (LDPC) codes reconfigurable device. QC-LDPC layered decoding technique, which has been specifically optimized parallelism tailored applications, suitably adapted accommodate performance proposed evaluated conducting BER measurements both floating-point 6-bit quantization. done assess extent deterioration fair manner. fixed-point synthesized subsequently used feature reception across noisy channel, aim presenting prototype study concludes some insights potential research avenues context communication.

Language: Английский

---

A Survey on Goal-Oriented Semantic Communication: Techniques, Challenges, and Future Directions

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 51223 - 51274

Published: Jan. 1, 2024

Although many proposals have been developed for the sixth-generation (6G) technology, realizing 6G is fraught with numerous fundamental interdisciplinary, multidisciplinary, and transdisciplinary challenges.To mitigate some of these challenges, goal-oriented semantic communication (SemCom) has emerged as a promising technology enabler.This enabler employs only semantically-relevant information successful task execution while minimizing power usage, bandwidth consumption, transmission delay.On other hand, essential major SemCom use cases such autonomous transportation.These paradigms call tighter integration SemCom.To facilitate this purpose, survey paper exposes challenges 6G; details notion its stateof-the-art research landscape; presents state-of-the-art trends, cases, frameworks SemCom; offers future directions SemCom.Consequently, article stimulates lines on theories, algorithms, realization.

Language: Английский

---

Collaborative Edge AI Inference over Cloud-RAN

IEEE Transactions on Communications, Journal Year: 2024, Volume and Issue: 72(9), P. 5641 - 5656

Published: April 15, 2024

In this paper, a cloud radio access network (Cloud-RAN) based collaborative edge AI inference architecture is proposed. Specifically, geographically distributed devices capture real-time noise-corrupted sensory data samples and extract the noisy local feature vectors, which are then aggregated at each remote head (RRH) to suppress sensing noise. To realize efficient uplink aggregation, we allow RRH receives vectors from all over same resource blocks simultaneously by leveraging an over-the-air computation (AirComp) technique. Thereafter, these quantized transmitted central processor (CP) for further aggregation downstream tasks. Our aim in work maximize accuracy via surrogate metric called discriminant gain, measures discernibility of different classes space. The key challenges lie on suppressing coupled noise, AirComp distortion caused hostile wireless channels, quantization error resulting limited capacity fronthaul links. address challenges, proposes joint transmit precoding, receive beamforming, control scheme enhance accuracy. Extensive numerical experiments demonstrate effectiveness superiority our proposed optimization algorithm compared various baselines.

Language: Английский

---

Over-the-Air Computation for 6G: Foundations, Technologies, and Applications

IEEE Internet of Things Journal, Journal Year: 2024, Volume and Issue: 11(14), P. 24634 - 24658

Published: May 24, 2024

The rapid advancement of artificial intelligence technologies has given rise to diversified intelligent services, which place unprecedented demands on massive connectivity and gigantic data aggregation. However, the scarce radio resources stringent latency requirement make it challenging meet these demands. To tackle challenges, over-the-air computation (AirComp) emerges as a potential technology. Specifically, AirComp seamlessly integrates communication procedures through superposition property multiple-access channels, yields revolutionary paradigm shift from "compute-after-communicate" "compute-when-communicate". By this means, enables spectral-efficient low-latency wireless aggregation by allowing multiple devices occupy same channel for transmission. In paper, we aim present recent in terms foundations, technologies, applications. mathematical form design are introduced foundations AirComp, critical issues over different network architectures then discussed along with review existing literature. employed analysis optimization reviewed information theory signal processing perspectives. Moreover, studies that practical implementation systems, elaborate applications Internet Things edge networks. Finally, research directions highlighted motivate future development AirComp.

Language: Английский

---