Intelligent integrated sensing and communication: a survey

Science China Information Sciences, Journal Year: 2024, Volume and Issue: 68(3)

Published: Dec. 11, 2024

Abstract Integrated sensing and communication (ISAC) is a promising technique to increase spectral efficiency support various emerging applications by sharing the spectrum hardware between these functionalities. However, traditional ISAC schemes are highly dependent on accurate mathematical model suffer from challenges of high complexity poor performance in practical scenarios. Recently, artificial intelligence (AI) has emerged as viable address issues due its powerful learning capabilities, satisfactory generalization capability, fast inference speed, adaptability for dynamic environments, facilitating system design shift model-driven data-driven. Intelligent ISAC, which integrates AI into been hot topic that attracted many researchers investigate. In this paper, we provide comprehensive overview intelligent including motivation, typical applications, recent trends, challenges. particular, first introduce basic principle followed key techniques. Then, an comparison model-based AI-based methods provided. Furthermore, trends AI-enabled reviewed. Finally, future research discussed.

Language: Английский

---

Private Collaborative Edge Inference via Over-the-Air Computation

IEEE Transactions on Machine Learning in Communications and Networking, Journal Year: 2025, Volume and Issue: 3, P. 215 - 231

Published: Jan. 1, 2025

We consider collaborative inference at the wireless edge, where each client's model is trained independently on its local dataset. Clients are queried in parallel to make an accurate decision collaboratively. In addition maximizing accuracy, we also want ensure privacy of models. To this end, leverage superposition property multiple access channel implement bandwidth-efficient multi-user methods. propose different methods for ensemble and multi-view classification that exploit over-the-air computation (OAC). show these schemes perform better than their orthogonal counterparts with statistically significant differences while using fewer resources providing guarantees. provide experimental results verifying benefits proposed OAC approach inference, ablation study demonstrate effectiveness our design choices. share source code framework publicly Github facilitate further research reproducibility.

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

---

The Impact of Artificial Intelligence on Communication Dynamics and Performance in Organizational Leadership

Administrative Sciences, Journal Year: 2025, Volume and Issue: 15(2), P. 33 - 33

Published: Jan. 23, 2025

This study explores the impact of artificial intelligence (AI)-based technologies on leadership-based organizational communication and employee performance within contemporary workplaces. While prior research has acknowledged AI’s potential in optimizing processes, significant gaps remain understanding its specific influence core dimensions outcomes. addresses these by examining six key elements—informing, message reception, feedback, acceptance, persuasion, reaction—to assess whether AI significantly enhance improving internal efficiency reducing transmission errors, which are crucial for productive interactions. Using a quantitative approach, data were collected via self-administered questionnaire from 203 employees major Romanian food industry company operating globally, including leaders three Eastern European countries. Partial least squares structural equation modeling (PLS-SEM) was employed to analyze relationships between performance. The findings revealed that informing, receiving, accepting messages, along with reaction-provoking, had strong positive effects performance, while feedback persuasion showed moderate impacts. These results emphasize transformative role flow positively influencing behavior, thereby enhancing productivity efficiency. contributes growing body literature situating AI-driven broader context, offering actionable insights managers aiming integrate ethically effectively. Additionally, it offers set recommendations lead process according new actual era digitization, is real benefits both parts. It also provides robust foundation future research, encouraging longitudinal cross-cultural studies further investigate implications diversity, innovation, well-being.

Language: Английский

---

Energy-Efficient Optimal Mode Selection for Edge AI Inference via Integrated Sensing-Communication-Computation

IEEE Transactions on Mobile Computing, Journal Year: 2024, Volume and Issue: 23(12), P. 14248 - 14262

Published: Aug. 8, 2024

Existing edge inference methods only consider one paradigm, i.e., of on-device inference, on-server or edge-device cooperative inference. Each paradigm has its pros and cons as well dominant application scopes. For example, the is best choice when task not computationally intensive, suitable if communication capacity strong, mode should be selected in scenario weak computation. However, each suffers from poor performance deployed outside scope, thus leading to limited potential flexibility. This paper proposes an AI framework, which makes first attempt jointly three modes for making full use their benefits. In addition, sensing data acquisition enabled at both server device. can effectively improve accuracy with rich information on target area two different views. On other hand, energy cost minimization turns out a key all over world significant issue wireless networks. To this end, we minimizing system under given guarantee network resource constraints, by coordinating sensing, communication, computation modes. By optimally solving optimization problem, integrated sensing-communication-computation (ISCC) based task-oriented selection scheme proposed. A practical ISCC platform built extensive experiments are conducted verify our theoretical analysis.

Language: Английский

---

Broadband Over-the-Air Voxel Fusion for Integrated Sensing and Edge AI

2022 IEEE International Conference on Communications Workshops (ICC Workshops), Journal Year: 2024, Volume and Issue: unknown, P. 1298 - 1303

Published: June 9, 2024

Language: Английский

---

Beamforming Design for Integrated Sensing, Over-the-Air Computation, and Communication in Internet of Robotic Things

IEEE Internet of Things Journal, Journal Year: 2024, Volume and Issue: 11(20), P. 32478 - 32489

Published: Aug. 14, 2024

Language: Английский

---

Reconfigurable Intelligent Surface Assisted Integrated Sensing, Communication and Computation Systems

Published: April 14, 2024

Language: Английский

---

Storage-Aware Joint User Scheduling and Bandwidth Allocation for Federated Edge Learning

IEEE Transactions on Cognitive Communications and Networking, Journal Year: 2024, Volume and Issue: 11(1), P. 581 - 593

Published: Aug. 29, 2024

Language: Английский

---

Joint Device Scheduling and Resource Allocation for ISCC-Based Multi-View-Multi-Task Inference

IEEE Internet of Things Journal, Journal Year: 2024, Volume and Issue: 11(24), P. 40814 - 40830

Published: Sept. 6, 2024

Language: Английский

---