Boyang Ji | Search arXiv

arXiv2026

Toward Service-Balanced ISAC: From Coupled RAN to De-Coupled RAN

Sixth-generation (6G) applications require radio access networks (RANs) to support reliable communication and seamless sensing across their operating regions. In coupled RAN deployments, shared downlink transmitting and uplink receiving sites constrain the network's ability to accommodate asymmetric links and different sensing geometries. De-Coupled RAN (DC-RAN) separates these functions, allowing independently deployed and coordinated base stations to extend uplink and downlink communication and sensing coverage. How this flexibility translates into balanced communication and sensing services, however, remains insufficiently explored. This article revisits the evolution from coupled to DC-RAN from the perspective of service-balanced integrated sensing and communication (ISAC). It examines how architectural choices affect the availability of both services, with communication-sensing coverage symmetry capturing their spatial alignment under application-specific quality requirements. Practical challenges include preserving communication consistency, maintaining sensing continuity, and coordinating distributed resources. Two case studies illustrate how DC-RAN can support coverage symmetry alongside consistent communication, and how complementary observations can sustain continuous and accurate sensing. These examples inform a discussion of future research toward service-balanced ISAC.

eess.SP↗

arXiv2020

Performance of regression models as a function of experiment noise

A challenge in developing machine learning regression models is that it is difficult to know whether maximal performance has been reached on a particular dataset, or whether further model improvement is possible. In biology this problem is particularly pronounced as sample labels (response variables) are typically obtained through experiments and therefore have experiment noise associated with them. Such label noise puts a fundamental limit to the performance attainable by regression models. We address this challenge by deriving a theoretical upper bound for the coefficient of determination (R2) for regression models. This theoretical upper bound depends only on the noise associated with the response variable in a dataset as well as its variance. The upper bound estimate was validated via Monte Carlo simulations and then used as a tool to bootstrap performance of regression models trained on biological datasets, including protein sequence data, transcriptomic data, and genomic data. Although we study biological datasets in this work, the new upper bound estimates will hold true for regression models from any research field or application area where response variables have associated noise.

q-bio.BM↗