# radio Published articles for radio. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Norwegians Release FOSS GNOME Software for Music Recording, Internet Radio, and Cameras DevFeed: [Norwegians Release FOSS GNOME Software for Music Recording, Internet Radio, and Cameras]() Original publisher: [Read original article]() Author: EditorDavid Published: 2026-11-08T16:34:00Z Content type: release Language: en Sources: [Slashdot]() Topics: [recording](), [Image](), [Web]() Tags: [cameras](), [foss](), [free](), [free-software](), [gnome](), [internet](), [internet-radio](), [music](), [radio](), [recording](), [release](), [software]() ### AI overview GarageJam 8.0.1 records audio directly to Ogg Vorbis files in the working directory and provides a GTK/GNOME wizard for editing metadata in .gjxml XML files; it is available in C and Python and uses the Gingerblue Recording Studio API. GNOME Media combines internet radio stations and photographs on an OpenStreetMap: users can select stations to listen, browse stations by city, and view or open photos whose EXIF data includes GPS positions. Its search filters both the station list and map. GPhoto 3.0.1 is built on libgphoto2 2.5.34, which supports more than 2,500 camera models. Skolelinux 13.6.0 is based on Debian 13 and is described as a ready-to-use school operating system with office, web, educational, and school network software. ### Source excerpt ole (Slashdot reader #19,909) writes in about his free, Norwegian open-source music recording studio for GNOME called GarageJam, which he says allows musicians to compose, record, and share original music seamlessly on the Internet. The latest release, GarageJam 8.0.1, is available in C and Python. It records audio immediately to Ogg Vorbis (.ogg) files in the current working directory and lets you edit metadata in .gjxml XML files from a GTK/GNOME wizard -- all built on the Gingerblue Recording Studio API. Ole shares links to its IETF GarageJam XML draft and GitHub repositories, and there's also GarageJam Studio, "a commercial music and audio recording app for the World Wide Web written by Aamot Innovation from Norway.". ole is also spreading the word about GNOME Media, which "puts internet radio and your photographs on one OpenStreetMap... built from GNOME Radio 85.0.1." Click a station on the map to listen. Cities with several stations show a count and a menu. Open a folder of pictures or import from a camera. Photos with a GPS position in their EXIF data appear on the map. Double-click a thumbnail to open it. The search box filters the station list and the map together. ole also announces: GPhoto 3.0.1. ("After 25 years, libgphoto2 2.5.34 now supports more than 2,500 camera models, and GPhoto 3.0.1 is built on it.") Skolelinux 13.6.0. Built on Debian 13 âoetrixieâ, Skolelinux is "a complete, ready-to-use Free Software operating system for schools, classrooms and home computers... an office suite, web browser, educational programs and network services for an entire school, all set up out of the box." Read more of this story at Slashdot. ## The Hidden Microcontroller Inside a LoRa chip DevFeed: [The Hidden Microcontroller Inside a LoRa chip]() Original publisher: [Read original article]() Author: Jenny List Published: 2026-11-07T12:00:34Z Content type: news Language: en Sources: [Hackaday]() Topics: [Microcontroller](), [Electrical engineering and computer science (EECS)]() Tags: [asic](), [chip](), [display](), [firmware](), [llms](), [lora](), [lr2021](), [mesh](), [mesh-network](), [microcontroller](), [microcontrollers](), [module](), [network](), [node](), [peripheral](), [radio](), [radio-hacks](), [reverse-engineering](), [sdr](), [semtech](), [software-defined-radio](), [wifi]() ### AI overview The Semtech LR2021 has an onboard microcontroller with updateable firmware, rather than operating only as a preprogrammed radio ASIC. Alex Beale reverse engineered it with help from LLMs and demonstrated custom firmware that runs FFTs for a waterfall display and can host a mesh network node on the chip. The excerpt describes these as newly unlocked capabilities; it does not detail the reverse-engineering method or the firmware update requirements. ### Source excerpt If you've ever done anything with LoRa, the chances are you've used a LoRa chip or module as a peripheral for a microcontroller, and left it at that. But that's ...read more ## PRB Starvation at Slot Time via Rank Indicator Inflation: Attacking Proportional Fair Memory in the Scheduler DevFeed: [PRB Starvation at Slot Time via Rank Indicator Inflation: Attacking Proportional Fair Memory in the Scheduler]() Original publisher: [Read original article]() Author: Ryan Barker, Julia Boone, Tolunay Seyfi, Alirez Ebrahimi, Ethan Farquhar, Brian Davis, Joseph Boccuzzi, Fatemeh Afghah Published: 2026-11-06T05:00:00Z Content type: article Language: en Sources: [arXiv: Networking]() Topics: [5G](), [scheduling](), [rate-limiting](), [round robin]() Tags: [5g](), [attack](), [cs-ni](), [denial-of-service](), [dos](), [failure](), [fairness](), [feedback](), [inflation](), [layers](), [memory](), [monte-carlo](), [offline](), [quality](), [radio](), [rank](), [ray-tracing](), [round-robin](), [scheduler](), [scheduling]() ### AI overview The abstract describes a served-but-undelivered denial-of-service attack on proportional fair (PF) scheduling: inflating a UE's rank indicator (RI) selects unsupported spatial layers, causing delivery failures that keep its delivered-service EWMA low. The evaluated PF allocator then repeatedly grants that UE the full PRB pool, starving honest UEs. Across simulations, selective RI inflation on the rank 2 geometry captured 94-95% of PRBs, lowered Jain fairness from 0.997 to 0.28, and caused mean honest zero-grant runs of 41-56 ms; round robin preserved equal allocation. Replay and recurrence analyses attribute the main effect to PF's delivered-service denominator. A channel-quality trigger was weaker and controller-dependent, and activity-gated EWMA defenses remained blind. The authors propose RI-consistency checks and slot-time PRB evidence within the O-RAN Distributed Unit. ### Source excerpt arXiv:2611.07225v1 Announce Type: new Abstract: Proportional fair (PF) scheduling in fifth-generation (5G) New Radio (NR) ranks user equipment (UE) by instantaneous rate over an exponentially weighted moving average (EWMA) of delivered service. We identify a served-but-undelivered denial-of-service (DoS) attack in which rank indicator (RI) inflation induces persistent physical resource block (PRB) starvation. Unsupported spatial layers cause first-attempt delivery failure, keeping the attacker's service EWMA low; the evaluated PF allocator repeatedly grants it the full PRB pool, denying honest UEs transmission opportunities. We formalize this recurrence and evaluate it in 3,300 paired, 200 slot multi-user shards spanning rank 1 and rank 2 Sionna Ray Tracing geometries, three link adaptation controllers, PF and round robin (RR), four target identities, and five seeds. On the rank 2 geometry, selective RI inflation yields 94--95\% target capture, reduces PRB Jain fairness from 0.997 to 0.28, and produces mean honest zero-grant runs of 41--56\,ms; RR preserves equal allocation. Exact offline replay and a Monte Carlo recurrence isolate the delivered-service denominator as the causal path. Cross-field and controller ablations show a weaker, controller-dependent channel-quality trigger, while activity-gated EWMA defenses remain structurally blind. The results motivate RI-consistency checks before feedback acquires scheduling authority and slot-time PRB evidence inside the O-RAN Distributed Unit. ## Deep Meets Classical: A CPU-Efficient Decision-Fusion Model for Automatic Modulation Classification DevFeed: [Deep Meets Classical: A CPU-Efficient Decision-Fusion Model for Automatic Modulation Classification]() Original publisher: [Read original article]() Author: Zhiyi Yin, Zhizhao Wen, Ruoxin Zhang, Chao Wang, Puyang Xu, Yifan Jiang, Yusi Gong Published: 2026-11-05T05:00:00Z Content type: article Language: en Sources: [arXiv: Artificial Intelligence]() Topics: [Artificial Intelligence](), [Neural Network](), [model architecture](), [catboost]() Tags: [classification](), [cnn](), [cpu](), [cpu-efficient](), [cs-ai](), [cs-lg](), [embedded](), [fusion](), [logistic-regression](), [radio](), [signal](), [snr]() ### AI overview FuseAMC combines a residual CNN on raw I/Q samples with a higher-order-cumulant classifier because their strengths differ by SNR: the CNN is more robust at low SNR, while the classical classifier is more accurate at high SNR. A logistic-regression combiner learns from both models' class posteriors using a validation split separate from the test set. On RadioML 2016.10a, across five seeds and a 44,000-frame held-out test set, it achieved 55.8% accuracy, 5.1 percentage points above the best cumulant baseline and 3.2 points above the CNN alone; reported paired-bootstrap confidence bounds for both gains were positive. The roughly 198,000-parameter CNN and full pipeline require about 3 MFLOPs per frame and run on one CPU core without hardware acceleration. ### Source excerpt arXiv:2611.05937v1 Announce Type: cross Abstract: Automatic modulation classification (AMC) underpins spectrum sensing and non-cooperative signal identification in cognitive radio, yet the two standard CPU-feasible approaches to it, a compact convolutional neural network (CNN) on raw in-phase and quadrature (I/Q) samples and a classical higher-order-cumulant feature classifier, are rarely compared against each other conditioned on signal-to-noise ratio (SNR). We show that they are, in fact, complementary: the CNN is markedly more robust at low SNR, where hand-crafted statistics collapse toward chance, while the cumulant classifier is more accurate at high SNR, where higher-order statistics cleanly separate dense constellations. We exploit this complementarity with FuseAMC, a lightweight decision-fusion model that trains a logistic-regression meta-combiner over the concatenated class-posteriors of an approximately 198k-parameter residual CNN and a gradient-boosted-tree cumulant classifier, on a validation split disjoint from test. On RadioML 2016.10a (5 seeds, 44k-frame held-out test set), FuseAMC reaches 55.8% overall accuracy, improving on the best cumulant-feature baseline by 5.1 points and on the CNN alone by 3.2 points (paired-bootstrap 95% confidence-interval lower bounds of 5.0 and 3.1 points, both positive), while matching the best classical baseline in its own strong high-SNR regime and the CNN in its strong low-SNR regime. With about 0.2 million parameters, a model footprint of a few megabytes, and roughly 3 MFLOPs per frame, the whole pipeline trains and runs on one CPU core, targeting general-purpose and embedded processors without hardware acceleration. ## CVE-2026-87040 - Bluetooth LE Controller accepts received PDUs whose length field exceeds the configured maximum receive length, causing out-of-bounds read and write DevFeed: [CVE-2026-87040 - Bluetooth LE Controller accepts received PDUs whose length field exceeds the configured maximum receive length, causing out-of-bounds read and write]() Original publisher: [Read original article]() Author: cvefeed.io Published: 2026-11-04T06:17:06Z Content type: article Language: en Sources: [Latest High/Critical Vulnerabilitiy Feed]() Topics: [Memory Safety](), [Bluetooth LE]() Tags: [2026](), [advertising](), [authentication](), [bluetooth](), [bluetooth-le](), [buffer](), [controller](), [corruption](), [cve](), [cve-2026-87040](), [encrypted](), [hci](), [interaction](), [iso](), [link](), [out-of-bounds-write](), [radio](), [range](), [update](), [write](), [zephyr](), [zephyrproject]() ### AI overview The nRF Bluetooth LE Controller failed to check received PDU length fields against the maximum length configured for the radio, allowing malformed packets to make downstream code read or write beyond buffers. A nearby attacker could trigger this on unencrypted LE connections or from a broadcaster the device is synchronised to for CONFIG_BT_CTLR_SYNC_ISO; pairing and user interaction are not required. Reported effects include controller crashes, memory corruption, and disclosure of controller memory through host data paths. Encrypted links are normally rejected by the CCM MIC check. The fix rejects PDUs longer than the configured receive maximum. The excerpt notes that periodic advertising sync reception in lll_sync.c was not changed and lacks an equivalent bound. ### Source excerpt CVE ID :CVE-2026-87040 Published : Nov. 4, 2026, 6:17 a.m. | 3 hours, 54 minutes ago Description :The nRF link-layer receive paths of the open-source Bluetooth LE Controller did not validate the on-air LENGTH field of a received PDU against the maximum receive length that was used to program the radio. isr_rx_pdu() in subsys/bluetooth/controller/ll_sw/nordic/lll/lll_conn.c enqueued any non-empty data PDU after only the sequence-number and (for encrypted links) MIC checks, and the corresponding isr_rx() handlers in lll_central_iso.c, lll_peripheral_iso.c, lll_sync_iso.c and lll_scan_aux.c did the same for ISO and extended-advertising PDUs. The nRF radio stores the received header verbatim and truncates only the payload at PCNF1.MAXLEN, so a frame declaring more octets than were configured leaves a node buffer whose len field describes more data than the buffer holds. An attacker within radio range that can emit a hand-crafted link-layer PDU -- for a connection, any peer that establishes an unencrypted LE connection to a connectable advertiser; for CONFIG_BT_CTLR_SYNC_ISO, any broadcaster the device is synchronised to -- can set the length byte up to 255 while the controller has programmed a much smaller maximum (lll->dle.eff.max_rx_octets, which is 27 until a Data Length Update, or the negotiated cis_lll->rx.max_pdu). No pairing, authentication or user interaction is required. On encrypted links the CCM MIC check normally rejects such a frame first, so the exposure is on unencrypted traffic, which is why the added check is placed after decryption. The unchecked length reaches hci_acl_encode() in subsys/bluetooth/controller/hci/hci.c, which performs net_buf_add(buf, pdu_data->len) followed by a memcpy() of that many bytes out of the node_rx pool element. Because CONFIG_BT_CTLR_DATA_LENGTH_MAX and CONFIG_BT_BUF_ACL_RX_SIZE both default to 27, this is an out-of-bounds read of up to roughly 228 bytes past the received PDU and a corresponding out-of-bounds write past the HC ## Build a portable radar station with a Raspberry Pi and SDR DevFeed: [Build a portable radar station with a Raspberry Pi and SDR]() Original publisher: [Read original article]() Author: Anne Barela Published: 2026-11-03T15:51:35Z Content type: news Language: en Sources: [Adafruit Industries]() Topics: [Raspberry Pi](), [AI Chat]() Tags: [ads-b](), [ai](), [aircraft](), [artificial-intelligence](), [conversational-ai](), [cooling](), [displays](), [external-antenna](), [flight-tracker](), [outdoor](), [portable](), [radio](), [raspberry-pi](), [science](), [sdr](), [software-defined-radio]() ### AI overview Jdaie Lin's portable flight tracker pairs a Raspberry Pi with an SDR to receive ADS-B broadcasts and extract aircraft altitude, speed and coordinates. A touchscreen displays nearby planes on a live radar map, while a Pi Sugar battery pack, external antenna and physical controls support outdoor use. The Pi and SDR run hot, so the build uses heat sinks and active cooling. A conversational AI layer answers questions about a plane's destination or expected arrival using the telemetry shown on screen. In outdoor testing, it tracked several aircraft at once with some lag. ### Source excerpt Julian Horsey at Geeky Gadgets covers a handheld flight tracker built by Jdaie Lin. It pairs a Raspberry Pi with a software-defined radio, a receiver that tunes radio signals in software instead of fixed hardware. The SDR picks up ADS-B, the position and status messages planes broadcast, and pulls out altitude, speed and coordinates. A [...] ## LakeShark: the pocket-sized portable SDR scanner DevFeed: [LakeShark: the pocket-sized portable SDR scanner]() Original publisher: [Read original article]() Author: Anne Barela Published: 2026-11-03T15:21:17Z Content type: news Language: en Sources: [Adafruit Industries]() Topics: [Decoding](), [Open Source]() Tags: [ads-b](), [amoled](), [electronics](), [esp-idf](), [esp32-p4](), [espressif](), [firmware](), [github](), [gpl](), [gps](), [handheld](), [headless](), [keyboard](), [lilygo](), [lora](), [maps](), [offline](), [offline-maps](), [portable](), [radio](), [reverse-engineering](), [rtl-sdr](), [scanner](), [sdr](), [vintage-computing]() ### AI overview LakeShark is a self-contained handheld SDR scanner built around the LilyGO T-Display P4; it can receive, decode and display radio signals without a connected PC. With an RTL-SDR Blog V3 or V4, it supports P25 Phase 1 trunking, FM, POCSAG, 1090 MHz ADS-B tracking and sub-GHz captures. P25 decoding uses OP25, Pavel Yazev's imbe_vocoder, DSD, dsd-fme and mbelib. An optional detachable keyboard adds CC1101, nRF24 and NFC, while CartoTUI, ZeroMesh, libcarto and a PMTiles reader provide GPS-based offline maps. The GPL-3.0 firmware requires ESP-IDF 5.4.3; the excerpt identifies version 2.3.2 as current. Headless Waveshare ESP32-P4 boards can run the receivers without a display. ### Source excerpt Open Electronics covered LakeShark, a handheld SDR scanner and radio workbench built by SAMS0N1TE. Software defined radio (SDR) has the tuning and decoding happening in code instead of fixed circuits. The build uses the LilyGO T-Display P4, with an ESP32-P4, a 4.1 inch AMOLED screen at 568 x 1232, 16 MB of flash, GPS, a [...] ## Dataset and Experimental Testbed for Deep Learning-Based Bluetooth Device Fingerprinting DevFeed: [Dataset and Experimental Testbed for Deep Learning-Based Bluetooth Device Fingerprinting]() Original publisher: [Read original article]() Author: Haytham Albousayri, Bechir Hamdaoui Published: 2026-11-03T05:00:00Z Content type: article Language: en Sources: [arXiv: Cryptography and Security]() Topics: [Deep learning](), [Bluetooth LE](), [Ground truth / benchmark quality]() Tags: [ai](), [benchmarking](), [ble](), [bluetooth](), [bluetooth-low-energy](), [cs-cr](), [dataset](), [deep-learning](), [dl](), [domain](), [eess-sp](), [environments](), [hardware](), [localization](), [networks](), [radio](), [raw](), [real-world](), [receiver](), [reliability](), [robust](), [robustness]() ### AI overview The paper introduces a BLE fingerprinting benchmark aimed at testing how well deep learning models generalize beyond their training conditions. Its dataset contains raw IQ transmissions from 31 commercial devices recorded across different days, locations, environments, temperatures, receiver hardware, and frequency channels. The paper also presents a case study evaluating state-of-the-art techniques for domain-robust radio frequency fingerprinting. The abstract motivates this work by noting that models effective under their original training configurations can fail in unseen conditions. ### Source excerpt arXiv:2611.00332v1 Announce Type: cross Abstract: AI-enabled wireless networks have emerged as vital components of future-generation wireless communication systems. Among various wireless architectures, Bluetooth Low Energy (BLE) networks have attracted significant research interest due to their widespread adoption and low cost. In these networks, deep learning (DL) models can be integrated directly into the physical-layer infrastructure to perform diverse tasks, including environment sensing, localization, radio frequency fingerprinting (RFFP), and signal denoising. While highly effective under their original training configurations, these DL models often fail significantly when deployed in unseen environments---such as different rooms, varying temperature conditions, or altered carrier frequencies. Addressing this limitation requires rigorous benchmarking of models and algorithms against unseen configurations to evaluate their generalization and robustness. To bridge this gap, this paper makes two key contributions: i) we introduce a comprehensive, large-scale wireless BLE dataset consisting of raw IQ transmissions from 31 distinct commercial devices captured across diverse days, locations, environments, temperatures, receiver hardware, and frequency channels; ii) we present a case study evaluating state-of-the-art techniques for domain-robust RFFP to advance real-world AI reliability. ## Spectral-Convolutional Factorized Transformer for Joint Multipath Parameter Estimation: Applications to mmWave Positioning and Radio SLAM DevFeed: [Spectral-Convolutional Factorized Transformer for Joint Multipath Parameter Estimation: Applications to mmWave Positioning and Radio SLAM]() Original publisher: [Read original article]() Author: Yaya Etiabi, Wessam Ajib, Halima Elbiaze Published: 2026-11-03T05:00:00Z Content type: article Language: en Sources: [arXiv: Artificial Intelligence]() Topics: [Artificial Intelligence](), [communications](), [Bluetooth LE]() Tags: [6g](), [ai](), [applications](), [attention](), [beam](), [channel](), [communication](), [complex](), [component](), [convolution](), [cs-ai](), [data](), [decoder](), [delay](), [eess-sp](), [environment](), [mmwave](), [parameter](), [positioning](), [radio](), [slam](), [transformer]() ### AI overview SCFT explicitly estimates multipath geometry from noisy complex channel estimates and physical beam-pair descriptors, targeting information that communication-focused channel estimators may not recover. It combines local spectral convolution, permutation-equivariant beam-set attention, and a query-based Transformer decoder to classify LoS and NLoS paths and estimate delay, AoA, and AoD. On realistic ray-tracing data, it reduced GOSPA error by 13.4% versus ResNet, the strongest competing baseline. In independent snapshot evaluations, position RMSE was lower by 18.5% for positioning and 65.0% for radio SLAM, relative to ResNet. The supplied abstract does not provide further experimental details. ### Source excerpt arXiv:2611.01491v1 Announce Type: cross Abstract: Future 6G wireless networks are expected to evolve toward AI-native systems that support intelligent, environment-aware services, including positioning and mapping. Current research has already integrated AI into several aspects of communication, particularly wireless channel estimation. However, most learning-based channel estimators focus on communication-oriented objectives rather than explicitly estimating multipath parameters such as delay, angle of arrival (AoA), and angle of departure (AoD). These parameters provide essential geometric information for downstream tasks including positioning and radio simultaneous localization and mapping (SLAM). In this work, we propose a Spectral-Convolutional Factorized Transformer (SCFT) for joint multipath component (MPC) estimation from noisy complex channel estimates and physical beam-pair descriptors. SCFT combines local spectral convolution, permutation-equivariant beam-set attention, and a query-based Transformer decoder to detect and classify line-of-sight (LoS) and non-line-of-sight (NLoS) paths and estimate their observed delays, AoAs, and AoDs. Experiments on realistic ray-tracing data show that SCFT reduces the generalized optimal sub-pattern assignment (GOSPA) error by 13.4% compared with ResNet, the strongest competing baseline. We further demonstrate this advantage in independent snapshot positioning and radio SLAM, where SCFT reduces position RMSE by 18.5% and 65.0%, respectively, relative to ResNet. These findings highlight the importance of explicitly recovering multipath geometry, as improvements in MPC estimation can translate into substantial gains in downstream tasks. ## RxGS: Receiver-Generalizable 3D Gaussian Splatting for Radio-Frequency Data Synthesis DevFeed: [RxGS: Receiver-Generalizable 3D Gaussian Splatting for Radio-Frequency Data Synthesis]() Original publisher: [Read original article]() Author: Kang Yang, Mani Srivastava Published: 2026-11-03T05:00:00Z Content type: article Language: en Sources: [arXiv: Networking]() Topics: [gaussian splatting](), [Machine learning]() Tags: [3d](), [3d-gaussian-splatting](), [3dgs](), [cs-ni](), [data](), [datasets](), [gaussian](), [gaussian-splatting](), [inference](), [learning](), [model](), [radio](), [receiver](), [rendering](), [rf](), [signal](), [storage](), [synthesis](), [training](), [wireless]() ### AI overview RxGS uses one shared 3D Gaussian Splatting model to synthesize RF signals at receiver positions excluded from training, within a surveyed scene. It first learns receiver-independent Gaussian geometry, freezes that geometry, then learns directional radiance conditioned on receiver position. A global branch models receiver effects shared across the scene, while a local branch captures per-scatterer differences tied to receiver geometry and occlusion. Shared geometry enables batched rendering across receivers. The abstract reports lower training, inference, and storage costs than approaches requiring a separate model for each receiver; it gives no numerical results or details about the datasets. ### Source excerpt arXiv:2605.24290v2 Announce Type: replace Abstract: Radio-frequency (RF) data synthesis predicts the received signal given transmitter and receiver positions, and is essential for wireless applications. Recent 3D Gaussian Splatting (3DGS)-based methods achieve efficient synthesis at any transmitter location within a surveyed scene, but require a separate model for each receiver. We therefore present RxGS, a shared 3DGS model that first learns receiver-independent Gaussian geometry and then freezes it while learning directional radiance conditioned on receiver position. Its global conditioning branch captures receiver-dependent effects shared across the scene, while a local branch models per-scatterer variations from the receiver's geometry and occlusion. The shared geometry also supports batched rendering through a multi-receiver rasterizer. Across RF datasets, RxGS predicts at receiver positions excluded from training within the surveyed scene while significantly reducing training, inference, and storage costs. Project page: https://kangyangg.com/projects/rxgs/. ## Communication-Efficient Model-Distributed Inference for CBRS Radar Detection at the Edge DevFeed: [Communication-Efficient Model-Distributed Inference for CBRS Radar Detection at the Edge]() Original publisher: [Read original article]() Author: Teng Li, Hulya Seferoglu Published: 2026-11-03T05:00:00Z Content type: article Language: en Sources: [arXiv: Distributed Computing]() Topics: [AI Infrastructure](), [Local AI](), [Data transmission](), [Jetson Orin](), [communications]() Tags: [5g](), [cbrs](), [communication](), [compression](), [cs-dc](), [data](), [detection](), [device](), [distributed](), [distributed-inference](), [edge](), [eess-sp](), [i-q](), [inference](), [jetson](), [jetson-orin](), [jetson-orin-nano](), [pipeline](), [quality](), [radar](), [radio](), [raw]() ### AI overview CEDAR reduces communication costs in edge-distributed CBRS radar detection by redesigning both the detector and model partitioning. CEDAR-YOLO removes YOLO's multi-scale neck and two detection scales, using a single-scale path with independently configured frequency and time resolutions. CEDAR-MDI adds lightweight activation compressors and chooses each compressor's partition to minimize the pipeline bottleneck. On an NVIDIA Jetson Orin Nano with real-world over-the-air data, CEDAR-YOLO reduced parameters by 35-57% and inference time by 16-33%; CEDAR-MDI achieved up to 3.27x the throughput of single-device inference. The abstract reports preserved detection quality for both, but provides no further evaluation details. ### Source excerpt arXiv:2611.00625v1 Announce Type: new Abstract: The Citizens Broadband Radio Service (CBRS) shares the 3550-3700 MHz band between incumbent radar systems and commercial LTE/5G users, so radar activity must be detected accurately and promptly. Spectrogram-based YOLO detectors can localize coexisting radar and cellular signals, but running them on resource-constrained edge devices is challenging. Model-distributed inference (MDI) can increase throughput by partitioning a model across edge devices. Using an end-to-end pipeline from raw I/Q samples to on-device detection, we show that partitioning recent YOLO generations incurs high activation-transfer costs due to their multi-scale structures. To reduce these costs, we propose CEDAR, a communication-efficient, edge-distributed architecture for radar detection. Its RF-aware detector, CEDAR-YOLO, removes YOLO's multi-scale neck and two of its three detection scales, leaving a single-scale path with independently configured frequency and time resolutions, which lowers the communication cost of partitioning. Its compression-aware MDI framework, CEDAR-MDI, integrates lightweight activation compressors and selects, for each compressor, the partition that minimizes the pipeline bottleneck. On an NVIDIA Jetson Orin Nano testbed with real-world over-the-air data, CEDAR-YOLO reduces the parameter count by 35-57% and model inference time by 16-33%, and CEDAR-MDI achieves up to $3.27\times$ the throughput of single-device inference, with detection quality preserved in both cases. ## DyRadio: Spatiotemporal Diffusion for Dynamic Radio Map Reconstruction DevFeed: [DyRadio: Spatiotemporal Diffusion for Dynamic Radio Map Reconstruction]() Original publisher: [Read original article]() Author: Zhijie Fan, Zhifeng Zhao, Rongpeng Li Published: 2026-11-03T05:00:00Z Content type: article Language: en Sources: [arXiv: Artificial Intelligence](), [arXiv: Machine Learning]() Topics: [Image processing](), [Neural Network]() Tags: [cs-ai](), [cs-lg](), [diffusion](), [map](), [measurement](), [model](), [networks](), [noise](), [prediction](), [radio](), [ratio](), [robustness](), [sampling](), [sequence](), [spatial](), [temporal](), [wireless]() ### AI overview DyRadio reconstructs consecutive radio maps from sparse, temporally distributed measurements while accounting for changing propagation conditions and unknown measurement noise. Its propagation-prior-guided, noise-conditioned spatiotemporal diffusion model captures dependencies across frames; an iterative predictive-likelihood procedure alternates between predicting unmeasured areas and updating the estimated noise level, which then conditions reconstruction of the full sequence. The abstract reports PSNR gains of 1.18-5.75 dB over the best-performing baseline across all evaluated settings, with improved robustness to measurement noise. ### Source excerpt arXiv:2611.01603v1 Announce Type: new Abstract: Accurate radio map (RM) reconstruction is essential for environment-aware wireless networks. Sampling-based methods, which infer radio conditions from sparse measurements, are widely adopted because they do not require explicit knowledge of transmitter configurations. However, in dynamic environments, time-varying propagation conditions cause RMs to evolve, complicating reconstruction from temporally distributed sparse observations. Although cross-frame observations provide complementary spatial information, their direct aggregation can introduce temporal state mismatch. Furthermore, unknown measurement noise adds to the reconstruction difficulties. To address these challenges, we propose DyRadio, a framework that integrates spatiotemporal RM reconstruction with unknown noise estimation. Specifically, a propagation-prior-guided, noise-conditioned spatiotemporal diffusion model (DM) jointly reconstructs consecutive RMs by capturing cross-frame dependencies, while adapting to measurement noise levels. To estimate the noise level, an iterative predictive likelihood method alternates between DM-based blind-area prediction and noise-level updates. The estimated noise level then conditions reconstruction of the complete RM sequence. Experimental results demonstrate superior reconstruction accuracy and robustness against measurement noise, with peak signal-to-noise ratio (PSNR) improvements of 1.18-5.75 dB over the best-performing baseline across all evaluated settings. ## Leaking secrets from air-gap computers by spelling radio signals from RAM DevFeed: [Leaking secrets from air-gap computers by spelling radio signals from RAM]() Original publisher: [Read original article]() Author: Anne Barela Published: 2026-11-02T20:45:05Z Content type: article Language: en Sources: [Adafruit Industries]() Topics: [Security](), [side channel](), [Cybersecurity](), [communications]() Tags: [air-gap](), [air-gapped](), [arxiv](), [computer](), [computers](), [data](), [electromagnetic-emissions](), [history](), [idea](), [industrial](), [machine](), [machines](), [memory](), [networks](), [one](), [paper](), [radio](), [ram](), [reverse-engineering](), [running](), [science](), [secrets](), [software](), [systems](), [vintage-computing]() ### AI overview The described attack turns RAM activity into a covert radio channel for removing data from an air-gapped computer. Software performs memory accesses in a controlled pattern; electromagnetic emissions from the memory bus form a signal that a nearby antenna can receive and decode, without a network connection, cable, or speaker. The excerpt says the 2024 arXiv paper covers the attack model, signal generation and modulation, data rates, distances, and defenses, but does not provide their specific details. ### Source excerpt Air-gapped computers are machines kept off networks on purpose, the way classified systems and industrial controls often are. A 2024 paper posted to arXiv describes a way to get data off one anyway, using the computer's own RAM as a radio transmitter. The idea: software running on the isolated machine reads and writes memory in [...] ## Static Radio For The Chumby One DevFeed: [Static Radio For The Chumby One]() Original publisher: [Read original article]() Author: Zoe Skyforest Published: 2026-11-02T12:00:22Z Content type: news Language: en Sources: [Hackaday]() Topics: [podcasting](), [pc]() Tags: [alsa](), [audio](), [buffer](), [c](), [chumby](), [client](), [cpu](), [decoder](), [digital-audio-hacks](), [firmware](), [fpu](), [hacks](), [internet-hacks](), [internet-radio](), [kernel](), [linux](), [mbedtls](), [mp3](), [native](), [openssl](), [podcast](), [radio](), [static-radio]() ### AI overview Brendan Fitzpatrick turned a 2009 Chumby One into a Static Radio player with a native C client that runs from USB without changing the original firmware. To work within its 454 MHz ARM9 CPU, 60 MB RAM and Linux 2.6.28 environment, the client bundles mbedTLS, fixed-point Helix MP3 decoding, HE-AAC and a polyphase resampler, sending audio through ALSA PCM. It buffers the selected station and two neighboring stations so dial changes can crossfade cleanly. ### Source excerpt If you haven't heard of Static Radio, it's basically an online radio station made up of podcast content. [Brendan Fitzpatrick] decided to take an old 2009 Chumby One and turn ...read more ## INLA for Adaptive UAV Sampling of Radio Environment Maps in IoT Networks: Prior Width Governs Accuracy and Calibration DevFeed: [INLA for Adaptive UAV Sampling of Radio Environment Maps in IoT Networks: Prior Width Governs Accuracy and Calibration]() Original publisher: [Read original article]() Author: Changhao He, Kaichuang Yang, Xiaojuan Zhang Published: 2026-11-02T05:00:00Z Content type: article Language: en Sources: [arXiv: Machine Learning]() Topics: [Machine learning]() Tags: [acquisition](), [adaptive](), [approximation](), [cells](), [construction](), [counts](), [coverage](), [cs-it](), [cs-lg](), [effect](), [entropy](), [environment](), [improvement](), [influence](), [iot](), [lookahead](), [lorawan](), [maps](), [math-it](), [model](), [networks](), [radio](), [sampling](), [stat-ml]() ### AI overview The study finds that prior shadowing-width choice has a substantial, corpus-dependent effect on radio-map accuracy and calibration, while differences among informative UAV sampling rules remain unresolved. It updates a Matérn GMRF posterior with INLA and selects reachable waypoints using entropy pre-screening and Sherman-Morrison lookahead; the likelihood-induced Skew-Normal correction has limited influence on selection. In 19 ray-traced windows, posterior-informed sampling reduced residual NMSE relative to random and lawnmower sampling. Widening the prior from 6.0 to 10.025 dB improved NMSE and interval coverage across a 4-16 dB sweep, but overconfidence persisted; estimating width online from UAV counts did not recover the gain. In 30 measured LoRaWAN windows paired with simulated counts and scored only on received cells, the adaptive-sampling margin reproduced, training-derived width gave the best tested interval score, and GP-UCB had nominally 3-5% lower NMSE. Results depend on corpus, scored cells, and model mismatch. ### Source excerpt arXiv:2610.40723v1 Announce Type: cross Abstract: We study adaptive UAV sampling for radio environment map (REM) construction from non-Gaussian IoT observations. Integrated nested Laplace approximation(INLA) updates a Mat\'ern GMRF posterior, with waypoints selected by entropy pre-screening and Sherman--Morrison lookahead over the reachable set. We show that the likelihood-induced Skew-Normal correction has a sextic entropy effect, explaining its limited influence on waypoint selection. Across 19 retained ray-traced windows,Random and lawnmower sampling cost a median 18.0\% and 14.0\% more residual NMSE than posterior-informed sampling, equivalently reductions of 15.3\% and 12.3\% when referred to those baselines, while differences among informative rules remain unresolved. Widening the prior shadowing standard deviation from 6.0 to 10.025\,dB improves NMSE and credible-interval coverage, with monotone improvement over a 4--16\,dB sweep on this corpus and no observed turning point, although overconfidence persists. Online width estimation from the UAV's own counts yields about 6.5\,dB without recovering the gain. Across 30 measured LoRaWAN propagation windows paired with simulated counts and scored only on received cells, the margin over non-adaptive sampling reproduces, the training-derived width minimizes the tested interval score, and GP-UCB has nominally $3$--$5\%$ lower NMSE. The results show substantial, corpus-dependent sensitivity to prior specification, while fine differences among acquisition rules have limited or unresolved effects, the preferred width depends on the corpus, scored cells and model mismatch. ## Bloatware in Aftermarket Auto Parts DevFeed: [Bloatware in Aftermarket Auto Parts]() Original publisher: [Read original article]() Author: Bruce Schneier Published: 2026-10-30T15:20:02Z Content type: news Language: en Sources: [Schneier on Security]() Topics: [Android Security](), [WebView](), [Web]() Tags: [adobe](), [ai](), [amazon](), [android](), [baidu](), [call](), [cars](), [claude](), [dab](), [internet-of-things](), [iot](), [pdfs](), [power](), [radio](), [reverse-engineering](), [smart-tv](), [software](), [spyware](), [system](), [uncategorized](), [voice-assistant](), [webview]() ### AI overview A Civic owner used Claude to examine a cheap Amazon aftermarket head unit and found several preinstalled apps: a voice assistant using Android WebView, Baidu location services, a call recorder, a DAB radio client, and Adobe Acrobat. The voice assistant reportedly consumed about a third of the device's processing power even while idle. The excerpt presents this as an example of software and security concerns in aftermarket automotive electronics, and notes that AI helped an individual reverse-engineer the device. ### Source excerpt This story is interesting: One Civic owner purchased a cheap aftermarket head unit off Amazon, and decided to have Claude work its magic on it, like it would a smart TV. What was reportedly discovered isn't surprising, but is worth knowing about. Among the pre-installed bloatware--or spyware, if you're being less charitable--was a voice assistant equipped with WebView, an Android system component that lets apps display content off the web. This apparently always used about a third of processing power, even while idle, which isn't great. There were also Baidu location services, a call recorder (!), a DAB radio client that is pretty much useless in the U.S., and Adobe Acrobat, presumably so your passenger can entertain themselves with PDFs on the go... ## Who Called? V33DA: A Physically Verified Multimodal Benchmark for Vocal Attribution in Zebra Finch Groups DevFeed: [Who Called? V33DA: A Physically Verified Multimodal Benchmark for Vocal Attribution in Zebra Finch Groups]() Original publisher: [Read original article]() Author: Maris Basha, Yuhang Wang, Xiaoran Chen, Longbiao Cheng, Luca Yapura, Anja T. Zai, Mathieu Salzmann, Richard Hahnloser Published: 2026-10-30T04:00:00Z Content type: article Language: en Sources: [arXiv: Machine Learning]() Topics: [Benchmark](), [Ground truth / benchmark quality](), [Transformers]() Tags: [3d](), [accelerometer](), [audio](), [benchmark](), [birds](), [call](), [camera](), [candidate](), [code](), [communication](), [cs-cv](), [cs-lg](), [cs-sd](), [evaluation](), [events](), [experiment](), [groups](), [identity](), [models](), [multimodal](), [q-bio-qm](), [radio](), [spatial](), [spatial-reasoning]() ### AI overview V33DA is a benchmark for identifying which visible zebra finch produced a detected vocalization, with physically verified caller labels from an on-body accelerometer signal withheld from benchmark models. It contains 33,625 events combining five-channel audio, three camera views, calibrated 3D poses, and radio telemetry for 10 birds across three experiments. Evaluations cover held-out dates, transfer to a new cohort, and a bird excluded from training. The abstract reports that methods relying on familiar vocal identity lose accuracy on unseen individuals, while candidate-aware methods that preserve spatial reasoning transfer better; the accelerometer-based reference remains near-perfect. V33DA++ provides verified overlapping-call events and surrounding context, but is unevaluated. ### Source excerpt arXiv:2610.38109v1 Announce Type: cross Abstract: Deciding which member of an animal group produced a vocalization and where that vocalization was produced are central to studying social communication but are rarely evaluated with physically verified ground truth. Existing resources either localize sounds without identifying the caller, or recognize individuals from isolated vocalizations without reliance on the 3D candidate geometry. We close this gap with V33DA, a dataset-centered multimodal benchmark for spatial vocal attribution in social zebra finches: it comprises 33,625 verified events coupling 5-channel audio with three camera views, calibrated 3D pose for every visible candidate, and per-bird radio telemetry across 10 individuals and three experiments. Caller identity is verified from an on-body accelerometer-derived vibration signal; this channel is withheld from benchmark models and used only by an on-body reference ceiling. Given a detected vocalization and the visible candidate birds, the task is to select the caller. We evaluate it under three regimes: session-disjoint testing on familiar birds from held-out recording dates, held-out-experiment transfer to a new cohort, and leave-one-individual-out evaluation on a bird whose vocalizations are held out from training. Reference methods expose a consistent gap between in-domain accuracy and transfer to unseen individuals: methods that can exploit familiar vocal identity perform well on known callers but degrade sharply on unseen ones, whereas candidate-aware methods preserving explicit spatial reasoning transfer substantially better. The on-body reference stays near-perfect across regimes, confirming the internal consistency of the accelerometer-verified labels. We release V33DA with fixed protocols and code for the evaluated methods, and V33DA++, an unevaluated companion set of verified overlapping-call events and +/-2 s context windows. ## Self-Supervised Doppler-Guided RF Odometry DevFeed: [Self-Supervised Doppler-Guided RF Odometry]() Original publisher: [Read original article]() Author: Kunzhe Song, Jialuo Du, Jingkai Lin, Huacheng Zeng Published: 2026-10-30T04:00:00Z Content type: article Language: en Sources: [arXiv: Machine Learning]() Topics: [Physical AI](), [autonomous vehicles]() Tags: [consistency](), [cs-lg](), [cs-ro](), [doppler](), [graph](), [motion](), [moving](), [radio](), [range](), [rf](), [robot](), [robotics](), [robust](), [sensing](), [sensor](), [sensors](), [sequences](), [static](), [temporal](), [velocity]() ### AI overview RFWalk estimates robot motion using RF data alone, without pose labels or auxiliary sensors. It learns dense correspondences between range-azimuth frames from unlabeled sequences using temporal cycle consistency, then applies a Doppler consistency loss based on the sensor's radial velocity to reject physically implausible matches. Robust SE(2) registration suppresses uncertain matches and those from independently moving objects. The abstract reports competitiveness with supervised baselines in static scenes and 58% lower absolute trajectory error in dynamic scenes with moving pedestrians. ### Source excerpt arXiv:2610.39005v1 Announce Type: cross Abstract: Radio-frequency (RF) sensing enables robot ego-motion estimation in darkness, smoke, and fog, yet RF odometry remains challenging because multipath and moving reflectors make cross-frame matching highly ambiguous. Existing methods often rely on auxiliary inertial sensors or ground-truth pose supervision. We present RFWalk, a self-supervised, RF-only odometry framework that models dense correspondences across range-azimuth frames as random walks on a space-time graph and learns them from unlabeled sequences through temporal cycle consistency. To rule out correspondences that are cycle-consistent but physically implausible, we introduce a Doppler consistency loss that constrains correspondence-induced motion using radial velocity measured by the RF sensor itself. Ego-motion is then recovered through robust $\mathrm{SE}(2)$ registration that suppresses uncertain correspondences and those arising from independently moving objects. Without pose labels or auxiliary sensors, RFWalk remains competitive with supervised baselines in static scenes and reduces absolute trajectory error by 58% in dynamic scenes with moving pedestrians. ## Learning Graph Beliefs for Active Radio Mapping With Decision-Certified Multi-Step Sensing DevFeed: [Learning Graph Beliefs for Active Radio Mapping With Decision-Certified Multi-Step Sensing]() Original publisher: [Read original article]() Author: Wangqian Chen, Hao Wang, Yumeng Zhang, Chenghong Bian, Junting Chen, Jun Zhang Published: 2026-10-30T04:00:00Z Content type: article Language: en Sources: [arXiv: Machine Learning](), [arXiv: Networking]() Topics: [AI Networking](), [Artificial Intelligence](), [Neural Network](), [Operations research and optimization]() Tags: [acquisition](), [bayes](), [bayesian](), [bayesian-inference](), [construction](), [correlation](), [cs-lg](), [cs-ni](), [evaluation](), [experiments](), [framework](), [full](), [gap](), [graph](), [inference](), [information](), [knowledge](), [learning](), [map](), [mapping](), [radio](), [sensing]() ### AI overview GraphBARC builds a joint radio-map belief from acquired measurements using a graph network that learns correlated node and edge factors; analytical Bayesian updates then incorporate new observations without retraining. It plans multi-step sensing routes by evaluating map-wide Bayes risk reduction and accounting for redundancy between measurements. To control planning cost, residual-based bounds compare route values, an error-aware continuation bound screens weak route prefixes, and only responses needed for unresolved comparisons are refined; certified exclusions remain valid during refinement. In the reported experiments, GraphBARC reduced mean RMSE by over 16% relative to evaluated baselines and core planning time by 56% versus a fixed-accuracy, unpruned implementation. ### Source excerpt arXiv:2610.37717v1 Announce Type: new Abstract: Radio maps provide essential wireless propagation knowledge for network optimization and autonomous platforms. Acquiring dense measurements, however, is prohibitively costly, requiring active sampling to prioritize informative measurements. Existing active sampling methods typically rely on variances from prescribed spatial models or learned pointwise uncertainty, which may not fully capture the spatial correlation of different measurements. This paper proposes GraphBARC, a graph-structured active radio map construction framework that integrates learned spatial modeling with analytical Bayesian inference. A graph network learns correlated node and edge factors using only acquired measurements, inducing a joint full-map belief that supports analytical observation updates without retraining. Rather than immediate one-step acquisition, it adopts a nonmyopic sensing strategy that evaluates joint map-wide Bayes risk reduction over feasible multi-step routes, accounting for information redundancy among planned measurements. We reuse candidate responses and derive residual-based bounds directly on route-value differences, retaining shared response-error structure to avoid uniformly high-accuracy evaluation. An error-aware continuation bound screens unpromising prefixes, after which only responses needed for unresolved comparisons are refined. We further establish a computable decision-gap bound and show that certified exclusions remain valid during refinement. Experiments show that GraphBARC reduces mean root-mean-square error (RMSE) by over 16% relative to the evaluated baselines and core planning time by 56% compared with the fixed-accuracy, unpruned implementation. ## Encrypted IoT networking via RF24Gateway with nRF24, nRF52x and nRF54x. Coming soon DevFeed: [Encrypted IoT networking via RF24Gateway with nRF24, nRF52x and nRF54x. Coming soon]() Original publisher: [Read original article]() Author: Anne Barela Published: 2026-10-28T20:49:22Z Content type: news Language: en Sources: [Adafruit Industries]() Topics: [Cryptography]() Tags: [adapters](), [aes](), [arduino](), [bluetooth](), [communication](), [encrypted](), [encryption](), [ethernet](), [forum](), [gateway](), [github](), [gpio](), [http](), [iot](), [ip](), [library](), [networking](), [nordic](), [nrf52](), [nrf54](), [protocol](), [radio](), [radio-communication](), [raspberry-pi](), [rf24gateway](), [seeed-studio](), [software](), [xiao]() ### AI overview RF24Gateway is being updated to enable encrypted networking across nRF24, nRF52x, and nRF54x devices. The underlying nrf_to_nrf library provides direct radio communication using Enhanced ShockBurst (ESB), without Bluetooth or Zigbee; its AES/CCM encryption is now enabled for nRF52x and nRF54x. RF24Gateway is intended to let these devices carry TCP/IP and UDP, supporting protocols such as MQTT and HTTP. It requires a Linux host with GPIO and SPI, such as a Raspberry Pi. The code and pull requests are in place, and the author expected a full release within a day or two. ### Source excerpt TMRh20Projects posted on the Seeed Studio forum about adding encryption to RF24Gateway. The work builds on nrf_to_nrf, a library for direct radio communication on XIAO nRF52840 and nRF54L15 boards. It does not use Bluetooth or Zigbee. It uses the Enhanced ShockBurst (ESB) protocol and direct radio access. The library already included AES/CCM encryption, and that [...] ## Hacking a marine radio dish DevFeed: [Hacking a marine radio dish]() Original publisher: [Read original article]() Author: Anne Barela Published: 2026-10-28T16:22:39Z Content type: article Language: en Sources: [Adafruit Industries]() Topics: [Hacking]() Tags: [antenna](), [control](), [dish](), [ethernet](), [hacking](), [marine](), [motors](), [radio](), [reverse-engineering](), [rp2040](), [satellite](), [satellite-dish](), [stepper](), [vintage-computing](), [wifi]() ### AI overview A used Intellian i4 marine satellite dish was made to operate on a roof without a boat by feeding its Antenna Control Unit simulated NMEA data. An RP2040 and TTL-to-RS-422 module supplied the sentences; Aptus software traffic and decompiled C# code revealed a text protocol with a simple checksum. Pointing commands use GO followed by azimuth and elevation as integers with two implicit decimal places. The dish's motorised sub-reflector, Intellian's Dynamic Beam Tilting, handles small wave corrections while the main motors make larger adjustments. The setup locked onto Astra 1P at 19.2°E. The excerpt also identifies the ACU's Ethernet, WiFi and RS-232 interfaces and its built-in GPS. ### Source excerpt melanpan.nl picked up a used Intellian i4 marine satellite dish on Marktplaats for about EUR 200, against a new price near EUR 4000. The dish uses stepper motors, a quad LNB, and an indoor Antenna Control Unit with Ethernet, WiFi and RS-232. The ACU expects a boat to tell it where it is and which way it [...] ## A new lightweight, hybrid routing mesh protocol for packet radios DevFeed: [A new lightweight, hybrid routing mesh protocol for packet radios]() Original publisher: [Read original article]() Author: Anne Barela Published: 2026-10-28T15:07:08Z Content type: news Language: en Sources: [Adafruit Industries]() Topics: [mesh networking](), [meshtastic]() Tags: [bluetooth](), [c-plus-plus](), [devices](), [distributed-mesh-network](), [embedded](), [github](), [hybrid](), [internet](), [library](), [lightweight](), [lora](), [mesh](), [meshcore](), [meshtastic](), [messages](), [packet](), [protocol](), [radio](), [range](), [raspberry-pi](), [relay](), [reticulum](), [routing](), [software](), [video]() ### AI overview MeshCore is a lightweight C++ library for multi-hop routing over LoRa and other packet radios: nodes relay messages so devices can communicate beyond a single radio link without internet access. The excerpt positions it between Meshtastic's casual LoRa messaging and Reticulum's deeper networking features, with custom embedded projects and off-grid or emergency use as its focus. Prebuilt binaries are available for supported devices. Setup options described include flashing with tools such as Adafruit ESPTool, reaching the network through a serial console, and companion firmware connections over BLE, USB, or Wi-Fi depending on the build. Repeater and room server firmware can be configured over USB in a web tool or remotely over LoRa from the mobile app. ### Source excerpt Seeed Studio has posted MeshCore on GitHub, a lightweight C++ library that handles multi-hop packet routing for embedded projects using LoRa and other packet radios. Nodes relay messages through each other, so devices can reach far past the range of a single radio link without any internet connection. MeshCore sits between Meshtastic and Reticulum. Meshtastic [...] ## Hacking a Marine Radio Dish DevFeed: [Hacking a Marine Radio Dish]() Original publisher: [Read original article]() Author: Zoe Skyforest Published: 2026-10-28T05:00:31Z Content type: news Language: en Sources: [Hackaday]() Topics: [Hacking]() Tags: [hacking](), [nmea](), [radio](), [radio-hacks](), [satellite](), [satellite-dish]() ### AI overview Melan repurposed an Intellian i4 marine satellite dish for land use by using an RP2040 and RS-422 module to send NMEA sentences that supplied the boat heading the antenna expected. After getting the manufacturer's software running with help from the company, she explored software-free control by sniffing communications to the Antenna Control Unit and decompiling the code. This let her describe the protocol and point the antenna with azimuth and elevation commands. ### Source excerpt Having watched some fun videos on repurposed satellite dishes on YouTube, [Melan] wanted to get in on the action. She managed to source herself an Intellian i4, a dish built ...read more ## Adaptive Calibration of RF Digital Twins via Budget-Constrained Radio Measurement Selection DevFeed: [Adaptive Calibration of RF Digital Twins via Budget-Constrained Radio Measurement Selection]() Original publisher: [Read original article]() Author: Yalin E. Sagduyu, Tugba Erpek, Hossein Jafari Published: 2026-10-28T04:00:00Z Content type: article Language: en Sources: [arXiv: Networking]() Topics: [communications](), [3D modeling]() Tags: [3d-modeling](), [adaptive](), [blender](), [budget](), [cs-ni](), [digital-twins](), [eess-sp](), [measurement](), [monte-carlo](), [online](), [openstreetmap](), [physics](), [pipeline](), [radio](), [ray-tracing](), [rf](), [sampling](), [select](), [selection](), [strategies](), [uncertainty]() ### AI overview The study finds that adaptive and structure-aware selection of radio measurement locations improves mean and worst-case RF digital twin calibration accuracy, especially with small measurement budgets. It builds a physics-based pipeline from OpenStreetMap geospatial data, Blender 3D models, and Sionna deterministic ray tracing, then calibrates its path-loss predictions against software-defined radio measurements. Locations are selected online to estimate a calibration offset. Compared approaches include random sampling, rank-structured sampling with balanced coverage, quasi-Monte Carlo ranked selection, progressive structure-aware allocation, and adaptive uncertainty-driven sampling with estimator stabilization. The supplied abstract does not provide quantitative results. ### Source excerpt arXiv:2610.36406v1 Announce Type: new Abstract: Radio-frequency (RF) digital twins (DTs) enable site-specific wireless propagation prediction by explicitly reconstructing the physical environment and modeling electromagnetic interactions. Although physics-based DTs reduce reliance on exhaustive measurements, systematic bias relative to real radio data arises from environmental uncertainty, material inaccuracies, and geometric abstractions. Calibration using field measurements is therefore necessary but costly under limited sampling budgets. This paper studies active RF DT calibration, in which measurement locations are selected sequentially and in an online manner to estimate a calibration offset under strict measurement budget constraints. A physics-based RF DT pipeline is developed, integrating semantic geospatial data from OpenStreetMap, 3D modeling in Blender, and deterministic ray tracing in Sionna to capture dominant building and foliage effects. This RF DT is calibrated using path-loss measurements collected with software-defined radios. Multiple online calibration strategies that select radio measurement locations are compared, including random sampling, rank-structured sampling with balanced coverage, quasi-Monte Carlo ranked selection, progressive structure-aware allocation, and fully adaptive uncertainty-driven sampling with estimator stabilization. Results demonstrate that adaptive and structure-aware schemes significantly improve both mean and worst-case calibration accuracy, particularly in the low-budget regime for radio measurements. [Next page]()