AI & ML
RespCCT and FreqCCT: Compact, Explainable and Cost-Aware Convolutional Transformers for Multi-Class Respiratory Disease Classification
arXiv cs.SD0 views
arXiv:2611.24323v1 Announce Type: new Abstract: Chest auscultation depends on the listener, and software that classifies lung sounds could give a second reading where trained listeners are scarce. The most accurate published classifiers fine-tune large pretrained networks, and their accuracy is rarely reported with running cost or paired statistics. This study makes three contributions. (i) It proposes RespCCT and FreqCCT, two compact convolutional transformers of 173,187 and 124,999 parameters that learn from random initialization on mel, constant-Q and cepstral images of 5 s frames from three public databases, ICBHI, KAUH and RD@TR, with 1,665 audio files in seven classes. (ii) It compares both models with five ImageNet-pretrained networks and larger distilled variants on one test set, using paired bootstrap intervals. (iii) It measures the cost of every pipeline stage on one CPU thread, tests whether attribution maps depend on the trained weights, and probes whether the learned features reveal the recording source. On the test fold, RespCCT reaches an accuracy of 98.13% and a macro F1 of 0.970, and FreqCCT reaches 97.58% and 0.951. Over five folds, RespCCT with three seeds reaches 97.65% and 0.959, and FreqCCT with one seed reaches 96.95% and 0.941. The two strongest pretrained networks reach a macro F1 of 0.984, whereas RespCCT needs 2.0 to 64.6 times less weight storage. Computing the three input images takes longer than running either model, and a linear probe identifies the source database with 0.958 accuracy. A team can weigh accuracy against storage and time before device testing.
Source:https://arxiv.org/abs/2611.24323PreviousConstructing Dynamic Conversations with Neural Back-channel Generation and Voice-line SchedulingNextHarmonic Circuit: Chord Progression Lies in a Sparse Principal Information Flow in Symbolic Music Models
Related posts

iOS 27 gave AirPods Pro a convenient new setting, here’s how to use it
09to5Mac
![Motorola’s iPhone Duo competitor, Razr Flex, leaks in detailed images [Gallery]](https://9to5google.com/wp-content/uploads/sites/4/2026/11/motorola-razr-flex-leak-sg-1.jpg?quality=82&strip=all&w=1600)
Motorola’s iPhone Duo competitor, Razr Flex, leaks in detailed images [Gallery]
09to5Google

AI features could be turned off with a simple toggle, Canva proves
09to5Google
Manuj Mittal on Why “Most Tokens Aren’t Securities” Leaves Crypto With More Questions Than Answers
0HackerNoon
I Found My Own Website Blocking ChatGPT. Then I Checked 640 Others.
0HackerNoon

Small Language Models, Not Giant LLMs, Should Power the Next Generation of AI Agents
0HackerNoon