EmoNet speech-emotion CNN reports 96.75% accuracy with 4.11M parameters
The model classifies seven emotions on combined TESS, RAVDESS and SAVEE data using a separable CNN and BiLSTM.
Stories per day · 30 days
3 RSS
Relatedagriculture1bilstm1computer-vision1emonet1ethiopia1mobilenetv21plantvillage1potato1specaugment1speech-emotion-recognition1
8 stories, newest first · one card per story
Stories tagged #cnn
Detection of Potato Plant Leaf Diseases using Convolutional Neural Networks
A 1.7 MB CNN classifies potato leaf blight, reaching 98.66% on PlantVillage and 90.28% in Ethiopian fields.
Systematically Optimized CNN-Transformer with Focal Loss for Imbalanced Intrusion Detection on NSL-KDD
A tuned CNN-Transformer with Focal Loss reaches 98.73% accuracy on imbalanced NSL-KDD detection.
Extracting CNNs in the Unknown-Architecture and Feedback-Agnostic Setting
Researchers show black-box attacks can recover a CNN's unknown architecture and its parameters.
Calibrated RF-Fingerprinting Under Interference With Heterogeneous Transmission Protocols
Researchers propose a calibrated multi-label 1D-CNN RF-fingerprinting method that identifies overlapping Wi-Fi, LTE, and 5G transmitters despite co-channel interference.
Delphi Scanner: efficient and interpretable static malware detection via API sequence modeling
Researchers introduce Delphi Scanner, a 1.53 MB CNN-based static malware detector for Windows PE files using API sequences, achieving 95.35% accuracy.
On Identifying Adversarial Intent Injection in AI-Native 6G Networks
Dual-path CNN and AutoEncoder framework detects adversarial intent injection in AI-native 6G networks, reaching 0.97 accuracy and 0.98 F1.
Understanding the Impact of Model Pruning on Long-Tail Forgetting and Explanation Reliability in Medical Imaging
Systematic study finds model pruning causes frequency-dependent long-tail forgetting in medical imaging and that gradient-informed methods best preserve explanations.