Timely and accurate detection of oestrus in cows is an essential element of the good management of dairy farms. At present, the detection of cows in oestrus by acoustic means is impeded by the problems of filtering, incomplete feature selection, and poor recognition accuracy. To overcome these difficulties, this study proposes a sound detection method for cows in oestrus based on machine learning technology using an optimal feature combination and an optimal time window. Firstly, a dual-channel sound detection tag consisting of a unidirectional microphone and an omnidirectional microphone (OM) was developed. The Least Mean Squares adaptive algorithm based on wavelet thresholds was used to filter the signals from the OM, and the dual-channel endpoint detection algorithm was used to identify the lowing of individual cows. The Friedman analysis was then used to select the sound features with significant differences before and after oestrus in terms of time, frequency, and cepstrum, and these were used to determine the most acceptable feature combination. We then analysed the effects of Back Propagation Neural Network (BPNN), Cartesian Regression Tree, Support Vector Machine, and Random Forest classification on the accuracy, precision, sensitivity, specificity, and F1 score of oestrus discrimination. Different time windows were used, and the discrimination performance of these algorithms was evaluated using the Area under Receiver Operating Characteristic Curve to find the most satisfactory match between the time window and the recognition algorithm. The dual-channel acoustic tag's accuracy, precision, sensitivity, and specificity results were 91.25, 98.83, 91.75, and 83.68%, respectively. BPNN with the 70 ms time window and the feature combination (spectral roll-off + spectral flatness + Mel-Frequency Cepstrum Coefficients) was confirmed as the most suitable oestrus recognition method. The average accuracy, precision, sensitivity, specificity, and F1 score of this method were 97.62, 98.07, 97.17, 97.19, and 97.63%, respectively. Based on these results, the approach was shown to be a feasible means of oestrus detection in dairy cows. Based on its ability to differentiate cows and its consistency, it was demonstrated that sound has the potential to replace accelerometers as an early indicator of oestrus in dairy cows.

Introduction: Scalp electroencephalography (EEG) is commonly used to assist in epilepsy detection. Even automated detection algorithms are already available to assist clinicians in reviewing EEG data, many algorithms used for seizure detection in epilepsy fail to account for the contributions of different channels. The Fully Convolutional Network (FCN) can provide the model’s interpretability but has not been applied in seizure detection.Methods: To address these challenges, a novel convolutional neural network (CNN) model, combining SE (Squeeze-and-Excitation) modules, was proposed on top of the FCN. The epilepsy detection performance for patient-independent was evaluated on the CHB-MIT dataset. Then, the SE module was removed from the model and integrated the model with Inception, ResNet, and CBAM modules separately.Results: The method showed superior advancement, stability, and reliability compared to the other three methods. The method demonstrated a G-Mean of 82.7% for sensitivity (SEN) and specificity (SPE) on the CHB-MIT dataset. In addition, The contributions of each channel to the seizure detection task have also been quantified, which led us to find that the FZ, CZ, PZ, FT9, FT10, and T8 brain regions have a more pronounced impact on epileptic seizures.Discussion: This article presents a novel algorithm for epilepsy detection that accurately identifies seizures in different patients and enhances the model’s interpretability.

Melanoma is a fatal skin cancer that can be treated efficiently with early detection. There is a pressing need for dependable computer-aided diagnosis (CAD) systems to address this concern effectively. In this work, a melanoma identification method with feature interpretation was designed. The method included preprocessing, feature extraction, feature ranking, and classification. Initially, image quality was improved through preprocessing and k-means segmentation was used to identify the lesion area. The texture, color, and shape features of this region were then extracted. These features were further refined through feature recursive elimination (RFE) to optimize them for the classifiers. The classifiers, including support vector machine (SVM) with four kernels, logistic regression (LR), and Gaussian naive Bayes (GaussianNB) were applied. Additionally, cross-validation and 100 randomized experiments were designed to guarantee the generalization of the model. The experiments generated explainable feature importance rankings, and importantly, the model demonstrated robust performance across diverse datasets.

Alzheimer’s disease (AD) is characterized by pronounced spatial heterogeneity and complex neurodegenerative patterns, which pose significant challenges for representation learning on three-dimensional brain images. Conventional convolutional neural networks relying on regular grid sampling struggle to align localized structural degeneration, and their performance is further compromised by class imbalance and a high proportion of weakly discriminative samples, leading to suboptimal optimization dynamics and reduced generalization ability. To address the aforementioned challenges, this study proposes Deformable Attention and Risk-aware 3D Network (DAR-3DNet), a modeling framework for 3D magnetic resonance imaging (MRI) classification. The proposed method incorporates deformable sampling and sampling-point modulation into spatial attention generation, enabling the attention estimation process to better adapt to the non-rigid spatial patterns associated with brain structural degeneration. On this basis, an instance-adaptive label smoothing loss with composite risk, termed Instance-wise Adaptive Label Smoothing Loss with Composite Risk (IASLCR), is further introduced to dynamically adjust supervision strength based on sample-specific risk, thereby alleviating optimization bias caused by class imbalance and weakly discriminative samples. Experiments conducted on 1749 structural MRI scans from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset show that the proposed method achieves accuracy values above 0.93 on the AD vs. normal control (NC), mild cognitive impairment (MCI) vs. NC, and AD vs. MCI classification tasks, while yielding better overall performance than the evaluated baseline models. These results suggest that the proposed framework has considerable potential for structural MRI-based AD/MCI classification.