Multivariate time series forecasts are widely used, such as industrial, transportation and financial forecasts. However, the dominant frequencies in time series may shift with the evolving spectral distribution of the data. Traditional Mixture of Experts (MoE) models, which employ a fixed number of experts, struggle to adapt to these changes, resulting in frequency coverage imbalance issue. Specifically, too few experts can lead to the overlooking of critical information, while too many can introduce noise. To this end, we propose Ada-MoGE, an adaptive Gaussian Mixture of Experts model. Ada-MoGE integrates spectral intensity and frequency response to adaptively determine the number of experts, ensuring alignment with the input data's frequency distribution. This approach prevents both information loss due to an insufficient number of experts and noise contamination from an excess of experts. Additionally, to prevent noise introduction from direct band truncation, we employ Gaussian band-pass filtering to smoothly decompose the frequency domain features, further optimizing the feature representation. The experimental results show that our model achieves state-of-the-art performance on six public benchmarks with only 0.2 million parameters.

Universit e Jean Monnet Saint-Etienne, T elecom Saint-Etienne, F-42023 Saint-Etienne, France Email: {firstname.surname}@univ-st-etienne.fr Abstract--Quality of Experience (QoE) modeling is crucial for optimizing video streaming services to capture the complex relationships between different features and user experience. We propose a novel approach to QoE modeling in video streaming applications using interpretable Machine Learning (ML) techniques over raw time series data. Unlike traditional black-box approaches, our method combines Kolmogorov-Arnold Networks (KANs) as an interpretable readout on top of compact frequency-domain features, allowing us to capture temporal information while retaining a transparent and explainable model. We evaluate our method on popular datasets and demonstrate its enhanced accuracy in QoE prediction, while offering transparency and interpretability. Quality of Experience (QoE) is a crucial aspect in today's digital landscape, as it directly affects how users perceive and interact with applications and services. Defined as'the overall acceptability of an application or service, as perceived subjectively by the end user' [1], QoE is a complex and multifaceted concept that cannot be solely defined by traditional Quality of Service (QoS) metrics such as bandwidth, delay, or jitter. In the context of video streaming, for instance, perceptual quality is a critical component of QoE.

Effective deepfake detection tools are becoming increasingly essential over the last few years due to the growing usage of deepfakes in unethical practices. There exists a diverse range of deepfake generation techniques, which makes it challenging to develop an accurate universal detection mechanism. The 2025 Signal Processing Cup (DFWild-Cup competition) provided a diverse dataset of deepfake images, which are generated from multiple deepfake image generators, for training machine learning model(s) to emphasize the generalization of deepfake detection. To this end, we proposed an ensemble-based approach that employs three different neural network architectures: a ResNet-34-based architecture, a data-efficient image transformer (DeiT), and an XceptionNet with Wavelet Transform to capture both local and global features of deepfakes. We visualize the specific regions that these models focus for classification using Grad-CAM, and empirically demonstrate the effectiveness of these models in grouping real and fake images into cohesive clusters using t-SNE plots. Individually, the ResNet-34 architecture has achieved 88.9% accuracy, whereas the Xception network and the DeiT architecture have achieved 87.76% and 89.32% accuracy, respectively. With these networks, our weighted ensemble model achieves an excellent accuracy of 93.23% on the validation dataset of the SP Cup 2025 competition. Finally, the confusion matrix and an Area Under the ROC curve of 97.44% further confirm the stability of our proposed method.

However, magnetometer data often suffer from disturbances caused by satellite dynamics, onboard instrument interference, and environmental noise. For instance, changes in satellite orientation can lead to anomalies in magnetic field measurements due to interference from electric currents within the satellite's instruments. These disturbances necessitate careful data correction to ensure the accuracy and reliability of measurements. Traditional correction methods rely heavily on human expertise and are rooted in well established physical and mathematical principles. While these methods have proven effective, they are inherently limited by their long processing times and delays in real time prediction [7] [6] [4] [2] [1]. In contrast, machine learning models, though rarely applied in this field, offer strong predictive capabilities and the potential for faster computations. This study seeks to address these limitations by combining the strengths of traditional correction methods with the adaptability and efficiency of machine learning models, thereby improving timeliness while ensuring both physical consistency and improved real time performance. This study bridges the gap between data driven models and physics based understanding by integrating Maxwell's equations into the neural network architecture as physical information. The key innovations are: 1 arXiv:2501.00020v3

Animal vocalisations are associated with different animal responses and can be used as useful indicators of the state of animal welfare. They are information about animal behavior allowing to determine the needs of the animals, providing personalized and optimal attention for the benefit of the production (Banhazi and Black, 2009; Bardeli et al, 2010). There are two types of poultry farming which coexist: traditional poultry farming and modern poultry farming which is recent and is gaining more and more importance. Unlike traditional poultry farming, which is less demanding, the establishment of modern poultry farming is subject to investment no less negligible and, requires rigorous conduct. Well conducted, modern poultry farming constitutes a source of unquestionable fortune for Poultry Farmers. Indeed, with the increase in demand for poultry products in the market and the presence of other factors such as consumers demanding more transparency in reporting on the welfare, environmental impact and safety of poultry products, it is essential to think on a rationalization in the treatment of animals.

Upper limb movement classification, which maps input signals to the target activities, is a key building block in the control of rehabilitative robotics. Classifiers are trained for the rehabilitative system to comprehend the desires of the patient whose upper limbs do not function properly. Electromyography (EMG) signals and Electroencephalography (EEG) signals are used widely for upper limb movement classification. By analysing the classification results of the real-time EEG and EMG signals, the system can understand the intention of the user and predict the events that one would like to carry out. Accordingly, it will provide external help to the user. However, the noise in the real-time EEG and EMG data collection process contaminates the effectiveness of the data, which undermines classification performance. Moreover, not all patients process strong EMG signals due to muscle damage and neuromuscular disorder. To address these issues, this paper explores different feature extraction techniques and machine learning and deep learning models for EEG and EMG signals classification and proposes a novel decision-level multisensor fusion technique to integrate EEG signals with EMG signals. This system retrieves effective information from both sources to understand and predict the desire of the user, and thus aid. By testing out the proposed technique on a publicly available WAY-EEG-GAL dataset, which contains EEG and EMG signals that were recorded simultaneously, we manage to conclude the feasibility and effectiveness of the novel system.

Freezing of gait (FoG) is a common gait disability in Parkinson's disease, that usually appears in its advanced stage. Freeze episodes are associated with falls, injuries, and psychological consequences, negatively affecting the patients' quality of life. For detecting FoG episodes automatically, a highly accurate detection method is necessary. This paper presents an approach for detecting FoG episodes utilizing a deep recurrent neural network (RNN) on 3D-accelerometer measurements. We investigate suitable features and feature combinations extracted from the sensors' time series data. Specifically, for detecting FoG episodes, we apply a deep RNN with Long Short-Term Memory cells. In our experiments, we perform both user dependent and user independent experiments, to detect freeze episodes. Our experimental results show that the frequency domain features extracted from the trunk sensor are the most informative feature group in the subject independent method, achieving an average AUC score of 93%, Specificity of 90% and Sensitivity of 81%. Moreover, frequency and statistical features of all the sensors are identified as the best single input for the subject dependent method, achieving an average AUC score of 97%, Specificity of 96% and Sensitivity of 87%. Overall, in a comparison to state-of-the-art approaches from literature as baseline methods, our proposed approach outperforms these significantly.

Classifying limb movements using brain activity is an important task in Brain-computer Interfaces (BCI) that has been successfully used in multiple application domains, ranging from human-computer interaction to medical and biomedical applications. This paper proposes a novel solution for classification of left/right hand movement by exploiting a Long Short-Term Memory (LSTM) network with attention mechanism to learn from sequential data available in the electroencephalogram (EEG) signals. In this context, a wide range of time and frequency domain features are first extracted from the EEG signal and are then evaluated using a Random Forest (RF) to select the most important features. The selected features are arranged as a spatio-temporal sequence to feed the LSTM network, learning from the sequential data to perform the classification task. We conduct extensive experiments with the EEG motor movement/imagery database and show that our proposed solution achieves effective results outperforming baseline methods and the state-of-the-art in both intra-subject and cross-subject evaluation schemes. Moreover, we utilize the proposed framework to analyze the information as received by the sensors and monitor the activated regions of the brain by tracking EEG topography throughout the experiments.