Real-Time Sign Language to text Translation using Deep Learning: A Comparative study of LSTM and 3D CNN

Manufacturing is undergoing a significant transformation as artificial intelligence (AI) enhances existing technologies such as digital twins, cloud computing, edge computing, and the industrial internet of things (IIoT). This shift allows factory operations teams to move from reactive problem-solving to proactive optimization across systems, improving efficiency and productivity.

The article discusses advancements in probabilistic forecasting, emphasizing the limitations of point predictions in capturing sudden changes in time series data. It introduces a novel approach using Deep Lattice Networks (DLN) to forecast non-parametric cumulative distribution functions (CDFs). This method aims to enhance the accuracy of forecasts by allowing for implicit quantile regression, addressing the historical reliance on parametric models in CDF forecasting.

Monitoring the spatiotemporal dynamics of forest CO2 uptake, known as Gross Primary Production (GPP), poses significant challenges in terrestrial ecosystem research. While Eddy Covariance towers provide high-frequency estimates, their spatial limitations hinder large-scale assessments. Remote sensing offers a scalable alternative, yet many methods rely on single-sensor spectral indices and statistical models that struggle to capture GPP's complex temporal dynamics. This study evaluates the performance of GPT-2, a transformer model, against LSTM, a recurrent neural network, for GPP prediction u…

The article introduces RoCoISLR, a new corpus for Romanian Isolated Sign Language Recognition, addressing the lack of large-scale datasets for this language. Comprising over 9,000 video samples and nearly 6,000 standardized glosses, RoCoISLR aims to enhance automatic sign language recognition, which is vital for communication between deaf and hearing individuals. The study evaluates seven advanced video recognition models, revealing that transformer-based architectures, particularly the Swin Transformer, achieve superior performance compared to traditional convolutional models.

The article presents a machine learning approach for synthesizing micro-Doppler radar spectrograms from Motion-Capture (MoCap) data. It formulates the translation as a windowed sequence-to-sequence task using a transformer-based model that captures spatial relations among MoCap markers and temporal dynamics across frames. Experiments demonstrate that the method produces plausible radar spectrograms and shows good generalizability, indicating its potential for applications in edge computing and IoT radars.