Towards Efficient Real-Time Video Motion Transfer via Generative Time Series Modeling

We propose a deep learning framework designed to significantly optimize bandwidth for motion-transfer-enabled video applications, including video conferencing, virtual reality interactions, health monitoring systems, and vision-based real-time anomaly detection. To capture complex motion effectively, we utilize the First Order Motion Model (FOMM), which encodes dynamic objects by detecting keypoints and their associated local affine transformations. These keypoints are identified using a self-supervised keypoint detector and arranged into a time series corresponding to the successive frames. Forecasting is performed on these keypoints by integrating two advanced generative time series models into the motion transfer pipeline, namely the Variational Recurrent Neural Network (VRNN) and the Gated Recurrent Unit with Normalizing Flow (GRU-NF). The predicted keypoints are subsequently synthesized into realistic video frames using an optical flow estimator paired with a generator network, thereby facilitating accurate video forecasting and enabling efficient, low-frame-rate video transmission. We validate our results across three datasets for video animation and reconstruction using the following metrics: Mean Absolute Error, Joint Embedding Predictive Architecture Embedding Distance, Structural Similarity Index, and Average Pair-wise Displacement. Our results confirm that by utilizing the superior reconstruction property of the Variational Autoencoder, the VRNN integrated FOMM excels in applications involving multi-step ahead forecasts such as video conferencing. On the other hand, by leveraging the Normalizing Flow architecture for exact likelihood estimation, and enabling efficient latent space sampling, the GRU-NF based FOMM exhibits superior capabilities for producing diverse future samples while maintaining high visual quality for tasks like real-time video-based anomaly detection.

From Automation to Autonomy in Smart Manufacturing: A Bayesian Optimization Framework for Modeling Multi-Objective Experimentation and Sequential Decision Making

Discovering novel materials with desired properties is essential for driving innovation. Industry 4.0 and smart manufacturing have promised transformative advances in this area through real-time data integration and automated production planning and control. However, the reliance on automation alone has often fallen short, lacking the flexibility needed for complex processes. To fully unlock the potential of smart manufacturing, we must evolve from automation to autonomous systems that go beyond rigid programming and can dynamically optimize the search for solutions. Current discovery approaches are often slow, requiring numerous trials to find optimal combinations, and costly, particularly when optimizing multiple properties simultaneously. This paper proposes a Bayesian multi-objective sequential decision-making (BMSDM) framework that can intelligently select experiments as manufacturing progresses, guiding us toward the discovery of optimal design faster and more efficiently. The framework leverages sequential learning through Bayesian Optimization, which iteratively refines a statistical model representing the underlying manufacturing process. This statistical model acts as a surrogate, allowing for efficient exploration and optimization without requiring numerous real-world experiments. This approach can significantly reduce the time and cost of data collection required by traditional experimental designs. The proposed framework is compared with traditional DoE methods and two other multi-objective optimization methods. Using a manufacturing dataset, we evaluate and compare the performance of these approaches across five evaluation metrics. BMSDM comprehensively outperforms the competing methods in multi-objective decision-making scenarios. Our proposed approach represents a significant leap forward in creating an intelligent autonomous platform capable of novel material discovery.

Confidence Adjusted Surprise Measure for Active Resourceful Trials (CA-SMART): A Data-driven Active Learning Framework for Accelerating Material Discovery under Resource Constraints

Accelerating the discovery and manufacturing of advanced materials with specific properties is a critical yet formidable challenge due to vast search space, high costs of experiments, and time-intensive nature of material characterization. In recent years, active learning, where a surrogate machine learning (ML) model mimics the scientific discovery process of a human scientist, has emerged as a promising approach to address these challenges by guiding experimentation toward high-value outcomes with a limited budget. Among the diverse active learning philosophies, the concept of surprise (capturing the divergence between expected and observed outcomes) has demonstrated significant potential to drive experimental trials and refine predictive models. Scientific discovery often stems from surprise thereby making it a natural driver to guide the search process. Despite its promise, prior studies leveraging surprise metrics such as Shannon and Bayesian surprise lack mechanisms to account for prior confidence, leading to excessive exploration of uncertain regions that may not yield useful information. To address this, we propose the Confidence-Adjusted Surprise Measure for Active Resourceful Trials (CA-SMART), a novel Bayesian active learning framework tailored for optimizing data-driven experimentation. On a high level, CA-SMART incorporates Confidence-Adjusted Surprise (CAS) to dynamically balance exploration and exploitation by amplifying surprises in regions where the model is more certain while discounting them in highly uncertain areas. We evaluated CA-SMART on two benchmark functions (Six-Hump Camelback and Griewank) and in predicting the fatigue strength of steel. The results demonstrate superior accuracy and efficiency compared to traditional surprise metrics, standard Bayesian Optimization (BO) acquisition functions and conventional ML methods.

Digital Twin Enabled Site Specific Channel Precoding: Over the Air CIR Inference

This paper investigates the significance of designing a reliable, intelligent, and true physical environment-aware precoding scheme by leveraging an accurately designed channel twin model to obtain realistic channel state information (CSI) for cellular communication systems. Specifically, we propose a fine-tuned multi-step channel twin design process that can render CSI very close to the CSI of the actual environment. After generating a precise CSI, we execute precoding using the obtained CSI at the transmitter end. We demonstrate a two-step parameters' tuning approach to design channel twin by ray tracing (RT) emulation, then further fine-tuning of CSI by employing an artificial intelligence (AI) based algorithm can significantly reduce the gap between actual CSI and the fine-tuned digital twin (DT) rendered CSI. The simulation results show the effectiveness of the proposed novel approach in designing a true physical environment-aware channel twin model.

In-Situ Melt Pool Characterization via Thermal Imaging for Defect Detection in Directed Energy Deposition Using Vision Transformers

Directed Energy Deposition (DED) offers significant potential for manufacturing complex and multi-material parts. However, internal defects such as porosity and cracks can compromise mechanical properties and overall performance. This study focuses on in-situ monitoring and characterization of melt pools associated with porosity, aiming to improve defect detection and quality control in DED-printed parts. Traditional machine learning approaches for defect identification rely on extensive labeled datasets, often scarce and expensive to generate in real-world manufacturing. To address this, our framework employs self-supervised learning on unlabeled melt pool data using a Vision Transformer-based Masked Autoencoder (MAE) to produce highly representative embeddings. These fine-tuned embeddings are leveraged via transfer learning to train classifiers on a limited labeled dataset, enabling the effective identification of melt pool anomalies. We evaluate two classifiers: (1) a Vision Transformer (ViT) classifier utilizing the fine-tuned MAE Encoder's parameters and (2) the fine-tuned MAE Encoder combined with an MLP classifier head. Our framework achieves overall accuracy ranging from 95.44% to 99.17% and an average F1 score exceeding 80%, with the ViT Classifier slightly outperforming the MAE Encoder Classifier. This demonstrates the scalability and cost-effectiveness of our approach for automated quality control in DED, effectively detecting defects with minimal labeled data.

A Data-Efficient Sequential Learning Framework for Melt Pool Defect Classification in Laser Powder Bed Fusion

Ensuring the quality and reliability of Metal Additive Manufacturing (MAM) components is crucial, especially in the Laser Powder Bed Fusion (L-PBF) process, where melt pool defects such as keyhole, balling, and lack of fusion can significantly compromise structural integrity. This study presents SL-RF+ (Sequentially Learned Random Forest with Enhanced Sampling), a novel Sequential Learning (SL) framework for melt pool defect classification designed to maximize data efficiency and model accuracy in data-scarce environments. SL-RF+ utilizes RF classifier combined with Least Confidence Sampling (LCS) and Sobol sequence-based synthetic sampling to iteratively select the most informative samples to learn from, thereby refining the model's decision boundaries with minimal labeled data. Results show that SL-RF+ outperformed traditional machine learning models across key performance metrics, including accuracy, precision, recall, and F1 score, demonstrating significant robustness in identifying melt pool defects with limited data. This framework efficiently captures complex defect patterns by focusing on high-uncertainty regions in the process parameter space, ultimately achieving superior classification performance without the need for extensive labeled datasets. While this study utilizes pre-existing experimental data, SL-RF+ shows strong potential for real-world applications in pure sequential learning settings, where data is acquired and labeled incrementally, mitigating the high costs and time constraints of sample acquisition.

Advancing Healthcare: Innovative ML Approaches for Improved Medical Imaging in Data-Constrained Environments

Healthcare industries face challenges when experiencing rare diseases due to limited samples. Artificial Intelligence (AI) communities overcome this situation to create synthetic data which is an ethical and privacy issue in the medical domain. This research introduces the CAT-U-Net framework as a new approach to overcome these limitations, which enhances feature extraction from medical images without the need for large datasets. The proposed framework adds an extra concatenation layer with downsampling parts, thereby improving its ability to learn from limited data while maintaining patient privacy. To validate, the proposed framework's robustness, different medical conditioning datasets were utilized including COVID-19, brain tumors, and wrist fractures. The framework achieved nearly 98% reconstruction accuracy, with a Dice coefficient close to 0.946. The proposed CAT-U-Net has the potential to make a big difference in medical image diagnostics in settings with limited data.

Deep Learning Model-Based Channel Estimation for THz Band Massive MIMO with RF Impairments

THz band enabled large scale massive MIMO (M-MIMO) is considered as a key enabler for the 6G technology, given its enormous bandwidth and for its low latency connectivity. In the large-scale M-MIMO configuration, enlarged array aperture and small wavelengths of THz results in an amalgamation of both far field and near field paths, which makes tasks such as channel estimation for THz M-MIMO highly challenging. Moreover, at the THz transceiver, radio frequency (RF) impairments such as phase noise (PN) of the analog devices also leads to degradation in channel estimation performance. Classical estimators as well as traditional deep learning (DL) based algorithms struggle to maintain their robustness when performing for large scale antenna arrays i.e., M-MIMO, and when RF impairments are considered for practical usage. To effectively address this issue, it is crucial to utilize a neural network (NN) that has the ability to study the behaviors of the channel and RF impairment correlations, such as a recurrent neural network (RNN). The RF impairments act as sequential noise data which is subsequently incorporated with the channel data, leading to choose a specific type of RNN known as bidirectional long short-term memory (BiLSTM) which is followed by gated recurrent units (GRU) to process the sequential data. Simulation results demonstrate that our proposed model outperforms other benchmark approaches at various signal-to-noise ratio (SNR) levels.

A Comprehensive Approach to Carbon Dioxide Emission Analysis in High Human Development Index Countries using Statistical and Machine Learning Techniques

Reducing Carbon dioxide (CO2) emission is vital at both global and national levels, given their significant role in exacerbating climate change. CO2 emission, stemming from a variety of industrial and economic activities, are major contributors to the greenhouse effect and global warming, posing substantial obstacles in addressing climate issues. It's imperative to forecast CO2 emission trends and classify countries based on their emission patterns to effectively mitigate worldwide carbon emission. This paper presents an in-depth comparative study on the determinants of CO2 emission in twenty countries with high Human Development Index (HDI), exploring factors related to economy, environment, energy use, and renewable resources over a span of 25 years. The study unfolds in two distinct phases: initially, statistical techniques such as Ordinary Least Squares (OLS), fixed effects, and random effects models are applied to pinpoint significant determinants of CO2 emission. Following this, the study leverages supervised and unsupervised machine learning (ML) methods to further scrutinize and understand the factors influencing CO2 emission. Seasonal AutoRegressive Integrated Moving Average with eXogenous variables (SARIMAX), a supervised ML model, is first used to predict emission trends from historical data, offering practical insights for policy formulation. Subsequently, Dynamic Time Warping (DTW), an unsupervised learning approach, is used to group countries by similar emission patterns. The dual-phase approach utilized in this study significantly improves the accuracy of CO2 emission predictions while also providing a deeper insight into global emission trends. By adopting this thorough analytical framework, nations can develop more focused and effective carbon reduction policies, playing a vital role in the global initiative to combat climate change.

Exploring the Efficacy of Group-Normalization in Deep Learning Models for Alzheimer's Disease Classification

Batch Normalization is an important approach to advancing deep learning since it allows multiple networks to train simultaneously. A problem arises when normalizing along the batch dimension because B.N.'s error increases significantly as batch size shrinks because batch statistics estimates are inaccurate. As a result, computer vision tasks like detection, segmentation, and video, which require tiny batches based on memory consumption, aren't suitable for using Batch Normalization for larger model training and feature transfer. Here, we explore Group Normalization as an easy alternative to using Batch Normalization A Group Normalization is a channel normalization method in which each group is divided into different channels, and the corresponding mean and variance are calculated for each group. Group Normalization computations are accurate across a wide range of batch sizes and are independent of batch size. When trained using a large ImageNet database on ResNet-50, GN achieves a very low error rate of 10.6% compared to Batch Normalization. when a smaller batch size of only 2 is used. For usual batch sizes, the performance of G.N. is comparable to that of Batch Normalization, but at the same time, it outperforms other normalization techniques. Implementing Group Normalization as a direct alternative to B.N to combat the serious challenges faced by the Batch Normalization in deep learning models with comparable or improved classification accuracy. Additionally, Group Normalization can be naturally transferred from the pre-training to the fine-tuning phase. .