Generalized Category Discovery (GCD) aims to classify labeled instances from known categories while discovering novel categories from unlabeled data. Despite recent progress in GCD for computer vision, existing GCD approaches largely rely on static final-step representations (in the visual domain), overlooking the temporally evolving nature of time-series data. In this paper, we introduce TGCD, the first framework specifically designed for GCD in time-series data. TGCD leverages both the dynamics of latent representations and the heterogeneity of predictions across multiple temporal segments to disover unknown (i.e., novel) categories, based on a pre-trained time-series foundation model. We propose a unified learning objective for TGCD that integrates the following three components: (i) a Stochastic Temporal Segment Dropout (STeSD) objective that regularizes the model by selectively penalizing high-entropy segments to encourage confident predictions on uncertain regions of the time-series, and (ii) a Known–Unknown Temporal Discriminability (KUTD) objective that promotes representational separation between known and unknown categories within unlabeled data and (iii) a margin-aware classification objective to improve generalization. Empirical evaluation on six multivariate time-series data sets demonstrates that the TGCD substantially outperforms existing GCD methods, particularly in discovering unknown categories. We further conduct ablation studies to highlight the individual contributions of each component. Additionally, we provide the first comprehensive benchmarking of recent GCD approaches on time-series data, revealing the limitations of naive transfer and underscoring the benefits of temporal modeling.

Abstract Glaucoma is a critical eye condition that causes permanent blindness by damaging the Optic Nerve Head (ONH). Ophthalmologists diagnose glaucoma in patients by conducting morphological analysis of Optic Cup (OC) and Optic Disc (OD) regions in retinal fundus images. The implementation of lightweight and robust Artificial-Intelligence-enabled tools to deliver prompt glaucoma diagnostics is paramount in biomedical engineering. This article proposes CSP-SegNet, a novel Channel-Spatial-Pixel (CSP) attention-integrated lightweight encoder-decoder architecture for joint semantic segmentation of OC and OD in retinal fundus images. The crux of this work lies in the novel Channel-Spatial-Pixel (CSP) attention module which facilitates enhanced feature representation from different levels of abstraction with faster convergence. The efficacy of novel CSP attention is analyzed using Grad-CAM–based attention map evolution for explainable interpretation. CSP-SegNet is a novel depthwise separable convolutional neural network comprising approximately 1.54M trainable parameters with 13.3G FLOPS and hence it is highly lightweight compared to other methods. This paper has rigidly analyzed the robustness and generalization ability of CSP-SegNet in contrast to state-of-the-art segmentation networks, across the REFUGE and ORIGA datasets with cross-dataset evaluation on Drishti-GS. The proposed CSP-SegNet has obtained statistically significant results in outperforming many competing methods for joint semantic segmentation of OC and OD across Dice Similarity Coefficient (DSC) and Intersection over Union (IoU) metrics. The quantitative and qualitative evaluation results justify the superiority of CSP-SegNet and effectiveness of CSP attention in terms of generalization ability, segmentation performance, robustness across distribution shift and compactness. The code is available at https://github.com/AIAnkitDas/CSP-SegNet/tree/main .

In many industries, there is a growing awareness to ensure the reliability and availability of manufacturing systems. Monitoring the health of machines enables the users to schedule repair and maintenance of the system ensuring less downtime, thereby enhancing its lifetime. With the advent of sensor technology, machine learning based algorithms show promise in estimating the Remaining Useful Life (RUL) of machine components. This paper presents recurrent architecture with attention for estimating the RUL of turbofan engines. First, we present a Deep Long Short Term Memory (DLSTM) network with dropout at multiple layers for RUL prediction. Next, we enhance the DLSTM model to handle the sequence in both forward and reverse direction using a Bidirectional Deep Long Short Term Memory (BiDLSTM). Finally, we present an Attention based Deep LSTM (Attn-DLSTM) which takes into account all the timesteps in estimation of the RUL. The inclusion of attention mechanism helps improve the accuracy as well as interpretability of the deep LSTM network. All the experiments are carried out using the publicly available NASA turbofan dataset. Results show the efficacy of deep networks compared to traditional machine learning algorithms.

In advanced manufacturing industries, there is a need to monitor the health of tools with the aim of enhancing its lifetime. Often due to several reasons such as cost and time, many organizations are faced with the difficulty in collecting complete degradation data for monitoring the tool. As such, this makes tool wear prognostics a challenging problem in the real world. Although there have been a number of studies on tool wear prognosis, the monitoring of tool wear where the complete wear data is unavailable is still a challenge. This paper presents a framework for tool wear prognosis when the degradation data is limited. First, we present an analysis of tool wear diagnosis, in which the health of tool is classified into three categories of new tool, medium worn tool and high worn tool. Next, we present the analysis of tool wear prognosis by assuming linear and non-linear degradation curves of tool wear. Real data for tool wear is collected using five different tools used for cutting with three different degrees of flank wears, namely, new, medium and high worn. Results showed high classification and prediction accuracies in terms of the trends of prediction as well as the mean squared error.

Analysis of high-content screening (HCS) data mostly relies on supervised machine learning based approaches employing user-defined image features. This strategy has limited applications due to the requirement of a priori knowledge of expected cellular phenotypes / perturbations and the time-consuming process of manually annotating these phenotypes. To address these issues, we propose a machine learning based unsupervised framework for high-content analysis. The framework performs anomaly detection using features transferred from natural images to the cellular images by deep learning models. We applied this framework to detect anomalous effects of FDA approved drugs on human monocytic cells. Drug anomaly detection based on image features derived using three deep learning architectures, DenseNet-121, ResNet-50 and VGG-16, is compared with the anomaly scores computed from user-defined features extracted from individually segmented cells. The drug anomaly scores of automatically extracted deep features and user-defined features were found to be comparable. Our method has broad implications for faster and reliable analysis of high-content data with limited human interaction which can provide new biological insights and identification of drug candidates for repurposing of FDA approved drugs for new clinical conditions.