We present SSL-HV: Self-Supervised Learning approaches applied to the task of Handwriting Verification. This task involves determining whether a given pair of handwritten images originate from the same or different writer distribution. We have compared the performance of multiple generative, contrastive SSL approaches against handcrafted feature extractors and supervised learning on CEDAR AND dataset. We show that ResNet based Variational Auto-Encoder (VAE) outperforms other generative approaches achieving 76.3% accuracy, while ResNet-18 fine-tuned using Variance-Invariance-Covariance Regularization (VICReg) outperforms other contrastive approaches achieving 78% accuracy. Using a pre-trained VAE and VICReg for the downstream task of writer verification we observed a relative improvement in accuracy of 6.7% and 9% over ResNet-18 supervised baseline with 10% writer labels.
Antimicrobial resistance (AMR) is a looming pandemic, demanding prompt actions to avert catastrophic consequences. Effluents from pharmaceutical industries containing antimicrobial residues could serve as one of the entry points of these drugs to the environment. This qualitative study explores the treatment and disposal practices of pharmaceutical effluent (PE) containing potential antibiotic residues (ARs) by interviewing major stakeholders. In addition, we assessed their knowledge and perception on contribution of PE to AMR.The study was conducted in the two Indian states, Haryana and Telangana and at the federal level. Data was collected by semi-structured in-depth interviews of 29 participants from 17 stakeholders/organizations viz. Central Pollution Control Board (CPCB), State Pollution Control Boards (SPCBs) of Telangana and Haryana, civic body, pharmaceutical manufacturers, pharmaceutical associations and civil society. Data was analyzed using thematic analysis.The effluent treatment and disposal practices varied with the multinational companies (MNCs) having advanced technologies whereas the small and medium-scale pharmaceutical companies (SMPCs) having effluent treatment plants as per the regulations but often under-utilized. The presence of ARs in the PE was considered inconsequential by SPCBs and SMPCs and majority of stakeholders imputed other causes as major contributors to AMR. However, the MNCs were well aware of the contribution of PE to AMR and CPCB also considered ARs as direct source of AMR. The central regulators as well as MNCs expressed concerns regarding the current regulations lacking maximum ARs in the PE.Setting up regulatory standards for maximum ARs in PE, their implementation and monitoring is an urgent need to curb environmental contribution of ARs to AMR. The findings of our study will help in systematic approach in policy making, awareness programs and capacity-building in dealing with the ARs in PE to combat AMR.
We propose an effective Hybrid Deep Learning (HDL) architecture for the task of determining the probability that a questioned handwritten word has been written by a known writer. HDL is an amalgamation of Auto-Learned Features (ALF) and Human-Engineered Features (HEF). To extract auto-learned features we use two methods: First, Two Channel Convolutional Neural Network (TC-CNN); Second, Two Channel Autoencoder (TC-AE). Furthermore, human-engineered features are extracted by using two methods: First, Gradient Structural Concavity (GSC); Second, Scale Invariant Feature Transform (SIFT). Experiments are performed by complementing one of the HEF methods with one ALF method on 150000 pairs of samples of the word "AND" cropped from handwritten notes written by 1500 writers. Our results indicate that HDL architecture with AE-GSC achieves 99.7% accuracy on seen writer dataset and 92.16% accuracy on shuffled writer dataset which out performs CEDAR-FOX, as for unseen writer dataset, AE-SIFT performs comparable to this sophisticated handwriting comparison tool.
Abstract Soft actuators are the latest trend of research because of their light weight and ease of manufacturing and control. Soft actuators have expanded their fields and taken place in many applications where linear or angular deflection is required. Soft actuators are very useful in the applications where deflection is required with soft touch. Soft Actuators are highly compliant and adaptive to unknown environments. Because of these characteristics, soft actuators are very popular in the field of medical and in the applications where interaction with fragile structure is required. The soft actuators can give required responses mostly depends on their shape. Linear or angular deformation can be achieved by changing the geometrical shape of actuators. This paper presents the effect of geometrical shape on axial deformation of soft pneumatic actuator. Samples of soft actuators are selected with various shapes for finite element analysis. Results are obtained in form of axial and lateral deformation. An attempt is made to achieve good amount of axial deformation with very less or negligible lateral deformation by selecting appropriate shape. Based on the generated results, the shape is identified which gives desired results and more suitable among the selected nine samples. This sample can be useful in the application having space constraint in lateral direction.
Handwriting Verification is a critical in document forensics. Deep learning based approaches often face skepticism from forensic document examiners due to their lack of explainability and reliance on extensive training data and handcrafted features. This paper explores using Vision Language Models (VLMs), such as OpenAI's GPT-4o and Google's PaliGemma, to address these challenges. By leveraging their Visual Question Answering capabilities and 0-shot Chain-of-Thought (CoT) reasoning, our goal is to provide clear, human-understandable explanations for model decisions. Our experiments on the CEDAR handwriting dataset demonstrate that VLMs offer enhanced interpretability, reduce the need for large training datasets, and adapt better to diverse handwriting styles. However, results show that the CNN-based ResNet-18 architecture outperforms the 0-shot CoT prompt engineering approach with GPT-4o (Accuracy: 70%) and supervised fine-tuned PaliGemma (Accuracy: 71%), achieving an accuracy of 84% on the CEDAR AND dataset. These findings highlight the potential of VLMs in generating human-interpretable decisions while underscoring the need for further advancements to match the performance of specialized deep learning models.
The pattern of Electroencephalogram(EEG) signal differs significantly across different subjects, and poses challenge for EEG classifiers in terms of 1) effectively adapting a learned classifier onto a new subject, 2) retaining knowledge of known subjects after the adaptation. We propose an efficient transfer learning method, named Meta UPdate Strategy (MUPS-EEG), for continuous EEG classification across different subjects. The model learns effective representations with meta update which accelerates adaptation on new subject and mitigate forgetting of knowledge on previous subjects at the same time. The proposed mechanism originates from meta learning and works to 1) find feature representation that is broadly suitable for different subjects, 2) maximizes sensitivity of loss function for fast adaptation on new subject. The method can be applied to all deep learning oriented models. Extensive experiments on two public datasets demonstrate the effectiveness of the proposed model, outperforming current state of the arts by a large margin in terms of both adapting on new subject and retain knowledge of learned subjects.
'%3e%3ccircle r='20' fill='%23008'/%3e%3ccircle r='17.5' fill='%23fff'/%3e%3ccircle r='3.5' fill='%23008'/%3e%3cg id='d'%3e%3cg id='c'%3e%3cg id='b'%3e%3cg id='a' fill='%23008'%3e%3ccircle r='.875' transform='rotate(7.5 -8.75 133.5)'/%3e%3cpath d='M0 17.5.6 7 0 2l-.6 5L0 17.5z'/%3e%3c/g%3e%3cuse xlink:href='%23a' transform='rotate(15)'/%3e%3c/g%3e%3cuse xlink:href='%23b' transform='rotate(30)'/%3e%3c/g%3e%3cuse xlink:href='%23c' transform='rotate(60)'/%3e%3c/g%3e%3cuse xlink:href='%23d' transform='rotate(120)'/%3e%3cuse xlink:href='%23d' transform='rotate(-120)'/%3e%3c/g%3e%3c/svg%3e)