Daily Archives: June 10, 2026

Authors: Ayushi Dixit , Dr. Brij Mohan Singh

Abstract: Accurate automated diagnosis of visually similar scalp diseases represents one of the most challenging problems in clinical dermatology. Conditions such as Psoriasis, Seborrheic Dermatitis, Tinea Capitis, Alopecia Areata, Folliculitis, and Eczema share overlapping visual characteristics: including redness, scaling, and patchy hair loss, making misclassification clinically dangerous and common even among trained dermatologists. The global shortage of specialist dermatologists, particularly in rural and resource-limited settings in India, further amplifies the need for reliable automated diagnostic tools. This comprehensive research proposes ScalpViT, a novel hybrid deep learning architecture that combines a 16×16 Patch Vision Transformer (ViT) with a Convolutional Neural Network (CNN) backbone connected via a bidirectional cross-attention fusion module. The ViT branch processes the scalp image by dividing it into 256 non-overlapping 16×16-pixel patches, embedding each as a 768-dimensional token, and applying multi-head self-attention across the full token sequence to capture global spatial distribution and morphological patterns. Concurrently, the CNN branch extracts local texture details. The bidirectional cross-attention enables texture features to query spatial features and vice-versa, avoiding the pitfalls of simple feature concatenation. Trained on a meticulously curated multi-source dataset of approximately 7,000 dermoscopic and clinical scalp images drawn from DermNet NZ, ISIC 2018, HAM10000, and SD-198, ScalpViT achieves 94.3% accuracy, a macro F1-score of 0.93, and an AUC of 0.97. It significantly outperforms conventional baselines like ResNet-50 (83.1%), EfficientNet-B3 (87.4%), standard ViT-B/16 (90.8%), Swin-Tiny (91.2%), and DINOv2-B (93.5%). Furthermore, to bridge the interpretability gap for clinical deployment, ScalpViT utilizes GradCAM for CNN texture heatmapping and Attention Rollout for ViT patch mapping, delivering dual visual explainability to clinicians. The paper extensively details the methodology, dataset construction, architectural innovations, and clinical relevance for point-of-care mobile deployments.

DOI: https://doi.org/10.5281/zenodo.20637980

Published by: vikaspatanker

Authors: Mr. Ashish Kumar, Dr. Satender Kumar

Abstract: The study of anomaly detection in time series has become one of the key topics in intelligent monitoring systems such as industrial automation, cybersecurity, healthcare, finance, IoT. The traditional approaches to anomaly detection primarily focused on detecting any signs of anomalous behaviour following their occurrence. However, in many cases, reactive anomaly detection does not allow for timely response to detected anomalies. Recently, some researchers have suggested the novel idea of Precursor-of-Anomaly (PoA) detection to detect and analyse warning signs prior to anomalies' occurrence. The present paper provides a review and experimental framework of PoA detection in time series. The paper outlines approaches to traditional anomaly detection, deep learning based forecasting models, uncertainty-aware models, and early warning approaches. Also, the paper outlines a practical framework of PoA analysis using industrial SWaT dataset and Isolation Forest approach. Experimental results prove that uncertainty-aware PoA detection is capable of delivering early warning signals before critical anomalies occur. The paper considers modern limitations and challenges in designing proactive anomaly prediction systems.

DOI: https://doi.org/10.5281/zenodo.20631084

Published by: vikaspatanker

Authors: Associate Professor Mahesh Thakare, Pooja Choudhary, Sakshi Harihar, Vijaykumar Kale, Associate professor Vaibhav Narwade

Abstract: Approximately 85% of teenagers suffer from acne vulgaris, which can last until adulthood. Teenagers see doctors approximately two million times a year, and the US spends more than $1 billion on acne treatments directly. There are many different therapy options for acne vulgaris, such as hormonal, anti- androgen, or anti seborrheic medications, as well as retinoids, isoprenoids, keratolytic soaps, alpha hydroxy acids, azelaic acid, and salicylic acid. All of these techniques do have some negative effects, though, and it's unclear exactly how they fit into therapy. This paper not only presents the potential causes of acne vulgaris, medications that can treat it, and recently released research on the usage of medicinal herbs to treat the condition were examined. Topical formulations (herbal cream) have been developed containing Ocimum sanctum (Tulsi) extract, Aloe barbadensis miller (Aloe-vera Gel), Melaleuca Oil (Tea Tree Oil). These medicinal herbs and essential oil (TTO) show anti-bacterial activity against acne causing bacteria like Propionibacterium and staphylococcus aures. Various batches containing above Herbs and Essential oil are prepared and their comparative studies are performed. Certain evaluation tests are performed like Irritancy, Washability, pH, Greasiness to check whether cream is suitable for human skin. In the end anti-bacterial activity of the cream was carried out using agar well diffusion method against staphylococcus aures.

DOI: http://doi.org/

Published by: vikaspatanker

Authors: Assistant Professor Dr. Vijaykumar Kale, Ms.Rutuja Popat Chavan, Ms.Pratiksha Ashok Jaybhay, Dr. Mahesh Thakare, Mr. Vaibhav Narwade

Abstract: Herbal cosmetics have gained significant importance due to their safety, effectiveness, and minimal side effects compared to synthetic products. The present research project focuses on the formulation and development of herbal hair oil using Betel Leaf as the major active ingredient. Betel leaf is traditionally known for its antimicrobial, antifungal, antioxidant, and anti-inflammatory properties, which are beneficial for maintaining healthy hair and scalp conditions The herbal hair oil was prepared using betel leaf along with other natural ingredients such as coconut oil, curry leaves, hibiscus, and aloe vera. The formulation was developed by heating the herbal materials with the base oil to extract the active constituents effectively. The prepared oil was filtered and evaluated for various physicochemical parameters including color, odor, pH, viscosity, specific gravity, irritation test, and stability study. The formulated herbal hair oil showed satisfactory physical appearance, good stability, and acceptable consistency without causing skin irritation. The presence of betel leaf in the formulation may help reduce dandruff, scalp infections, and hair fall due to its medicinal properties. The study concludes that the prepared herbal hair oil can serve as a safe, economical, and natural alternative for hair care management. This research supports the growing demand for herbal cosmetic products and highlights the potential. [1]

Published by: vikaspatanker

Authors: By Mr. Basavaraj Swamy

Abstract: Techniques from Machine learning and deep learning are usually helpful in classification of data. A dataset is processed through a CNN before it is used for classification. Text mining, image processing, and score prediction techniques are very much important in the field of analytics. In paper, we used classification and data prediction methods to demonstrate image and numerical analysis. Analytics show that traditional backup methods have been improved with better ways of managing data. This process of supervised learning produces comparable present outcomes with accurate predicted values.

Published by: vikaspatanker