Browse Items (11810 total)
Sort by:
-
Enhancing Mobility: A Smart Cane with Integrated Navigation System and Voice-Assisted Guidance for the Visually Impaired
Blindness is a condition which affects many people, and for the affected people, quality of life can take a big hit. Most blind people already use walking sticks to feel the terrain in front of them as they move around and navigate using touch and sound. However, they cannot judge distances to objects until the cane actually hits the object. In some cases, the contact with the cane may damage the object. Hence, it may be better to have some early warning system so that there is less likelihood of causing damage. This paper presents the design and development of a 'Smart Cane' aimed at enhancing mobility and safety for visually impaired individuals. The cane incorporates ultrasonic sensors to detect objects in the user's surroundings. When an object is detected within a specified distance range, the cane provides haptic feedback through a bidirectional vibration motor, alerting the user to its presence. The microcontroller-based system processes data from both sensors and efficiently manages power consumption to ensure extended battery life. The device's design includes user-friendly controls and an ergonomic enclosure to offer ease of use and protection for the electronic components. Further, there is built-in navigation via online Map API. With the convenience of navigating oneself without external assistance, the 'Smart Cane' demonstrates great potential to improve the independence and confidence of visually impaired individuals in navigating their environments safely. 2024 IEEE. -
A machine learning model to predict suicidal tendencies in students
[No abstract available] -
A Specular Reflection Removal Technique in Cervigrams
Cancer detection through medical image segmentation and classification is possible owing to the advancement in image processing techniques. Segmentation and classification tasks carried out to predict and classify diseases need to be dependable and precise. Specular reflections are the high-intensity and low-saturation areas that reflect the light from the probing devices that capture the picture of the organ surface. These areas sometimes mimic the features that are key identifying factors for cancers like acetowhite lesions. This review article examines the various methods proposed for removing specular reflections from medical images, especially those captured by colposcopes. The fundamentals of specular reflection removal and its associated challenges are discussed. The paper reviews several prominent approaches for removal of specular reflections proposes a novel method to remove the specular reflections. The comprehensive review can be a strong foundation for researchers looking to decide on appropriate techniques to employ in their respective research approaches. 2023 IEEE. -
Specular Reflection Removal Techniques in Cervix Image: A Comprehensive Review
Cancer detection through medical image segmentation and classification is possible owing to the advancement in image processing techniques. Segmentation and classification tasks carried out to predict and classify diseases need to be dependable and precise. Specular reflections are the high-intensity and low-saturation areas that reflect the light from the probing devices that capture the picture of the organ surface. These areas sometimes mimic the features that are key identifying factors for cancers like acetowhite lesions. This review article examines the various methods proposed for removing specular reflections from medical images, especially those captured by colposcope. The fundamentals of specular reflection removal and its associated challenges are discussed. The paper reviews several state-of-the-art approaches for specular reflection removal. The comprehensive review can be a strong foundation for researchers looking to decide on appropriate techniques to employ in their respective research approaches. 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Multimodal Early Fusion Strategy Based on Deep Learning Methods for Cervical Cancer Identification
It is essential to enhance the accuracy of automatic cervical cancer diagnosis by combining multiple forms of information obtained from a patients primary examination. However, existing multimodal systems are not very effective in detecting correlations between different types of data, leading to low sensitivity but high specificity. This study introduces a deep learning system for automatic diagnosis of cervical cancer by incorporating multiple sources of data. First, a convolutional neural network (CNN) to transform the image database to a vector that can be combined with non-image datasets is used. Subsequently, an investigation of jointly the nonlinear connections between all image and non-image data in a deep neural network is performed. Proposed deep learning-based method creates a unified system that takes advantage of both image and non-image data. It achieves an impressive 89.32% sensitivity at 91.6% specificity when diagnosing cervical intraepithelial neoplasia on a wide-ranging dataset. This result is far superior to any single-source system or prior multimodal approaches. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
A Lesion Feature Engineering Technique Based on Gaussian Mixture Model to Detect Cervical Cancer
Latest innovations in technology and computer science have opened up ample scope for tremendous advances in the healthcare field. Automated diagnosis of various medical problems has benefitted from advances in machine learning and deep learning models. Cancer diagnosis, prognosis prediction and classification have been the focus of an immense amount of research and development in intelligent systems. One of the major concerns of health and the reason for mortality in women is cervical cancer. It is the fourth most common cancer in women, as well as one of the top reasons of mortality in developing countries. Cervical cancer can be treated completely if it is diagnosed in its early stages. The acetowhite lesions are the critical informative features of the cervix. The current study proposes a novel feature engineering strategy called lesion feature extraction (LFE) followed by a lesion recognition algorithm (LRA) developed using a deep learning strategy embedded with a Gaussian mixture model with expectation maximum (EM) algorithm. The model performed with an accuracy of 0.943, sensitivity of 0.921 and specificity of 0.891. The proposed method will enable early, accurate diagnosis of cervical cancer. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Advanced Cervical Lesion Detection using Deep Learning Techniques
Cervical cancer has been one of the common causes for mortality by cancer in women across the world. But there are currently not enough skilled colposcopists, and the training process is drawn out. This implicates that there is a significant scope for artificial intelligence based computational models for segmentation of colposcope images. This paper proposes a segmentation network to accurately segment the cervix region and acetowhite lesions in a cervigram. This research can lay a foundation for research aiming to classify the cervix malignancy using AI. The method performed with a precision of 0.73870.1541, accuracy of 0.9291, recall of 0.79120.1439, a dice score of 0.74310.1506 and specificity of 0.95890.0131. The results prove that the model is reliable and robust. 2024 IEEE. -
CeLaTis: A Large Scale Multimodal Dataset with Deep Region Network to Diagnose Cervical Cancer
Cervical cancer is a leading cause of mortality in third world countries. Although there are multiple ways of screening cervical cancer, colposcope image analysis is considered to be standard routine method of diagnosis. Due to factors like lack of skilled personnel and interobserver variability, there is a need for automated diagnostic support for cervical cancer. However, artificial intelligence solutions for medical image analysis done through deep and machine learning models require high quality, non-erroneous and sufficient amount of data. Owing to the lack of such established benchmark datasets for the colposcope images, this work aims at establishing a standard benchmark multi state colposcope image dataset that also contains clinical findings pertaining to each case. In order to establish the quality of the images, mask R-CNN method is used for segmenting the images. Subsequently, a series of IMAGENet pretrained deep learning models are deployed on the dataset to evaluate the performance. The dataset will be made available upon request for strictly research purposes. The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. -
Comparative Performance Analysis of Deep Learning Models in Cervical Cancer Detection
Cervical cancer one of the four most common malignancies worldwide and poses a significant threat, particularly in resource-constrained regions. Automated diagnostic approaches, leveraging colposcope image analysis, hold great promise in curbing the impact of this disease. In this paper, we deploy a range of deep learning methods, including DenseNet 121, ResNet 50, AlexNet and VGG 16 to classify the cervical intraepithelial neoplasia. Our methodology is deployed on a dataset sourced from a Cancer Research institute in India. The current experiment aims to establish the execution of the state-of-the-art pretrained frameworks in deep learning. This will be a baseline experiment for researcher who aim to develop further deep learning models for cervical cancer diagnosis. The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. -
Early-Stage Cervical Cancer Detection via Ensemble Learning and Image Feature Integration
Cervical cancer ranks as the fourth most common malignancy worldwide and poses a significant threat, particularly in resource-constrained regions. Automated diagnostic approaches, leveraging colposcope image analysis, hold great promise in curbing the impact of this disease. In this study, we introduce an ensemble of machine learning and deep learning models, including DenseNet 121, ResNet 50, and XGBoost to classify the cervical intraepithelial neoplasia. A novel feature integration is proposed which ensembles the results of the individual models in five fold validation process. Our methodology is deployed on a dataset sourced from the International Agency for Cancer Research. The results from the proposed framework have shown to be accurate, robust and dependable. This method can be utilized for achieving automatic identification of cervical cancer in early stages so it can be treated appropriately. The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. -
Attention Based Meta-Module to Integrate Cervigrams with Clinical Data for Cervical Cancer Identification
Cervical cancer remains a significant burden on public health, particularly in developing countries, where its malignancy and mortality rates are alarmingly high. Early diagnosis stands as a pivotal factor in effectively treating and potentially curing the cervical cancer. This study introduces a novel approach of meta module based on recurrent gate architecture designed to enhance the classification of cervix images efficiently. This innovative framework incorporates a meta module capable of dynamically selecting image modalities most pertinent attributes. Furthermore, it integrates clinical data with extracted image features and employs a range of EfficientNet architectures (B0-B5) for image classification. Our results indicate that the EfficientNet B5 architecture outperforms its counterparts, achieving an AUC (Area Under the Curve) score of 55.1 and an F1-Score of 75.1. Overall, this work represents a crucial step towards improving the early detection of cervical cancer, which in turn can lead to more effective treatment strategies and, ultimately, better outcomes for patients worldwide. The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. -
A Review of Deep Learning Methods in Automatic Facial Micro-expression Recognition
Facial expression analysis to understand human emotion is the base for affective computing. Until the last decade, researchers mainly used facial macro-expressions for classification and detection problems. Micro-expressions are the tiny muscle moments in the face that occur as responses to feelings and emotions. They often reveal true emotions that a person attempts to suppress, hide, mask, or conceal. These expressions reflect a persons real emotional state. They can be used to achieve a range of goals, including public protection, criminal interrogation, clinical assessment, and diagnosis. It is still relatively new to utilize computer vision to assess facial micro-expressions in video sequences. Accurate machine analysis of facial micro-expression is now conceivable due to rapid progress in computational methodologies and video acquisition methods, as opposed to a decade ago when this had been a realm of therapists and assessment seemed to be manual. Even though the research of facial micro-expressions has become a longstanding topic in psychology, this is still a comparatively recent computational science with substantial obstacles. This paper a provides a comprehensive review of current databases and various deep learning methodologies to analyze micro-expressions. The automation of these procedures is broken down into individual steps, which are documented and debated. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
TelsNet: temporal lesion network embedding in a transformer model to detect cervical cancer through colposcope images
Cervical cancer ranks as the fourth most prevalent malignancy among women globally. Timely identification and intervention in cases of cervical cancer hold the potential for achieving complete remission and cure. In this study, we built a deep learning model based on self-attention mechanism using transformer architecture to classify the cervix images to help in diagnosis of cervical cancer. We have used techniques like an enhanced multivariate gaussian mixture model optimized with mexican axolotl algorithm for segmenting the colposcope images prior to the Temporal Lesion Convolution Neural Network (TelsNet) classifying the images. TelsNet is a transformer-based neural network that uses temporal convolutional neural networks to identify cancerous regions in colposcope images. Our experiments show that TelsNet achieved an accuracy of 92.7%, with a sensitivity of 73.4% and a specificity of 82.1%. We compared the performance of our model with various state-of-the-art methods, and our results demonstrate that TelsNet outperformed the other methods. The findings have the potential to significantly simplify the process of detecting and accurately classifying cervical cancers at an early stage, leading to improved rates of remission and better overall outcomes for patients globally. 2023, Universitas Ahmad Dahlan. All rights reserved. -
Media's influence on suicide: Building a safer online world for all
In 1999, World Health Organization (WHO) initiated a global campaign focused on suicide prevention. In collaboration with International Association for Suicide Prevention, WHO compiled recommendations and resources intended to educate various societal and groups with the potential to impact suicide prevention, and this included the media. In order to combat the alarmingly high incidence of suicides (Tandon and Nathani, 2018), it is imperative to institute guidelines outlining how the social media forums ought to disseminate altruistic, essential educational content while. This work is a step toward achieving the same by laying down guidelines that could potentially reduce the suicide rate. 2023 Elsevier B.V. -
EGMM: removal of specular reflection with cervical region segmentation using enhanced Gaussian mixture model in cervix images
Colposcopy is a crucial imaging technique for finding cervical abnormalities. Colposcopic image evaluation, particularly the accurate delineation of the cervix region, has considerable medical significance.Before segmenting the cervical region, specular reflection removal is an efficient one. Because, cervical cancer can be found using a visual check with acetic acid, which turns precancerous and cancerous areas whiteand these could be viewed as signs of abnormalities. Similarly, bright white regions known as specular reflections obstruct the identification of aceto-whiteareas and should therefore be removed. So, in this paper, specular reflection removal with segmentingthe cervix region ina colposcopy image is proposed. The proposed approach consists of two main stages, namely, pre-processing and segmentation. In the pre-processing stage, specular reflections are detected and removed using a swin transformer. After that, cervical regions are segmented using an enhanced Gaussian mixture model (EGMM). For better segmentation accuracy, the best parameters of GMM are chosen via the adaptive Mexican Axolotl Optimization (AMAO) algorithm. The performance of the proposed approach is analyzed based on accuracy, sensitivity, specificity, Jaccard index, and dice coefficient, and the efficiency of the suggested strategy is compared with various methods. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024. -
CMT-CNN: colposcopic multimodal temporal hybrid deep learning model to detect cervical intraepithelial neoplasia
Cervical cancer poses a significant threat to women's health in developing countries, necessitating effective early detection methods. In this study, we introduce the Colposcopic Multimodal Temporal Convolution Neural Network (CMT-CNN), a novel model designed for classifying cervical intraepithelial neoplasia by leveraging sequential colposcope images and integrating extracted features with clinical data. Our approach incorporates Mask R-CNN for precise cervix region segmentation and deploys the EfficientNet B7 architecture to extract features from saline, iodine, and acetic acid images. The fusion of clinical data at the decision level, coupled with Atrous Spatial Pyramid Pooling-based classification, yields remarkable results: an accuracy of 92.31%, precision of 90.19%, recall of 89.63%, and an F-1 score of 90.72. This achievement not only establishes the superiority of the CMT-CNN model over baselines but also paves the way for future research endeavours aiming to harness heterogeneous data types in the development of deep learning models for cervical cancer screening. The implications of this work are profound, offering a potent tool for early cervical cancer detection that combines multimodal data and clinical insights, potentially saving countless lives. 2024, Universitas Ahmad Dahlan. All rights reserved. -
Tunable Capacitive Behavior in Metallopolymer-based Electrochromic Thin Film Supercapacitors
Volumetric capacitance is a more critical performance parameter for rechargeable power supply in lightweight and microelectronic devices as compared to gravimetric capacitance in larger devices. To this end, we report three electrochromic metallopolymer-based electrode materials containing Fe2+as the coordinating metal ion with high volumetric capacitance and energy densities in a symmetric two-electrode supercapacitor setup. These metallopolymers exhibited volumetric capacitance up to 866.2 F cm-3at a constant current density of 0.25 A g-1. The volumetric capacitance (poly-Fe-L2: 544.6 F cm-3> poly-Fe-L1: 313.8 F cm-3> poly-Fe-L3: 230.8 F cm-3at 1 A g-1) and energy densities (poly-Fe-L2: 75.5 mWh cm-3> poly-Fe-L1: 43.6 mWh cm-3> poly-Fe-L3: 31.2 mWh cm-3) followed the order of the electrical conductivity of the metallopolymers and are among the best values reported for metal-organic systems. The variation in the ligand structure was key toward achieving different electrical conductivities in these metallopolymers with excellent operational stability under continuous cycling. High volumetric capacitances and energy densities combined with tunable electro-optical properties and electrochromic behavior of these metallopolymers are expected to contribute to high performance and compact microenergy storage systems. We envision that the integration of smart functionalities with thin film supercapacitors would warrant the surge of miniaturized on-chip microsupercapacitors integrated in-plane with other microelectronic devices for wearable applications. 2022 American Chemical Society. All rights reserved. -
A molecular QCA based UV lamp for water purification /
Patent Number: 201731011405, Applicant: Dr.Paramartha Dutta. -
A multi-layer memory enriched staticmemory system /
Patent Number: 202141039100, Applicant: Debarka Mukhopadhyay.
The present invention is configured with the generation of multiprocessor core of each 15 bit CAM cell and a section works at a lower supply area which will drive a part to work at a more prominent induced voltage for the CAM core processor. The present device is configured in such a way so that no level converters are required. The system operates avoiding the power overhead and low supply area as illustrated in Fig1. This process is used assorting voltage with less area interface inside the CAM cells, related by the applying product on D-FF. The match line indicates the search word and stored word are indistinguishable (the match case) or are extraordinary (a confounding case, or miss) of the CAM cell. -
A novel secured ledger platform for real-time transactions
The present disclosure relates to a new centralized ledger technology with a centralized validation process. It offers a single platform for all categories of real-time transactions and validations, unlike existing conventional blockchain technology. It offers three levels of hashing placed at the generator, server, and validator end for data security from data tampering and two levels of encryption for communication lines between generator-server and server-validator for packet security. This system ensures trustworthiness, authenticity, and CIA (confidentiality, integrity, and availability) to its end users while being real-time in execution. The proposed system does not follow a chain-based file architecture. Due to this, no concept of chain break arises, and the problems that arise as a result of chain break in the blockchain are avoided. 2022 Elsevier Inc. All rights reserved.