In an era of rapidly advancing technology, the need for secure and efficient electoral processes has never been more crucial. Therefore, a comprehensive voting system is proposed, leveraging the power of Hyperledger Iroha and seamlessly integrating with Django and React frameworks. The system offers a user-friendly android application for voters and a separate administration portal for efficient election management. The Hyperledger Iroha framework forms the backbone of the system, providing a robust and tamper-proof ledger for recording votes. It Brings the power of permission-based blockchain with Yet Another Consensus algorithm. Furthermore, the versatile architecture of this system extends its applicability beyond democratic elections, offering a flexible framework for various voting scenarios, including corporate decision-making, community polls, and organizational surveys. Through this innovative amalgamation of technologies, the project aims to set a new standard for secure and efficient voting systems, contributing to the advancement of democratic practices worldwide.

The global incidence of diabetes is steadily increasing, necessitating timely identification and intervention to reduce its impact. Diabetic-Retinopathy (DR) is a prevalent complication of diabetes and a primary cause of global blindness. Timely identification and intervention are crucial in order to regulate his severity. The detection of diabetic retinopathy (DR) at the clinical level is frequently conducted using image-supported approaches. The present study introduces a deep-learning (DL) technique designed for the automated identification of diabetic retinopathy (DR) by utilizing retinal fundus images (FI). The research procedure involves several stages: collecting retinal FI and performing initial processing, extracting features using selected deep learning algorithms, reducing features and combining them, and performing bi-level classification and confirming performance. This study examines the DenseNet121 (DN121) scheme and conducts bi-level classification using the SoftMax and other selected classifiers. The findings of this study validate that the DN121 model achieves classification accuracy over 91% when using individual features with SoftMax, and surpasses 98% when utilizing fused features with the Decision Tree classifier. This study yielded a noteworthy outcome, and the suggested deep learning method can be regarded as a viable option for assessing the clinical grade of retinal fibrosis in the future.

Dental caries (DC), sometimes called tooth decay, is a bacterial illness that demineralizes and destroys the tooth's complex structures, leaving cavities or holes in the teeth. DC may result in abscesses and tooth loss if left untreated. It is strongly advised that DC be diagnosed and treated as soon as possible. Clinical evaluations usually involve a dentist's ocular assessment and then radiograph-supported screening. This project aims to create an AI-supported system for radiograph-based dental caries detection. The suggested method uses a Convolutional Neural Network (CNN) architecture to find the DC region in digital radiographs. The work combines CNN segmentation with picture pre-processing to increase detection accuracy. The suggested tool's efficacy is assessed on a chosen database, and the experimental findings verify that the scheme can successfully identify DC using VGG-UNet with an accuracy of over 98%, surpassing the performance of UNet, SegNet, and UNet+.

To handle the variety of digital data, a significant number of automatic data examination techniques have been created recently. These algorithms are essential for analyzing image data in many different fields, including agriculture. One frequent activity in agriculture is plant health monitoring using image processing, and the goal of this research is to provide a way for more accurately classifying plant leaf data into the healthy and disease classes. Data on tomato plant leaves were selected for this investigation. This system consists of three stages: binary classification with 3-fold cross validation and verification, deep feature mining with a selected algorithm, and image collection and resizing. The pre-processed image helps to obtain an enhanced outcome compared to the raw leaf data, according to the experimental results of this work, which is conducted utilizing the selected pre-trained models employing the raw and pre-processed photos. In this study, a binary classification utilizing SoftMax is implemented. The detection accuracy of the data, both raw and pre-processed using adaptive thresholding, is >88% and >92%, respectively. This study validates that, when applied to the selected leaf data, the suggested technique yields superior results.

Individuals with Dental Abnormality (DA) have minor to severe health difficulties; therefore, prompt detection and treatment are essential. A typical method for diagnosing DA at the clinical level is image-supported screening. The goal of this project is to create a unique Unified Deep-Learning (UDL) approach for caries identification in teeth from non-invasive digital pictures. This scheme consists of the following stages: (i) taking pictures with a digital camera; (ii) resizing and processing the images; (iii) putting the UDL model for tooth and caries identification into practice; and (iv) verifying and evaluating the scheme's performance. In this work, the Region Proposal Network (RPN) is integrated with the pre-trained MIDNet18 to create the UDL scheme. The effectiveness of this UDL model is tested against the current segmentation strategy, and its effectiveness is validated by the obtained outcomes. The main benefit of UDL-based detection is that the suggested method is easy to use and effective in identifying dental caries in the selected digital photos. Furthermore, when compared to other sophisticated image capture and evaluation methods already in use in dental clinics, the adopted UDL model is straightforward and trustworthy.

In human physiology, lungs are chief part of the respiration system and infection in lung is a medical emergency. Pneumonia is one of the lung infections, which severely affects the respiration system and may cause severe illness in children and elderly. The early diagnosis of the pneumonia is essential and the clinical level assessment of pneumonia's severity will be assessed clinically using chest X-Ray. This research aims in developing a deep-learning supported tool for pneumonia (viral+bacterial) detection. The phases of this tool includes; data collection, resizing and contrast enhancement, feature extraction with pre-trained deep-learning (PD) method, deep-features reduction with 50% dropout and serial features integration, and binary classification and verification. The experimental investigation is performed on the chosen database using; (i) individual deep-feature, and (ii) reduced-features and (iii) fused deep-features. During this investigation, Random-Forest (RF) assisted classification is executed and this process provided an accuracy of >98% when the fused deep-features are considered. In the future, the performance of this scheme can be verified using the Covid19 database found in the literature.

Lung is a vital internal organ responsible for the respiration process. Abnormality in the lung causes mild to severe illness and may lead to death. Tuberculosis (TB) is a common disease in people, and it is very important to find and treat it quickly. At the clinical level, chest x-rays are used to diagnose TB, and based on the results, the right treatment needs to be started. The suggested study aims to use DenseNet (DN) variants and deep transfer learning (DTL) to sort chest X-rays into two groups: healthy and TB. The plan that was put into action has five steps: collecting and resizing data, deep-features mining using DN variants, feature reduction and serial features fusion, and binary classification and verification. In this paper, the performance of the system that was built is tested using both separate and combined features. Several binary classifiers are used to complete the classification job. The results of this study show that the detection accuracy is >91% with individual features and 99% when fused features are taken into account. This proves that the plan that was put in place works better on the chosen image database.

Diabetes is a chronic illness usually caused by elevated blood glucose levels. If left untreated, diabetes can have serious repercussions. Diabetic foot ulcers (DFUs) is a chief complications of diabetes, which can result in foot wounds and, if left untreated, can amputation of a limb or leg. A visual examination by the physician is typically used to identify the DFU at the clinical level and assess its severity. This research aims to create a computer program that can identify DFU from digital photos taken using a camera. The stages of the developed technique are as follows: gathering and processing DFU images, extracting features using a selected deep-learning (DL) scheme, reducing and fusing features, and classifying the results using five-fold cross-validation. In this research, the benchmark DFU images were taken into consideration, and MobileNet (MN) and its variations were used to carry out the classification task. Using the individual deep-features, the proposed DFU detection task is first carried out. Afterwards, the selected features are serially fused to obtain a new feature vector, and the proposed work is repeated. The study's experimental results validate the developed technique's merit, as the K-Nearest Neighbor classifier achieves 97% detection accuracy.

Disease in brain is one of the medical emergencies and appropriate diagnoses and treatment is necessary. Medical imaging-assisted Brain Condition Monitoring (BCM) is one of the common clinical procedures, and Magnetic Resonance Imaging (MRI) is a standard modality for BCM. This research presents a unique BCM scheme utilizing the deep-learning procedure. Several stages of this arrangement includes the following; MRI slice resizing, feature extraction using deep-learning procedure, feature optimization with Geometric Mean Optimizer (GMO), feature fusion and binary classification. In this work, brain tumour detection is presented. This work is implemented using individual, fused and ensemble of features. The investigational outcome authorizes that this arrangement works fine on the brain tumour detection task using the benchmark image datasets. The proposed approach helped to accomplish a BT recognition accuracy of 100% with the Support Vector Machine (SVM) using ensemble features. This confirms that the proposed MRI-supported BCM arrangement worked well on the chosen image database.

The segmentation and analysis of forests from satellite images play a vital role in the comprehensive monitoring and effective management of ecosystems. This process facilitates precise evaluations of various critical aspects such as forest cover, biodiversity, and overall health. By connecting this information, resource planning becomes more informed and strategic, contributing to sustainable forest management practices. Moreover, the data derived from satellite imagery aids in identifying areas susceptible to deforestation, allowing for timely intervention to mitigate its adverse environmental impacts. The integration of advanced satellite technologies in forest analysis enhances the ability to address contemporary environmental challenges, providing a foundation for policies and practices that promote ecological resilience and the long-term well-being of our planet. In this work, VGG-UNet is implemented to segment the forest and it achieved an accuracy of >94%, which is better compared to other existing methods in the literature.

A lot of different fields, including agriculture, use automatic data handling. Using computer algorithms to handle agricultural data has become an important way to keep an eye on crops at different times. The goal of this study is to create a tool that can use deep transfer learning (DTL) to find plant diseases by looking at pictures of their leaves. This plan has three steps: collecting and preprocessing images, reducing features with DTL, and classifying images into two groups using five-fold cross validation. A small group of well-known, lightweight models that support transfer learning are used to test how well the suggested tool works. The proposed classification job is carried out using the SoftMax classifier, and the accuracy of the detections shows that this method works. As proof in the real world, pictures of strawberry leaves were used, and the method helped achieve detection accuracy of 100% when ResNet18 was used and over 97% when MobileNet was used. These results show that the suggested tool with the DTL does a good job on the picked database.

Computer algorithm plays a vital role in image examination tasks and hence a number of methods are developed to process grey- and RGB-scaled images. This work considered the examination of the satellite images using MobileNet (MN) based classification system. This work considered the benchmark satellite images having the lake and the satellite images and the obtained images are examined using the following procedures; image collection and resizing, image improvement using the contrast enhancement technique, implementing the MN-approach to extract the necessary features from the image, and binary classification to detect the lake and the river from the chosen images. In this work, lightweight deep-learning technique is implemented by considering the MN and its variants and the obtained result is confirmed and verified. The experimental outcome confirms that the MN - V2 provides a better detection result (accuracy >96%) compared to other MN-schemes of this study.

Skin is one of the largest sensory organs in the human physiology and the abnormality in skin will lead to various complications. Skin melanoma is one of the harsh conditions and the untreated melanoma will lead to death due to the cancer. Early diagnosis and treatment is essential and the clinical level detection is done using the dermoscopy. This work aims to implement the deep learning based benign/malignant melanoma classification. The various phases in this tool includes; data collection and preprocessing, deep-features mining, features reduction using the Bat Algorithm (BA), and classification and performance verification. The proposed work considers the lightweight deep-learning tool to examine the chosen image database. During this task, the MobileNet-variants and the NasNetvariants are considered for the study. The classification executed using the MobileNetV2 provided an accuracy of 92.50% and the NasNetMobile based detection offered an accuracy of 91.50%. The serially integrated deep-features based detection helped to get 98% accuracy when the Support Vector Machine classifier is considered. This confirms that the implemented scheme provided better detection accuracy.

Every business has a responsibility to understand the needs of the consumer and produce the products accordingly. The upsurge of any sales in a product an depend on a variety of factors. To reach the targeted business goals, every company must contribute to the needs of business. But most importantly, it is required to understand the trends and analytics in the current data. The purpose of business customer segmentation is to briefly understand the progression in the recent interests of the customers. The process helps to understand the depth of what the customer really needs. The aggregation of prospective buyers into groups or segments with common needs actually ensures there is consistent profit annually. The research draws a clear picture on how to ascertain growth and minimise risks of loss in a skin care cosmetics company using the Marketing Segmentation technique.

Cancer disease caused a major death in worldwide. To prevent this, various cancer classification approaches are employed, which are mostly relied on clinical characteristics and histopathological characteristics. Deep learning-based classification models are very effective and accurate. As a result, this research established the Adam-based Deep Quantum Neural Network, which is the optimal deep learning-based cancer classification method. The information on gene expression is used to classify cancer. Using the Box-Cox transformation, which converts the data into a legible format, the data transformation procedure is carried out. Utilizing information gain, the features are chosen in order to choose the proper gene expression. Additionally, Deep QNN is used to classify cancer, and for better classification, which is trained via Adam optimization. The experimental result shows the developed model provide better classification result with respect to accuracy, true positive rate and true negative rate of 94.91%, 95.59% and 95.4%.

Efficient approaches to estimating and understanding student performance are paramount in the dynamic landscape of higher education. This paper introduces "AData-driven Predictive ApproachUsing Custom and Regression Models for Estimating Student’s Performance," aiming to provide educators with valuable insights into academic outcomes. By integrating specific academic data sources and employing regression analysis, machine learning algorithms, and other data-driven methodologies, educators can gain actionable insights into student performance trends through predictive modeling. The paper delves into the technical complexities of the strategy, outlining methodologies and presenting practical implementations through illustrative examples and case studies. The ethical considerations of data usage and privacy are carefully investigated, emphasizing responsible implementation in the educational context. Pilot implementations in real-world educational settings are explored, shedding light on the strategy’s efficacy and potential impact on educators and students. This study represents a significant advancement in using data-driven strategies to estimate student performance in higher education, envisioning a future where educators are equipped with valuable tools to understand and support each student’s academic journey comprehensively.

The rising complexity of information communication technology has greatly affected communication through conventional broadcast media over the past decade. Smartphone applications are increasingly emasculating the new socio-economic broadcasting environment. The trend is the same in the workplace, at home and in recreation. Social networking has stolen the game and is increasingly shifting to another age, the era of “digital relationships,” in which conventional interpersonal social interactions are replaced by mobile devices and social networks. The consequences of such false information promoted by miscreants and apologists for social media are far-reaching because it has resulted in scandals in households, communities, partnerships, organizations, and culture as a whole. The purpose of this paper is to lead to the eradication of counterfeit media by the use of technology. In this article, we proposed and built a model that incorporates neural networks to identify and eradicate false phrases posted to social media networks and web forums. Also, we compared our work Elmo VNetwith current state-of the-art models. The experimental results demonstrated that the proposed Elmo VNetmodel have better accuracy rate than the existing models.

Loans are important aspect of any banks. Any loan application's approval or denial directly affects the bank's income and profitability. Many people come to bank for availing loans and banks have limited funds in their accounts. To approve the loan in this situation, the proper applicant must be chosen. This will make a profitable situation to both banks and customers from which both of them will be benefited and reduce the risk of loss of money. Therefore in order to make an effective loan approval many machine learning prediction models are used in our work. In order to overcome the problem of loan going into default by identifying whether the customer is eligible for loan and to help customers keep a good credit score by avoiding the loans which they cannot repay. The prediction is performed by data pre processing techniques to clean the dataset and give accurate data for training the machine learning models. Many machine learning models which are mainly used for classification algorithm are trained and are tested in our work for predicting whether to approve a loan applicant or not. Baseline modeling and KFold cross validation techniques are used to check the accuracy of models and the model with highest accuracy is taken for consideration of developing the loan approval prediction model. This trained model is then turned to receive the inputs from the user and give the predictions results as the output.

Here, SnS thin films having p and n-type conductivity were fabricated using vacuum-free deposition techniques such as chemical bath deposition (CBD) and chemical spray pyrolysis technique (CSB). The fabricated thin films were subjected to structural, morphological, optical, and electrical analysis using various characterization techniques. The direct optical bandgaps of the SnS-based thin films are 1.80 eV and 1.66 eV. The absorption coefficient of SnS thin films fabricated by the CSP technique is 105 cm−1. The electrical properties of SnS thin films were analyzed by a hall measurement system. The type of conductivity obtained for the SnS thin films was different for both deposition techniques. In the CBD method, p-type conductivity were obtained for SnS films. The SnS thin films fabricated by the CSP technique possess n-type conductivity. The optimum bandgap, high absorption coefficient, type conversion nature and suitable morphology helps the material as potential candidate for thin film based energy generation and energy conversion applications.

Abstract SrTiO3 and SrTiO3/GO nanocomposites were synthesized by varying hydrothermal reaction period as 12, 24 and 48 h. XRD analysis confirms the crystal structure of prepared samples. Morphological changes from spherical to cubic with increased growth period was confirmed by SEM and TEM. The functional groups in GO and SrTiO3/GO were studied by FTIR. From Raman Spectrum, Id/Ig ratio was calculated which reveals the formation of GO. The electrical resistivity of 48 h samples were relatively lower than that of other samples. Seebeck Coefficient of 24 h and 48 h samples were higher than that of as prepared sample. From the obtained Seebeck coefficient and electrical resistivity, the power factor was calculated. The 48 h sample exhibited relatively high power factor of 0.70 × 10− 6 Wm− 1K− 2 at 450 K compared to other samples. Thus, GO plays an important role in enhancing the power factor of SrTiO3/GO nanocomposites.