Browse Items (16481 total)
Sort by:
-
Automated Leukaemia Prediction and Classification Using Deep Learning Techniques
Leukemia is typically diagnosed based on an abnormal blood count, frequently an elevated White Blood Cell (WBC) count. The diagnosis is established through bone marrow, replaced by neoplastic cells. Acute Lymphoblastic Leukemia (ALL) is a type of leukaemia that affects the blood and bone marrow. Leukaemia primarily affects children and adults around the world. Early leukaemia detection is critical for appropriately treating patients, especially children. This research aims to present a diagnostic method that uses computational intelligence and image processing algorithms to identify blast cells from ALL images. The medical image is prepared initially using the preprocessing and segmentation technique for efficient classification. In this research, the type is accomplished using Bidirectional Associative Memory Neural Networks (BAMNN), where the accuracy is 96.87%, the highest classification rate and outperforms the existing technique. 2023 IEEE. -
Automated Leaf Disease Detection using a Hybrid CNN-BiLSTM Model for Smart Agriculture
The mitigation of crop losses and the sustainability of agriculture rely on the prompt identification of foliar diseases. In large-scale agriculture, conventional identification methods such as expert eye inspections are inefficient, susceptible to errors, and labour-intensive. A growing number of individuals are seeking automated methods to monitor plant health, given that the majority of Indians are employed in agriculture. This study presents a hybrid DL strategy for leaf disease detection, encompassing preprocessing, segmentation, feature extraction, and model training. Initially, images are processed to enhance their quality and uniformity. The impacted regions of the leaf are subsequently categorised by K-Means clustering. The classification accuracy is improved by utilising several feature extraction methods. The proposed model, CNBiLS, integrates bidirectional LSTM layers with convolutional layers to leverage the spatial and sequential information in image data. When evaluated against contemporary state-of-the-art models, CNBiLS exhibited superior performance, achieving an exceptional 99.84% classification accuracy. This result underscores the model's accuracy in identifying various leaf diseases. Ultimately, CNBiLS offers a precise, scalable, and robust automated system for detecting leaf diseases, equipping farmers with timely information to manage illnesses effectively, so enhancing both the quality and yield of their crops. 2025 IEEE. -
Automated hyperspectral image clustering using multilevel quantum differential evolution on quantum /
Patent Number: 202141013977, Applicant: Tulika Dutta.
Hyperspectral images are data cubes composed of huge spectral information. The spectral bands contain abundant information but are also full of redundant data. The huge information content also increases the space and time complexity to deal with hyperspectral images and due to Hughes phenomena, the accuracy also decreases with increase in information content. The constraint of research data and ground truth images of hyperspectral images is a real limitation of efficiently developing algorithms, especially supervised ones which require priori knowledge about the dataset. -
Automated Fetal Brain Localization, Segmentation, and Abnormalities Detection Through Random Sample Consensus
The ability to detect and identify prenatal brain abnormalities using magnetic resonance imaging (MRI) is critical, as one in every 1000 women is pregnant with one. The brain is abnormal. Detection of embryonic brain abnormalities at an early stage machine learning techniques can help you increase the quality of your data. Treatment planning and diagnosis according to the literature that the majority of the research done in order to classify brain abnormalities in the term "very early age" refers to preterm newborns and neonates, not fetal development. However, studies of prenatal brain MRI imaging have been published and compared these images to the MRI scans of newborns to identify a non-fetal aberrant behavior in neonates. In this case, a pipeline procedure, on the other hand, is time-consuming. In this research, a machine learning-based pipeline process for fetal brain categorization (FBC) is proposed. The classification of fetal brain anomalies at an early stage, before the baby is delivered, is the paper's key contribution. The proposed approach uses a flexible and simple method with cheap processing cost to detect and categorize a variety of abnormalities from MRI images with a wide range of fetal gestational age (GA). Segmentation, augmentation, feature extraction, and classification and detecting anomalies of the fbrain are different phases of the recent method. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Automated epileptic seizure classification using adaptive fast Fourier transform with non-uniform sampling and improved deep belief network
In automated brain-computer interaction (BCI), EEG signals are essential. This research uses AI to detect epileptic seizures, employing data from the BONN dataset (UCI), CHB-MIT dataset (physionet server), and Bangalore EEG Epilepsy Dataset (BEED). The goal is to develop an automated system for accurate seizure detection using adaptive fast Fourier transform with non-uniform sampling (AIFFT-NS) and an improved deep belief network (IDBN) model to enhance classification accuracy. The AIFFT-NS model serves as a channel for transforming spectro-temporal data. Using various EEG datasets, a number of extensive experiments are carried out, resulting in the validation of the efficacy of the proposed approach. High accuracy metrics, with 96.16% for the BEED dataset, 99.41% for the BONN dataset, and 96.31% for the CHB-MIT dataset, represent the evidentiary outcomes. This study emphasises the critical function of AI-facilitated spectro-temporal EEG analysis within the domain of medical diagnostics, going beyond the realm of automated seizure onset classification. Copyright 2024 Inderscience Enterprises Ltd. -
Automated Door with Password-Based Lock
The application of this work is to lock the door and ensure the safety of our space. This was done with heavy locks earlier. Locks do not ensure safety completely and there is a lot of tension around them. The main problem with traditional locks is that they are heavy, and their system is completely mechanical. The three basic ideas of this project are safety, privacy, and automation. This device is a password-based door lock system in which the door is opened and closed without any physical work, i.e. automatically. The key here is the password that the user has to enter to open the door. When the correct password is entered into the keypad, the microcontroller gives a command to the servo motor to rotate at a specific angle. If the incorrect password is entered, the motor will not do any operation and the user will not be allowed to enter. 2025 Author(s). -
Automated Diabetic Retinopathy Diagnosis Using Ensemble Approach
Diabetic Retinopathy is a major reason of vision impairment among diabetic patients, early and accurate diagnosis is crucial. This research focuses on developing a machine learning-based classification system to detect different stages of DR using Support Vector Machine (SVM), Random Forest (RF) and ensemble model. The dataset is divided into five categories: Healthy, Mild, Moderate, Proliferative and Severe DR. Performance evaluation using various metrics, including Accuracy, F1-score, RMSE and AUC-ROC, indicates that the ensemble model achieves the best results, with an accuracy of 77.66% and an AUC-ROC of 0.9015. The confusion matrices show that existing models struggle with certain misclassifications, the ensemble approach enhances overall predictive capability. Future improvements can include integrating deep learning models such as convolutional Neural Networks leveraging larger and more diverse datasets and incorporating image preprocessing techniques to enhance feature extraction. This system can help ophthalmologists to detect early and treatment planning, ultimately decrease the risk of blindness in diabetic patients. The Author(s), under exclusive license to Springer Nature Switzerland AG 2026. -
Automated Detection of Deepfakes using Integrated AI and Computer Vision Strategies
Deepfakes, or artificial intelligence-generated fake videos, are becoming a greater concern for online information trust, personal privacy, and digital content security. This paper presents a straightforward and understandable technique for automatically identifying deepfakes in order to address this significant problem. The approach makes use of conventional computer vision and machine learning methods. The model examines manually produced visual cues such as eye distance, mouth movement, and head tilt in video footage. To increase accuracy, it employs a variety of classifier types, including Random Forest, Gradient Boosting, and a soft Voting Classifier. A method known as SMOTE was used to clean and balance the data, and categorical data was transformed into a format suitable for machine learning models. With an F1-score of 0.9802 and 98% accuracy, the results demonstrate that the Voting Classifier, which combines several models, works admirably while being straightforward and effective. This method makes detection successful and simple to comprehend while offering a helpful tool for swiftly identifying deepfakes, especially on systems with constrained resources. 2025 IEEE. -
Automated Detection Model (ADM) for Glaucoma, Exudate and Diabetic Retinopathy (DR) Diagnosis Using Fundus Images
A total of 15 million people in India suffer from blindness yet statistical analysis shows 75% of these cases can be treated. The research shows DR and Glaucoma lead to blindness in India. Long-term diabetes mainly causes diabetic retinopathy which stands as the primary cause of blindness. Glaucoma damages the optic nerve until blindness develops. The digitized format of fundus images provides useful diagnostic information about infected retinas for proper eye disease detection. Eye defect diagnosis at an early stage enables medical care that greatly decreases patient vision loss risk. An ophthalmologist conducted the disease screening process through examination of fundus image abnormalities. Higher rates of DR and glaucoma prevalence do not affect the number of available ophthalmologists for evaluating fundus images so the prevention of diseases has been delayed. An automated analytical system should be developed presently to help ophthalmologists enhance their diagnostic process efficiency. The paper introduces an artificial learning methodology that utilizes concatenate systems to detect input fundus images in three categories namely ND and GI and EI and DRI. No Diseases (ND), ii. Glaucoma (GI) iii. The classification groups include Exudate infected Images (EI) along with two other categories namely Glaucoma (GI) and DR Images (DRI). The proposed model Automated Detection Model (ADM) starts by analyzing input samples with histogram-based model and employs DenseNet121 and Inception-ResNetV2to facilitate further processing. The Convolution Neural Networks (CNN) function gathers and sorts the feature extraction data obtained from both models. The proposed approach demonstrates improved accuracy and recall plus average precision when used instead of a solitary model. The proposed machine-learning approach using fundus images proves successful for Glaucoma, Exudate and DR diagnosis according to this experiment. 2025 IEEE. -
Automated Contactless Continuous Temperature Monitoring System for Pandemic Disease Controlling Infrastructures
People are being thermally screened in hospitals and in such facilities, all the data collected must be stored and displayed. The person responsible for keeping track of people's body temperatures must put in more time and effort. This approach is a tedious task, especially during times of dealing with the pandemic diseases like Covid-19. Hence, in this paper, an automated contactless continuous temperature monitoring system is designed to eliminate this time-consuming process. If a person's temperature is too high, that is, higher than the usual temperature range, the system records it and monitors it continuously via a mobile application. In this paper, we present the development of an Automated contactless continuous body temperature monitoring system using a Raspberry Pi camera and mobile application. 2023 IEEE. -
Automated Classification of Medicinal Plants Using Lightweight Deep Learning and Transfer Learning
The identification of medicinal plants plays a pivotal role in traditional medicine, biodiversity conservation, and rural healthcare. Conventional manual identification methods are often time-consuming and error-prone, particularly when differentiating between morphologically similar species or plants at varying growth stages. Recent developments in deep learning, especially convolutional neural networks (CNNs) with transfer learning, have emerged as robust solutions for image-based classification tasks, offering efficiency and high accuracy with limited computational resources. The proposed framework employs a carefully structured deep learning pipeline integrating advanced preprocessing, lightweight architecture design, and domain-adaptive transfer learning. A large real-world dataset of 20,109 medicinal leaf images across 99 classes was standardized through resizing, normalization, and categorical encoding, followed by targeted data augmentation and class-weight balancing to address inter-class similarity and dataset imbalance. A key methodological novelty lies in the use of MobileNetV3 with an optimized transfer-learning strategy, leveraging its inverted residual blocks, Squeeze-and-Excite modules, and hard-swish activation to enhance texture-, venation-, and contour-based feature extraction in plant leaves. Unlike existing plant-recognition studies that rely on heavier CNNs, our approach introduces a computationally efficient, low-latency model specifically tailored for mobile and embedded deployment. Experimental results demonstrate that the proposed MobileNetV3-based model achieved a classification accuracy of 92.88%, with macro- and weighted-average F1-scores of 0.85 and 0.86, respectively. Precision and recall values across most classes ranged between 0.80 and 0.95, confirming the models reliability in differentiating species. The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2026. -
Automated Brain Tumor Segmentation in MRI Using AI for Improved Neurodiagnostics
Early and accurate classification of brain tumors plays a pivotal role in clinical decision-making and treatment planning. Manual methods are time-intensive and prone to variability, creating a need for robust automated solutions. This study aims to classify brain tumors from MRI scans using artificial intelligence techniques, specifically Logistic Regression (LR) and Support Vector Machines (SVM) with Radial Basis Function (RBF) kernels. The dataset, sourced from The Cancer Imaging Archive (TCIA), includes four classes: Meningioma, Glioma, Hypothalamic tumor, and No tumor. Preprocessing involved dimensionality reduction using Principal Component Analysis (PCA) to retain dominant features. Models were trained on an 80:20 train-test split, with LR achieving 99.83% training and 78.91% testing accuracy, while SVM performed better with 93.85% training and 81.88% testing accuracy. Error analysis revealed 104 misclassified samples, primarily due to structural similarity among tumor types. The findings suggest that SVM offers superior classification performance, and the study recommends further enhancement through deep learning models like Convolutional Neural Networks (CNNs) for improved diagnostic accuracy. 2025 Oriental Scientific Publishing Company. All rights reserved. -
Automated Brain Imaging Diagnosis and Classification Model using Rat Swarm Optimization with Deep Learning based Capsule Network
Earlier identification of brain tumor (BT) is essential to increase the survival rate of the patients. The commonly used imaging technique for BT diagnosis is magnetic resonance imaging (MRI). Automated BT classification model is required for assisting the radiologists to save time and enhance efficiency. The classification of BT is difficult owing to the non-uniform shapes of tumors and location of tumors in the brain. Therefore, deep learning (DL) models can be employed for the effective identification, prediction, and diagnosis of diseases. In this view, this paper presents an automated BT diagnosis using rat swarm optimization (RSO) with deep learning based capsule network (DLCN) model, named RSO-DLCN model. The presented RSO-DLCN model involves bilateral filtering (BF) based preprocessing to enhance the quality of the MRI. Besides, non-iterative grabcut based segmentation (NIGCS) technique is applied to detect the affected tumor regions. In addition, DLCN model based feature extractor with RSO algorithm based parameter optimization processes takes place. Finally, extreme learning machine with stacked autoencoder (ELM-SA) based classifier is employed for the effective classification of BT. For validating the BT diagnostic performance of the presented RSO-DLCN model, an extensive set of simulations were carried out and the results are inspected under diverse dimensions. The simulation outcome demonstrated the promising results of the RSO-DLCN model on BT diagnosis with the sensitivity of 98.4%, specificity of 99%, and accuracy of 98.7%. 2023 World Scientific Publishing Company. -
Automated and Interpretable Fake News Detection With Explainable Artificial Intelligence
Fake news is a piece of misleading or forged information that affects society, business, governments, etc., hence is an imperative issue. The solution presented here to detect fake news involves purely using rigorous machine learning approaches in implementing a hybrid of simple yet accurate fake text detection models and fake image detection models to detect fake news. The solution considers the text and images of any news article, extracted using web scraping, where the text segment of a news article is analyzed using an ensemble model of the Nae Bayes, Random Forest, and Decision Tree classifier, which showed improved results than the individual models. The image segment of a news article is analyzed using only a Convolution Neural Network, which showed optimal accuracy similar to the text model. To better train the text models, data preprocessing and aggregation methods were used to combine various fake-real news datasets to have ample amounts of data. Similarly, the CASIA dataset was used to train the image model, over which Error Level Analysis was performed to detect fake images. model results are represented as confusion matrices and are measured using various performance metrics. Also, to explain predictions from the hybrid model, Explainable Artificial Intelligence is used. 2024 Taylor & Francis Group, LLC. -
Automate Threat Detection and Analysis Through Intelligent Data Mining Techniques for Network Traffic and Cybersecurity
Today, we are constantly surrounded by vast amounts of data, a trend that is expected to grow significantly over the next decade. The abundance of data presents challenges for thorough analysis and extraction of valuable insights buried within unstructured information. Advanced tools like data mining are crucial in uncovering this useful information and making full use of it. In light of the increasing number of security threats in networks, there is a need for robust security solutions. While traditional network security measures have been primarily managed locally, concerns about internet-based security have grown due to heightened computer usage leading to cybercriminal activities previously limited to physical intrusions. A threat intelligence program aims to enhance analytical and preventive capabilities by acquiring knowledge about potential or existing threats based on evidence. As most devices are interconnected with the Internet, many organizations prioritize cybersecurity as they acknowledge the vulnerabilities arising from this connectivityproviding opportunities for cyber-attacks. Effective threat intelligence concerning network traffic necessitates a comprehensive understanding supported by thoughtful representation techniques. This paper proposes an extensive exploration of various machine learning methods aimed at identifying weaknesses in detecting invasive activity using different approaches and evaluating their performance against the KDD 99 benchmark dataset. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Autoimmune diseases and an approach to type 1 diabetes analysis using PSO, K-means, and silhouette values
An estimated 50 million Americans suffer from autoimmune diseases, as per the report from AARDA (American Autoimmune Related Diseases Association). More than 30 million people suffer in India from type 1 diabetes. More than $100 billion is spent on healthcare for autoimmune diseases in America, more than for cancer healthcare. Host genes and environmental factors control autoimmune diseases, and typically they do not have any specific cure. This paper proposes an artificial intelligence-based framework for the initial prediction of autoimmune diseases. This work attempts to identify characteristics of autoimmune diseases, and it lists the commonly occurring autoimmune diseases, the organs attacked by them, and the different stages involved. It also seeks to identify ways to prioritize the severity of the patient's disease, for providing treatments based on the severity, with the goal of reducing the pressure on the healthcare sector. Type 1 diabetes is an autoimmune disease and identifying the risk associated with diabetes and other related health problems could help to improve health worldwide. This work proposes a framework while exploring autoimmune disease prediction using machine learning techniques. The autoimmune disease considered is type 1 diabetes. The usage of machine learning techniques can help to enhance patient care and early prediction. This research is an attempt to explore the possibilities and also to propose a framework for early prediction of type 1 diabetes. Clustering is performed using K-means and PSO K-means. Validation of the clusters is carried out using silhouette coefficient. 2024 Elsevier Inc. All rights are reserved including those for text and data mining AI training and similar technologies. -
Auto-encoder Convolut?onal Neural Network (AECNN) for Apple Fruit Flower Detection
The yield estimation task altogether relies upon the way toward identifying and checking the quantity of fruits on trees. In production of fruit, basic yield the board choices are guided through the bloom frequency, i.e., the quantity of the flowers that are present in a plantation. The intensity of bloom technique is still commonly assessed by methods for human visual investigation. Mechanized PC vision frameworks for flower recognizable proof depend closely on designed procedures which function just under explicit conditions and with restricted execution. This work comprises four significant advances, (I) system preparing for Fully Convolutional Network (FCN), (ii) preprocessing, (iii) component extraction, (iv) division. Initially, a strategy for assessing high-resolution pictures with deep FCN on Graphics Processing Unit (GPU). Then, non-linear and linear algorithms are presented for lessening the image noise, so the exact flower identification can be ensured. The next phase of the work handles the highlight extraction for diminishing the quality of the prime assets which are needed for handling without compromising on data applicable. By applying Local Binary Pattern (LBP), surface example likelihood can be summed up into a histogram. At last, isolate an image with high resolution into sub patches, assess all patches with the help of AECNN, at that point apply the refinement calculation on acquired score maps to figure out the final version of the mask segmentation. Trial results are led utilizing two datasets on flower pictures of AppleA and AppleB. Results are estimated regarding the measurements like Precision (P) and Recall (R). The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Auto-diagnosis of covid-19 using lung ct images with semi-supervised shallow learning network
In the current world pandemic situation, the contagious Novel Coronavirus Disease 2019 (COVID-19) has raised a real threat to human lives owing to infection on lung cells and human respiratory systems. It is a daunting task for the researchers to find suitable infection patterns on lung CT images for automated diagnosis of COVID-19. A novel integrated semi-supervised shallow neural network framework comprising a Parallel Quantum-Inspired Self-supervised Network (PQIS-Net) for automatic segmentation of lung CT images followed by Fully Connected (FC) layers, is proposed in this article. The proposed PQIS-Net model is aimed at providing fully automated segmentation of lung CT slices without incorporating pre-trained convolutional neural network based models. A parallel trinity of layered structure of quantum bits are interconnected using an N -connected second order neighborhood-based topology in the suggested PQIS-Net architecture for segmentation of lung CT slices with wide variations of local intensities. A random patch-based classification on PQIS-Net segmented slices is incorporated at the classification layers of the suggested semi-supervised shallow neural network framework. Intensive experiments have been conducted using three publicly available data sets, one for purely segmentation task and the other two for classification (COVID-19 diagnosis). The experimental outcome on segmentation of CT slices using self-supervised PQIS-Net and the diagnosis efficiency (Accuracy, Precision and AUC) of the integrated semi-supervised shallow framework is found to be promising. The proposed model is also found to be superior than the best state-of-the-art techniques and pre-trained convolutional neural network-based models, specially in COVID-19 and Mycoplasma Pneumonia (MP) screening. 2013 IEEE. -
Auto configuration of refrigeration systems in cold chain /
Patent Number: US 9,384,458 B2, Applicant: Thermo King Corporation.
An environmentally-controlled structure for a cold chain. The structure includes a sensor, an identification reader, an environment implementer, and a controller. The sensor senses a parameter indicative of an environmental condition in the environmentally-controlled structure. -
Autism Spectrum Disorder: Automated Detection based on rs-fMRI images using CNN
Autism spectrum disorder (ASD) impacts approximately 1 in every 160 children globally and is classified as a neurodevelopmental condition. Image classification in neuroscience has advanced primarily due to convolutional neural networks (CNNs) and their capacity to provide better algorithms, more computing resources, and data. This study used a brain scan dataset to test the feasibility of utilizing CNN to detect ASD. Using functional connectivity patterns, the Autism Brain Imaging Exchange (ABIDE) data repository, which includes recordings of rest-state functional magnetic resonance imaging (rs-fMRI), the aim of using it was to distinguish between individuals who have Autism Spectrum Disorder (ASD) and those who are healthy controls. The proposed method effectively classified the two groups. According to the test findings, the suggested model has the ability to accurately detect ASD with a reliability rate of 92.22% when implemented on the ABIDE dataset using the CC200, CC400, and AAL116 brain atlases. The CNN model is computationally more efficient since it uses fewer parameters than other cutting-edge methods. 2023 IEEE.