12 research outputs found
Performance Comparison of Machine Learning and Deep Learning Models for Sentiment Analysis of Hotel Reviews
No full textThis research paper conducts a thorough examination, comparing BERT and LSTM architectures with machine learning models for sentiment classification task. To establish a foundational reference point, conventional machine learning algorithms including Logistic Regression (LR), Support Vector Machines (SVM), Random Forest (RF), Decision Tree (DT) and BernoulliNB are utilized. The BERT and LSTM models along with machine learning models have been implemented and trained using a dataset comprising hotel reviews. Their performance has been assessed through the utilization of multiple metrics, including accuracy, precision, recall, and F1-score. In the context of text classification and sentiment analysis tasks, the experimental outcomes highlight the superior effectiveness of BERT and LSTM models when compared to traditional machine learning algorithms. The BERT model distinguishes itself through the incorporation of bidirectional training and contextual embedding strategies, ultimately showcasing outstanding performance in its ability to proficiently capture contextual information and subtle nuances prevalent in textual data. Moreover, the LSTM technique has been able to attain noteworthy outcomes through its effective modeling of sequential data and preservation of temporal dependencies. The present research yields significant findings regarding the comparative analysis of machine learning models employing BERT and LSTM architectures concerning text classification and sentiment analysis. The results of this study provide valuable insights into the merits and constraints of each model, thereby aiding researchers and practitioners in making informed decisions when choosing suitable models that are customized for specific natural language processing (NLP) tasks
Conceptualization of Software Defined Network layers over internet of things for future smart cities applications
No full textBlockchain enabled IoMT and transfer learning for ocular disease classification
No full textAbstract For detecting and diagnosing a wide range of ophthalmological diseases, fundus images are used as a primary and basic tool. Early and accurate diagnosis of these ocular diseases can substantially improve the quality of treatment as well as important for preventing permanent vision loss. Changes in the anatomical structures like the optic disc, macula, blood vessels, and fovea show the presence of diseases like age-related macular degeneration, glaucoma, diabetic retinopathy, cataracts, myopia, and hypertension. In the proposed work, six different automated convolutional neural network architectures based on the Internet of Medical Things (IoMT) using transfer learning techniques were implemented for the classification of fundus images that can detect ocular diseases. These pre-trained neural networks were tuned by modifying the four layers before training them on the dataset. The proposed models incorporate blockchain technology-based private clouds for the security of the patient’s data. Transfer learning provides a promising framework with the combination of IoMT technologies and blockchain technology layers to enhance the diagnosing capabilities of Ocular disease. An ocular disease dataset was used, which was classified into four classes Cataract, Glaucoma, Myopia, and AMD. Class-wise Accuracy, Precision, Sensitivity, F1 Score, Specificity, and Misclassification Rate were computed with up to 96.88% training and 95.40% testing accuracy. The second part of this research is a comparative analysis of implemented models. The performance of AlexNet, GoogleNet, MobileNetV2, DarkNet-19, VGG-19, and DenseNet-201 compared in terms of accuracy. GoogleNet yielded unquestionably impressive results when compared to AlexNet and MobileNetV2
Transfer learning for accurate brain tumor classification in MRI: a step forward in medical diagnostics
No full textAbstract Brain tumor classification is critical for therapeutic applications that benefit from computer-aided diagnostics. Misdiagnosing a brain tumor can significantly reduce a patient's chances of survival, as it may lead to ineffective treatments. This study proposes a novel approach for classifying brain tumors in MRI images using Transfer Learning (TL) with state-of-the-art deep learning models: AlexNet, MobileNetV2, and GoogleNet. Unlike previous studies that often focus on a single model, our work comprehensively compares these architectures, fine-tuned specifically for brain tumor classification. We utilize a publicly available dataset of 4,517 MRI scans, consisting of three prevalent types of brain tumors—glioma (1,129 images), meningioma (1,134 images), and pituitary tumors (1,138 images)—as well as 1,116 images of normal brains (no tumor). Our approach addresses key research gaps, including class imbalance, through data augmentation and model efficiency, leveraging lightweight architectures like MobileNetV2. The GoogleNet model achieves the highest classification accuracy of 99.2%, outperforming previous studies using the same dataset. This demonstrates the potential of our approach to assist physicians in making rapid and precise decisions, thereby improving patient outcomes. The results highlight the effectiveness of TL in medical diagnostics and its potential for real-world clinical deployment. This study advances the field of brain tumor classification and provides a robust framework for future research in medical image analysis
Voice biomarkers as prognostic indicators for Parkinson’s disease using machine learning techniques
No full textAbstract Many people suffer from Parkinson’s disease globally, a complicated neurological condition caused by the deficiency of dopamine, an organic chemical responsible for regulating movement in individuals. Patients with Parkinson face muscle stiffness or rigidity, tremors, vocal impairment, slow movement, loss of facial expressions, and problems with balance and coordination. As there is no cure for Parkinson, early diagnosis can help prevent the progression of this disease. The study explores the potential of vocal measures as significant indicators for early prediction of Parkinson. Different machine learning models such as Support Vector Machine (SVM), Random Forest (RF), Logistic Regression (LR), and Decision Tree (DT) are used to detect Parkinson using voice measures and differentiate between the healthy and Parkinson patients. The dataset contains 195 vocal recordings from 31 patients. The Synthetic Minority Over-Sampling Technique (SMOTE) is used for handling class imbalance to improve the performance of the models. The Principal Component Analysis (PCA) method was used for feature selection. The study uses different parameters to evaluate the model’s classification results. The results highlight RF as the most effective model with an accuracy of 94% and a precision of 94%. In addition, SVM achieves an accuracy score of 92%, and precision of 91%. However, with the PCA method, SVM achieves an accuracy of 89%, 92%, and 87% for RF and DT respectively. This study highlights the significance of using vocal features along with advanced machine learning methods to reliably diagnose Parkinson’s disease, considering the challenges associated with early detection
MobNas ensembled model for breast cancer prediction
No full textAbstract Breast cancer poses a real and immense threat to humankind, thus a need to develop a way of diagnosing this devastating disease early, accurately, and in a simpler manner. Thus, while substantial progress has been made in developing machine learning algorithms, deep learning, and transfer learning models, issues with diagnostic accuracy and minimizing diagnostic errors persist. This paper introduces MobNAS, a model that uses MobileNetV2 and NASNetLarge to sort breast cancer images into benign, malignant, or normal classes. The study employs a multi-class classification design and uses a publicly available dataset comprising 1,578 ultrasound images, including 891 benign, 421 malignant, and 266 normal cases. By deploying MobileNetV2, it is easy to work well on devices with less computational capability than is used by NASNetLarge, which enhances its applicability and effectiveness in other tasks. The performance of the proposed MobNAS model was tested on the breast cancer image dataset, and the accuracy level achieved was 97%, the Mean Absolute Error (MAE) was 0.05, and the Matthews Correlation Coefficient (MCC) was 95%. From the findings of this research, it is evident that MobNAS can enhance diagnostic accuracy and reduce existing shortcomings in breast cancer detection
Automatic melanoma and non-melanoma skin cancer diagnosis using advanced adaptive fine-tuned convolution neural networks
No full textAbstract Skin Cancer is an extensive and possibly dangerous disorder that requires early detection for effective treatment. Add specific global statistics on skin cancer prevalence and mortality to emphasize the importance of early detection. Example: “Skin cancer accounts for 1 in 5 diagnosed cancers globally, with melanoma causing over 60,000 deaths annually. Manual skin cancer screening is both time-intensive and expensive. Deep learning (DL) techniques have shown exceptional performance in various applications and have been applied to systematize skin cancer diagnosis. However, training DL models for skin cancer diagnosis is challenging due to limited available data and the risk of overfitting. Traditionally approaches have High computational costs, a lack of interpretability, deal with numerous hyperparameters and spatial variation have always been problems with machine learning (ML) and DL. An innovative method called adaptive learning has been developed to overcome these problems. In this research, we advise an intelligent computer-aided system for automatic skin cancer diagnosis using a two-stage transfer learning approach and Pre-trained Convolutional Neural Networks (CNNs). CNNs are well-suited for learning hierarchical features from images. Annotated skin cancer photographs are utilized to detect ROIs and reset the initial layer of the pre-trained CNN. The lower-level layers learn about the characteristics and patterns of lesions and unaffected areas by fine-tuning the model. To capture high-level, global features specific to skin cancer, we replace the fully connected (FC) layers, responsible for encoding such features, with a new FC layer based on principal component analysis (PCA). This unsupervised technique enables the mining of discriminative features from the skin cancer images, effectively mitigating overfitting concerns and letting the model adjust structural features of skin cancer images, facilitating effective detection of skin cancer features. The system shows great potential in facilitating the initial screening of skin cancer patients, empowering healthcare professionals to make timely decisions regarding patient referrals to dermatologists or specialists for further diagnosis and appropriate treatment. Our advanced adaptive fine-tuned CNN approach for automatic skin cancer diagnosis offers a valuable tool for efficient and accurate early detection. By leveraging DL and transfer learning techniques, the system has the possible to transform skin cancer diagnosis and improve patient outcomes
Antenna systems for IoT applications: a review
No full textAbstract In smart homes, industrial automation, healthcare, agriculture, and environmental monitoring, IoT antenna systems improve communication efficiency and dependability. IoT antenna systems affect network performance and connection by affecting gain, directivity, bandwidth, efficiency, and impedance matching. Dipole, patch, spiral, metamaterial-based, and other antenna types are tested in IoT settings to identify their applicability, benefits, and downsides. Current antenna technology has challenges with frequency, bandwidth, size, weight, material choices, and energy efficiency, requiring new solutions. According to the study, interference control, power consumption, and dynamic IoT adaptation research are inadequate. Metamaterials, nanomaterials, and 3D printing may circumvent these antenna design limitations. AI and machine learning can improve antenna design real-time optimization and performance in complex settings. The paper explores how standards and regulatory frameworks affect IoT antenna system development to ensure future designs meet a fast-growing market. For the growing range of IoT applications, this research suggests more flexible and reconfigurable antennas that can function across numerous frequency bands. The report emphasizes antenna material and design innovation to improve durability, cut costs, and scale manufacturing. This research tackles these key elements to enable the next generation of antenna systems to meet IoT technology's expanding needs and increase networked devices' functionality, efficiency, and integration across industries. This comprehensive approach helps identify current trends and concerns and prepares for future IoT antenna system advancements, enabling smarter, more connected, and more efficient technologies
Correction: Harnessing AI for sustainable higher education: ethical considerations, operational efficiency, and future directions
No full textPR-FCNN: a data-driven hybrid approach for predicting PM2.5 concentration
No full textAbstract The atmosphere’s fine articulate Matter (PM2.5) poses various health-related risks. Even though multiple efforts have been made to lower the emissions of these substances, the mortality rate is continuously increasing, requiring immediate inclination of the scientific community towards the design and development of advanced predictive models. Conventional statistical approaches have become dormant due to their limitations in capturing the innate relationships between the pollutants, particularly for predicting PM2.5 concentrations. In contrast, machine and deep learning techniques have shown great potential for forecasting air quality, providing more accuracy than its predecessor techniques. The present study investigates the utilization of hybrid approaches by integrating machine learning models with deep learning models to improve the prediction capabilities of PM2.5 concentration. It uses datasets from the World Air Quality Index (WAQI) and the State of Global Air (SOGA) to analyze the performance of the models on both the daily and annual data, respectively. This ensures the model’s effectiveness on a diversified dataset. The present study implements Random Forest (RF), Polynomial Regression (PR), XGBoost, and Extra Tree Regressor (ETR) coupled with Fully Connected Neural Network (FCNN), Long Short-Term Memory (LSTM), and Bi-directional LSTM (Bi-LSTM) for obtaining optimized results. Finally, after a thorough investigation, the hybrid PR model coupled with FCNN (PR-FCNN) is found to be the best model with improved R-squared (R2) values, portraying its potential for predicting PM2.5 concentration accurately. Based on the experimentation, the preset study recommends implementing hybrid approaches, offering better predictive accuracy in forecasting air pollutants, especially PM2.5
