Fig 5 - available from: Multimedia Tools and Applications
This content is subject to copyright. Terms and conditions apply.
Source publication
In a developed society, people have more concerned about their health. Thus, improvement of medical field application has been one of the greatest active study areas. Medical statistics show that heart disease is the main reason for morbidity and death in the world. The physician’s job is difficult because of having too many factors to analyze in t...
Context in source publication
Context 1
... the varied elements of the symptoms. By using the suggested healthcare framework, the patients enter these symptoms that he suffers from such as Dyspnea, Edema, Fatigue, Ascites, Nausea, Chest pain. After then, the consultants send a report to patient by email, for informing that the percentage that the patient suffer from heart failure (Fig. ...
Citations
... Abdel-Basset M et al. [17] proposed this study to develop an IoT model to detect and monitor heart failure-infected patients. Achieved from various wearable sensors. ...
... Zulqarnain et al. [27] proposed the generalised aggregate operators on soft computing in a neutrosophic setting. Al-Sharqi et al. used this tool with many concepts within the fuzzy environment, such as fuzzy hypersoft [28], q-rung orthopair fuzzy neutrosophic valued [29], neutrosophic soft matrix [30], and bipolar neutrosophic hypersoft setting [31], and they employed all these concepts with AO in solving different real-life applications [32][33][34][35]. ...
The best way to deal with complicated life scenarios that accompany the decision-making process is to update previous concepts constantly. Therefore, researchers must constantly discover powerful mathematical tools that suit the accompanying circumstances. In this regard, we combine both soft set, neutrosophic set, and interval setting under Q-two-dimensional universal information to introduce a new hybrid innovative model called interval valued-Q-neutrosophic soft sets. The core goal of this model is to keep the features of previous models like soft sets, neutrosophic sets, and Q-Fuzzy sets in dealing with the lack of uncertainty and neutrality associated with real-life issues. This new approach allows decision-makers to employ interval-valued form with Q-two-dimensional universal information, which provides them with more stability and feasibility in describing uncertain information more completely and accurately. Under the our propose model, we discuss effectively set-theory operations such as subset, union, intersection, complement, AND operation, and OR operation for interval valued-Q-neutrosophic soft sets, as well as some special operations like the necessity and possibility operations of an interval valued-Q-neutrosophic soft sets. In addition, we presented many properties supported by numerical examples that explain how they work. Finally, this new model has been successfully tested in dealing with one of the medical diagnostic problems based on hypothetical data for a respiratory disease. Building an algorithm based on the aggregation operator for interval valued-Q-neutrosophic soft set data solved this issue (i.e., selecting the optimal alternative).
... In [66], the authors select the hand as the best position for smartphone placement for position detection. In [70,71], a 3-axial accelerometer fixed at the thigh and hip of the person is used for the prediction and the detection of falls [58,60,62] Pulse rate sensor Pulse rate sensor [63] Smartphone GPS, PPG (through camera), magnetometer, accelerometer [11][12][13]64] ECG sensor AD 8232 ECG sensor [41] Smartphone, Smartwatches Inertial, location, physiological [38,52] RFID sensor W2ISP sensor [65] W-BAN Aerobic rate, skin fever, ECG, bearing, EMG muscle vigor [66] Smartphone IMU sensor Accelerometer, magnetometer, gyroscope [67] -Accelerometer, gyroscope, magnetometer, heart rate sensor [68] cognitive sensor - [69] WISE respectively. In a few papers, the pulse rate sensor is placed at the finger of the person and the accelerometer is placed at different places on the body like waist, arm etc. ...
... 8. W-BAN sensor: W-BAN stands for a wearable-body area network, in which wearable sensors such as aerobic, ECG, skin fever, bearing (posture) and EMG muscle vigor, etc. are used for measuring the body biomarkers. In [65], the author used W-BAN to capture blood pressure, heart rate, motion, glucose etc. in real-time. The data are col-lected from the patient's body using a mobile app and then stored in the cloud. ...
This paper provides a comprehensive survey of various aspects of the systems detecting falls and activities of daily living. Such systems are very useful for elderly people who live alone. The feature values pertaining to the movement can be acquired by the wearable sensors mounted on various parts of the body. Detecting activities of daily living and falls can help in alerting caretakers but predicting falls before occurrence can alert the subject and avoid injuries. The inertial measurements of body movements can help in detecting falls. However, the physiological features combined with inertial measurements of body movements can further improve the accuracy of detection and may lead to prediction. This paper provides a state-of-the art review of various sensors which can be used to capture inertial measures and physiological features. We also provide a comprehensive review of the existing forty-two datasets which comprises inertial measurements and can be extended with physiological features. A pilot study has been conducted using five machine learning techniques exhibiting the phases in detecting and predicting falls which concluded that original captured features are more characteristic than single representative feature computed using Sum Magnitude Vector. Further as we move towards developing a generalized system, accuracy gets affected.
... Rights reserved. methods [21]. Nevertheless, a hybrid learning algorithm is essential for health monitoring data to enhance the outcome's quality and increase parameter estimation [22]. ...
People who lead hectic lives daily suffer from a variety of illnesses, including diabetes, high blood pressure, hypertension, etc. For someone to survive, they must become aware of these illnesses promptly. The Internet of Things (IoT) and cloud computing are the two critical prerequisites for digital healthcare. In the present research, the attacked data are detected and removed using the security module to enhance the security of the healthcare system. However, an accurate prediction mechanism is needed for the early diagnosis of the diseases. To predict the sickness and its severity more accurately, a unique Dragon Fly-based Generalised Approximate Reasoning Intelligence Control (DF-GARIC) is devised in this article. This system was primarily responsible for preprocessing the cloud medical records entered into the system. Additionally, the regression algorithm extracts the relevant features. Based on the retrieved features, the dragonfly function is used to classify the disease and estimate its severity. Subsequently, a warning is given to the providers for the abnormal condition via SMS or e-mail. The system validated a higher accuracy level of 99.8% from the MATLAB execution.
... • k-Nearest Neighbors (kNN): Anon-parametric classifier that predicts the class of an instance based on the class labels of its k-nearest neighbors [1]. ...
INTRODUCTION: Cardiovascular diseases, including heart disease, remain a significant cause of morbidity and mortality worldwide. Timely and accurate diagnosis of heart disease is crucial for effective intervention and patient care. With the emergence of machine learning techniques, there is a growing interest in leveraging these methods to enhance diagnostic accuracy and predict disease outcomes. OBJECTIVES: This study evaluates the performance of three machine learning classifiers—Naive Bayes, Logistic Regression, and k-Nearest Neighbors in predicting heart disease based on patient attributes. METHODS: In this study, we explore the application of three prominent machine learning classifiers—Naive Bayes, Logistic Regression, and k-Nearest Neighbors (kNN)—to predict the presence of heart disease based on a set of patient attributes. RESULTS: Using a dataset of 303 patient records with 14 attributes, including age, sex, and cholesterol levels, the data is pre-processed, scaled, and split into training and test sets. Each classifier is trained on the training set and evaluated on the test set. Results reveal that Naive Bayes and k-Nearest Neighbors classifiers outperform Logistic Regression in terms of accuracy, precision, recall, and area under the ROC curve (AUC). CONCLUSION: This study underscores the promising role of machine learning in medical diagnosis, showcasing the potential of Naive Bayes and k-Nearest Neighbors classifiers in improving heart disease prediction accuracy. Future work could explore advanced classifiers and feature selection techniques to enhance predictive accuracy and generalize findings to larger datasets.
... IoT and computer-supported diagnosis can be used to monitor patients with heart failure, according to Abdel-Basset et al. [16]. It was initially communicated using Bluetooth technology to the cloud database via a smart gateway, which was connected to the mobile phones of the patients with heart failure. ...
... By dividing the total amount of real positives and false positives by the number of true positives, it is determined. Eq. defines the equation for precision (16). ...
Artificial intelligence and data mining have played an increasingly important part in the evolution of the Internet of Things (IoT) during the last few years, allowing researchers to evaluate both current and historical data. In contrast to men, women are more likely to be diagnosed with breast cancer than men. In an IoT healthcare system, early-stage breast cancer recovery and treatment are dependent on an accurate and quick diagnosis. There are currently no effective methods for detecting early breast cancer stages, and many women succumbed to the disease as a result. As a result, medical specialists and researchers face a significant barrier in identifying breast cancer at an early stage. We developed a deep learning-based diagnostic system that accurately distinguishes between malevolent and healthy people in the IoT environment. Our suggested approach uses a 1-D convolutional neural network (1D-CNN) as a deep learning classifier to distinguish between cancerous and benign individuals. To recover the classification presentation of the classification system, we employed an ensemble filter based feature selection approach to choice more relevant features from the breast cancer dataset. Use of the splits strategy for training and testing of a classifier for the finest prediction model is employed here. The dataset "Wisconsin Diagnostic Breast Cancer" was used in this study to test the proposed method. Classifier 1D-CNN obtained optimal classification performance on this best subset of data, as demonstrated by the experiments, which show that the suggested feature selection strategy selects the most useful features.
... Abdel-Basset et al., [22] approached the people who were more concerned regarding their health in developed cultures. Improving medical sector applications has been one of the most active research areas. ...
The Internet of Things (IoT) technology is currently being used in healthcare systems to collect sensor values for heart disease diagnosis and prediction. Although many researchers have focused on the diagnosis of heart disease, the accuracy of the diagnosis results is low. To address this problem, we present a novel method for predicting heart disease. This paper proposes a novel approach for heart disease detection using long short-term memory networks (LSTM) optimized with Self-improved Jellyfish Optimization. Initially, input data are gathered from the smartwatch and heart monitor device that is attached to the patient to monitor the blood pressure and electrocardiogram (ECG). Then the input data are Pre-processed using the Principal Component Analysis (PCA) algorithm. The African vulture’s optimization algorithm (AVOA) is employed for feature selection. Selected features are provided to LSTM for classifying the received sensor data into normal and abnormal. The proposed approach aims to optimize LSTM hyperparameters the Self-improved Jellyfish Optimization (SIJO) is utilized. In addition, the proposed algorithm incorporates a self-improvement mechanism. By then, the proposed approach's performance has been tested on the MATLAB platform and its results have been compared to those of other approaches. Thus, the results demonstrate the effectiveness of the Jellyfish Optimization algorithm in enhancing LSTM for heart disease detection.
... Finally, IoT technology enables intelligent management of medical information. Through the fusion of the medical information diagnosis platform with cloud computing technology, intelligent management of medical information becomes attainable, thereby further advancing the efficiency and quality of healthcare services [14]. The salient advantages of the medical information diagnosis platform under the amalgamation of ChatGPT and IoT technology are illustrated in Fig. 1. ...
In order to enhance the operational efficiency of the healthcare industry, this paper investigates a medical information diagnostic platform through the application of swarm and evolutionary algorithms. This paper begins with an analysis of the current development status of medical information diagnostic platforms based on Chat Generative Pre-trained Transformer (ChatGPT) and Internet of Things (IoT) technology. Subsequently, a comprehensive exploration of the advantages and disadvantages of swarm and evolutionary algorithms within the medical information diagnostic platform is presented. Further, the optimization of the swarm algorithm is achieved through reverse learning and Gaussian functions. The rationality and effectiveness of the proposed optimization algorithm are validated through horizontal comparative experiments. Experimental results demonstrate that the optimized model achieves favorable performance at the levels of minimum, average, and maximum algorithm fitness values. Additionally, preprocessing data in a 10 * 10 server configuration enhances the algorithm’s fitness values. The minimum fitness value obtained by the optimized algorithm is 3.56, representing a 3 % improvement compared to the minimum value without sorting. In comparative experiments on algorithm stability, the optimized algorithm exhibits the best stability, with further enhancement observed when using sorting algorithms. Therefore, this paper not only provides a new perspective for the field of medical information diagnostics but also offers effective technical support for practical applications in medical information processing.
... Karabasevi et al. [44] developed a novel extension of the TOPSIS method using NSs. Abdel-Basset et al. [45] suggested a neutrosophic MCDM (NMCDM) approach to assist patients and physicians in determining if a patient is suffering from heart failure. Jana and Pal [46] introduced a new aggregation operator of SVNSNs and utilized this operator to address medical diagnosis problems. ...
During the transitional phase spanning from the realm of fuzzy logic to the realm of neutrosophy, a multitude of hybrid models have emerged, each surpassing its predecessor in terms of superiority. Given the pervasive presence of indeterminacy in the world, a higher degree of precision is essential for effectively handling imprecision. Consequently, more sophisticated variants of neutrosophic sets (NSs) have been conceived. The key objective of this paper is to introduce yet another variant of NS, known as the q-rung orthopair fuzzy-valued neutrosophic set (q-ROFVNS). By leveraging the extended spatial range offered by q-ROFS, q-ROFVNS enables a more nuanced representation of indeterminacy and inconsistency. Our endeavor commences with the definitions of q-ROFVNS and q-ROFVN numbers (q-ROFVNNs). Then, we propose several types of score and accuracy functions to facilitate the comparison of q-ROFVNNs. Fundamental operations of q-ROFVNSs and some algebraic operational rules of q-ROFVNNs are also provided with their properties, substantiated by proofs and elucidated through illustrative examples. Drawing upon the operational rules of q-ROFVNNs, the q-ROFVN weighted average operator (q-ROFVNWAO) and q-ROFVN weighted geometric operator (q-ROFVNWGO) are proposed. Notably, we present the properties of these operators, including idempotency, boundedness and monotonicity. Furthermore, we emphasize the applicability and significance of the q-ROFVN operators, substantiating their utility through an algorithm and a numerical application. To further validate and evaluate the proposed model, we conduct a comparative analysis, examining its accuracy and performance in relation to existing 5039 models.
... The applications of neutrosophic sets and their hybrids in MCDM approaches have been explored by numerous scholars [23][24][25][26] and [27]. By employing mathematical methods, real-world problems such as human resource selection, gadget selection, shortest path selection, robot selection, security considerations, medical equipment selection, and environmental safety measures can be addressed. ...
Language is closely connected to the concepts of uncertainty and indeterminacy, as it functions as a fundamental tool for the expression and communication of information. Linguistic formulations possess inherent qualities of ambiguity, imprecision, and vagueness. The comprehension of language frequently hinges upon contextual factors, individual interpretation, and subjective viewpoints, resulting in ambiguities in comprehension. Neutrosophic-linguistic valued hypersoft sets (N-LVHS) play a pivotal role in decision-making by effectively managing linguistic uncertainty, modeling real-world complexity, and accommodating multidimensional information. In the realm of medical diagnosis and treatment, several limitations tied to language and indeterminacy persist. Patients often use vague or imprecise language to describe their symptoms, complicating the accurate identification of ailments. Moreover, diagnostic criteria are subjectively defined, leading to inconsistencies in diagnoses. Disease progression, characterized by its complexity and unpredictability, adds further indeterminacy in treatment planning. The variability in patient responses to treatments introduces uncertainties in outcome prediction. Inconclusive test results and limited clinical data may compound these challenges, underscoring the need for innovative approaches like N-LVHS to address these linguistic and indeterminacy-related limitations and improve the precision and efficacy of medical decision-making and treatment procedures. In constructing an N-LVHS framework for medical diagnosis and treatment, relevant factors, and linguistic terms characterizing medical conditions and treatments are identified. For example, disease severity could be described using terms such as "mild," "moderate," and "severe," while treatment effectiveness may be categorized as "low," "moderate," and "high." Each factor is then assigned neutrosophic values based on their measured impacts. This approach provides a more precise representation of the complex medical diagnostic and treatment landscape. The findings of this study have the potential to assist medical practitioners, researchers, and policymakers in optimizing medical diagnosis and treatment strategies, enhancing patient outcomes, and improving healthcare practices.
