An explainable analytical approach to heart attack detection using biomarkers and nature-inspired algorithms

Cyber-Physical Systems (CPSs) are the complicated formulation of cyber and physical equipment that effectively utilizing the capabilities of sensors, actuators, networks, and communication systems. The system is vulnerable to various cyber-attacks in the smart grid that are active and passive attacks, DoS attacks, data injection attacks, replay attacks, etc., With the exponential growth of communication and electronic devices, it is a large and complex task to manage these devices from vulnerabilities. However, cyber-attacks on CPS can cause severe harm to the resources, network infrastructure, and communication channels with the key objectives of confidentiality, integrity, and authentication. This paper considers the design of detecting cyber-attacks during transmission from control center to plant over the networked control center and preventing cyber-attacks with the help of a genetic algorithm and deep feedforward neural networks. This method ensures the security of networked control center in CPS environment of smart grid. This also mitigates the drawbacks of existing attack detection techniques. The performance is evaluated in benchmarking IEEE 39 bus system for achieving the accuracy, performance metrics, and low false positive rate to improve the attack detection in a smart grid environment in cyberspace.

Advancement in technology has resulted in the easy sharing of locations across various stakeholders. Unprotected sharing of location information makes any Global Navigation Satellite System (GNSS) device vulnerable to spoofing attacks. Spoofed GNSS signals propagate misleading trajectories to cripple any Location-Based Service (LBS). This manuscript introduces a novel algorithm for the detection and mitigation of spoofing attacks. The proposed algorithm was implemented in the Android application using the OpenStreetMap dataset. GNSS spoofing attacks were simulated and detected in real-time. The efficiency of the proposed algorithm was analyzed using the Ratio of Correctly Detected (RCD) and Ratio of Correctly Matched (RCM) spoofed points. The maximum observed values for RCD and RCM were 75% and 94%, respectively. Minimum RCD and RCM values observed during the experiment were 59% and 92%. The accuracy of the proposed algorithm was further analyzed using average positional error (APE). Maximum and minimum recorded APE values were 25.08% and 13.83% respectively. The manuscript concludes with a comparison of the proposed algorithm with that of existing techniques.

<p>The security of web applications is a significant issue because of their widespread use in everyday activities. Although machine learning has shown success in identifying attacks, it can face difficulties when dealing with wide datasets. Algorithms inspired by nature, renowned for their optimization capabilities, offer potential solutions to this difficulty.</p><p> This paper analyses the use of Nature-Inspired Optimization Algorithms (NIOAs) to identify web application threats and assess their performance in detecting web application attackers.</p><p> This paper involves a comprehensive review of several kinds of patented algorithms that are based on nature- inspired algorithms to measure their performance in recognizing new types of web attacks. Additionally, this paper compares these methods with conventional machine learning approaches to reveal their strengths and weaknesses when used for web security purposes.</p><p> The study emphasizes the effectiveness of Nature-Inspired Optimization Algorithms (NIOAs) in enhancing detection mechanisms for evolving threats. These algorithms demonstrate adaptability and often outperform traditional methods in specific scenarios. The results reveal that optimization approaches like WOA, EO, GWO, and BAT achieved outstanding classification accuracy. WOA-stacking classifier gives the best performer with a classification accuracy of 99.28% and a leader fitness score of 99.17%. EO-Xgboost also stood out with a perfect accuracy of 100%. While traditional classifiers like Logistic Regression and SVM performed well, NIOA-based methods showed superior results.</p><p> Nature-inspired optimisation Algorithms can improve the security of web applications. The findings suggest that nature-inspired algorithms have potential applications across different problem domains, This empirical study provides valuable insights for researchers seeking accurate classifiers for detecting website attacks.</p>

Now a day's Heart attack is a common one which affects almost 60% of total population due to their food conditions and various environmental factors. Still now there is no separate system for the intimation of heart attack. After the occurrence of heart attack only, the patient can be monitored. Only pre possible solution for the detection of heart attack is by analyzing the number of beats per minute (BPM). So this work detects the heart attack based on the number of pulses. If the pulse rate other than the range (60–90) occurs it is considered as the indication of heart attack. Addition to this detection of heart attack, this work intimates the occurrence of heart attack to the helpline in wireless GSM module. In this work, a system to detect heart attack is designed and developed. A pulse sensor is used for sensing the heart beat signals. The microcontroller checks these signals and counts the pulses. If the pulses are greater or less than certain levels, the controller activates GSM module and sends an alert message to mobile numbers already coded in a microcontroller. The developed system is tested with the measurement of different male and female persons. The system performed accurate detection and intimation of messages to the different care takers of the patients. Many lives may be saved in the short duration by using this developed system.

Accurate and timely detection of heart attacks is crucial for effective intervention and treatment. This paper presents a comprehensive study on enhancing heart attack detection using advanced machine learning (ML) and deep neural network (DNN) models, integrated through multi-model images. We propose an innovative approach that combines various machine learning techniques and deep learning architectures to improve prediction accuracy and robustness. Our methodology includes the integration of convolutional neural networks (CNNs) for feature extraction from medical imaging data, recurrent neural networks (RNNs) for analyzing time-series data, and ensemble methods for combining predictions. We systematically evaluate these models individually and in combination to determine their effectiveness in heart attack detection. Performance metrics such as accuracy, precision, recall, and F1-score are used to assess model efficacy, and comparative analyses are conducted to highlight improvements over traditional methods. The results demonstrate that the proposed multi-model approach significantly enhances prediction accuracy and reduces false positives and negatives, offering a more reliable tool for early heart attack detection. Our findings underscore the potential of integrating diverse ML and DNN techniques to address complex medical diagnosis challenges and pave the way for future research in predictive healthcare.

The integration of the Internet of Things (IoT) in healthcare has enabled intelligent and early heart attack detection (HAD) through artificial intelligence; however, the existing approaches suffer from high computational complexity and suboptimal performance, leading to inaccurate predictions, which can jeopardize patient well-being. Moreover, they fail to provide secure bidirectional communication between patients and medical centers while safeguarding patient privacy. Therefore, this paper addresses these limitations by proposing a novel secure and efficient HAD approach in healthcare. First, we propose a customized consortium blockchain network that leverages group signatures to ensure patient anonymity, data unlinkability, and secure two-way communication, thereby preserving patient privacy. Then, a lightweight, robust HAD model is devised via knowledge distillation by leveraging a novel proposed hybrid deep learning architecture that enables accurate early detection of heart attacks, supporting timely clinical intervention. Experimental results on a real dataset, i.e., the Cleveland dataset, demonstrate the scalability of the proposed approach that can process up to 500,000 patients in under 2.5 minutes, while preserving patient privacy. Moreover, it offers 99.22% accuracy, an F1-score of 99.23%, outperforming state-of-the-art techniques, with an inference time of 90 ms and a model memory footprint of only 0.28 MB.

Ultrasensitive cardiac troponin I antibody based nanohybrid sensor for rapid detection of human heart attack

Heart attack is one of the leading causes of human death worldwide. Every year, about 610,000 people die of heart attack in the United States alone—that is one in every four deaths—but there are well understood early symptoms of heart attack that could be used to greatly help in saving many lives and minimizing damages by detecting and reporting at an early stage. On the other hand, every year, about 2.35 million people get injured or disabled from road accidents. Unexpectedly, many of these fatal accidents happen due to the heart attack of drivers that leads to the loss of control of the vehicle. The current work proposes the development of a wearable system for real-time detection and warning of heart attacks in drivers, which could be enormously helpful in reducing road accidents. The system consists of two subsystems that communicate wirelessly using Bluetooth technology, namely, a wearable sensor subsystem and an intelligent heart attack detection and warning subsystem. The sensor subsystem records the electrical activity of the heart from the chest area to produce electrocardiogram (ECG) trace and send that to the other portable decision-making subsystem where the symptoms of heart attack are detected. We evaluated the performance of dry electrodes and different electrode configurations and measured overall power consumption of the system. Linear classification and several machine algorithms were trained and tested for real-time application. It was observed that the linear classification algorithm was not able to detect heart attack in noisy data, whereas the support vector machine (SVM) algorithm with polynomial kernel with extended time–frequency features using extended modified B-distribution (EMBD) showed highest accuracy and was able to detect 97.4% and 96.3% of ST-elevation myocardial infarction (STEMI) and non-ST-elevation MI (NSTEMI), respectively. The proposed system can therefore help in reducing the loss of lives from the growing number of road accidents all over the world.

Heart attacks are a leading cause of sudden death, and in many cases, the first attack can be fatal if not detected early. Regular health monitoring is essential for early detection and prevention. Many people lose their lives due to poor diet, aging, lack of physical activity, and other factors. To address this, we propose an IoT-based Heartbeat Monitoring and Heart Attack Detection System that continuously monitors the user's heart rate. In case of abnormal readings indicating a potential heart attack, the system sends emergency alerts to nearby police stations, ambulances, and registered family contacts. It also provides GPS tracking to help responders locate the person or vehicle quickly. Keywords-ESP32, SP02 Sensor, MQ-3 Sensor, Vibration sensor, LCD.

Introduction Fatal car accidents have become an alarming issue all over the globe. A sudden medical condition such as a heart attack causes medical symptoms that lead a driver to lose consciousness while driving and consequently leads to a crash. Many studies have demonstrated the high correlation between the driver's sudden medical conditions and involving in a car crash [1][2]. Therefore, to reduce car crashes from the driver's sudden illness from heart-attack as well as save the driver's life in a timely manner, in this work, we discuss the development of a portable wearable system that can continuously monitor the driver for any early symptoms of heart attack and inform him before losing conciuous to stop the car as well as inform medical caregivers to save life. Background Myocardial infarction (MI) is the medical term for the medical condition commonly known as a heart attack, a serious medical emergency in which the blood supply to the heart is suddenly blocked, usually by a blood clot, leading to damage heart muscle [3]. A complete blockage of a coronary artery is a ‘STEMI’ heart attack (ST-elevation MI), whereas a partial blockage would be a ‘NSTEMI’ heart attack (a non-ST-elevationMI) [4]. The average, resting heart rhythm has a QRS-complex following a P-wave and followed by a T-wave, as illustrated in Figure 1(a). A STEMI heart attack will cause an elevation in the ST-complex (Figure 1(b)), whereas a NSTEMI heart attack would not signify ST elevation, but nonetheless can cause ST-segment depression or T-wave inversion (Figure 1(c)), which can be detected immediately by a real-time device to save the driver's life. Method The prototype system consists of two subsystems (Figure 2) that communicate wirelessly using Bluetooth low energy (BLE) technology: wearable sensor subsystem, and an intelligent heart attack detection and warning subsystem. Wearable Subsystem: The wearable chest-belt sub-system includes dry electrodes (reference and two electrodes for differential acquisition), analogue front end (AFE), power management module, and RFDuino microcontroller with BLE. This subsystem acquires the ECG signals from human body continuously and sends these raw measurements wirelessly using BLE technology to the intelligent subsystem. Reusable and smaller dimension dry electrodes (Cognionics, Inc) were embedded in a chest belt to be worn by a car driver. AD82832 AFE is an integrated signal conditioning block to extract, amplify (60 dB gain), and filter (0.48-41 Hz) ECG signal in the presence of noisy conditions. Lithium Polymer (LiPo) battery of 3.7 V (1000 mAH) with the Microchip MCP73831 charge controllers, and Texas instruments' TPS61200 voltage regulators to supply 3 V to the wearable system. The miniaturized ARM Cortex M0 RFDuino microcontroller digitizes the signal at 500 Hz sampling rate and transmits the acquired signal through built-in BLE to decision making subsystem. Intelligent Decision-making Subsystem: This subsystem will receive the ECG signals from the wearable subsystem continuously. It is capable of processing, analyzing the received ECG signals, and making the right decision using support vector machine (SVM) algorithm to classify the normal and abnormal ECG signal to detect heart attack symptoms. This subsystem was built around the single board computer, Raspberry Pi 3 (RPi3) along with SIM 908 GSM and GPS module for location information and alerting service. Multi-threaded python code was written for RPi3 to automatically acquire, buffer, baseline correction and digital smoothing and analyse the ECG data. SVM algorithm was implemented in RPi 3 and used for real-time abnormality detection using the trained model and classification was done using LIBSVM, an open source library [5]. 4-fold cross-validation was used to evaluate classification accuracy. SIM908 GSM+GPS shield attached on the RPi3 to provide car location (latitude, longitude) and to connect to the mobile network for generating an automatic call to medical emergency. This subsystem is designed to take power from the car battery using Cigarette Lighter Socket, which powers the system only when the car's engine is ON. To develop the intelligent program for decision-making subsystem, public MIT-BIH ST change database [6] was used to train a SVM model for normal, ST-elevated, and T-inverted ECG-beats with the time domain (TD), frequency domain (FD) and extended time-frequency domain (TFD) features extracted. The TD features mean, variance, skewness, kurtosis, and coefficient of variation and the FD features spectral flux, spectral entropy and spectral flatness were calculated to spot abnormalities in the ECG-beats. Three time-frequency (TF) distributions were also used in this study: Wigner-Ville Distribution (WVD), Spectrogram (SPEC), and Extended Modified B-Distribution (EMBD). Result and Discussion Recorded ECG Traces: It was clearly revealed from Fig. 5 that the ECG signal transmitted using the prototyped system is in clinical grade. Training SVM: Five hundred traces from each patient and total 2500 traces from MIT-BIH database having either normal or abnormal heart rhythm were segmented and averaged for each case (Figure 6 (A, B, & C)). The power spectral of the signal in Figure 6 (D, E & F) shows that the power spectral density peaks appear at different frequencies for normal and abnormal ECG signals. This reflects that the FD feature can help in classifying the ECG signals. However, TD, FD, and TFD features provide an insight on the signal while compensating for the noise or motion artefacts. Classification using SVM: Table 1 below summarizes the accuracy of the prototyped device. EMBD produces higher accuracy in classification of ECG signal. Conclusion This work shows the possibility to detect driver's heart attack reliably using the developed prototype system. SVM machine learning algorithm that was trained with a sufficiently high number of training data can classify STEMI or NSTEMI with approximately 97.4% and 96.3% accuracy respectively when the extended TF features (with EMBD distribution) were used for training and classification. The maximum current drawn by the wearable chest-belt subsystem during continuous acquisition is 9.3 mA, which ensures the life span of a 1000 mAh LiPo battery is 75 hours, once it is fully charged and therefore it can be expected that the device can run longer without requiring recharging daily.

Heart attacks continue to be a major cause of death globally, making it crucial to develop accurate and efficient predictive models for early diagnosis and timely treatment. This research presents an improved Convolutional Neural Network (CNN) model designed to enhance heart attack prediction and detection while addressing the common issues of overfitting and poor generalization found in traditional machine learning methods. The enhanced model utilizes advanced regularization techniques and optimization strategies to improve its performance, capitalizing on CNNs' ability to effectively extract spatial features. The experimental results reveal significant improvements in both accuracy and robustness of the model. The enhanced CNN achieved a maximum accuracy of 100% and a validation accuracy of up to 75% after 50 training epochs.

Using a novel bio-inspired optimization algorithm based on the navigation strategy of moths in a universe called transverse orientation, called the Moth-Flame Optimization Algorithm (MFOA), has been applied to solve the load flow problem for power systems under critical conditions. This mechanism is highly effective for traversing covering expanded radius in straight direction. As a matter of fact, moths follow a deadly spiral path as they get confused by artificial lights. For the tuning of parameters, both exploration and exploitation processes play an important role. MFOA is exercised for load flow analysis of small, medium, and large ill-conditioned power systems. The three different standard ill-conditioned cases considered in order to verify the robustness of the algorithm are IEEE 14-bus, IEEE 30-bus and IEEE 57-bus test systems. The results obtained by the application of MFOA shows that the algorithm is able to provide better results than the results obtained by the application of a biogeography inspired optimization algorithm, namely biogeography-based optimization (BBO) and a nature-inspired optimization algorithm, namely the whale optimization algorithm (WOA). This approves the superiority of the proposed algorithm. Simulation and numerical results demonstrate that the MFO is a potent alternative approach for load flow analysis under both normal and critical conditions in practical power systems especially in case of failure of conventional methods, thereby proving the robustness of the method. To the best of the authors' awareness, it is the first report on application of MFOA load flow analysis.

Atherosclerotic cardiovascular disease is the leading cause of mortality and morbidity in the USA. Millions of dollars are spent each year for research efforts to find the best therapy for reperfusion of acutely closed coronary arteries, which would otherwise lead to acute myocardial infarction (MI). As with other disease states, heart attacks have beginnings. Chest discomfort before severe chest pain represents a clinical ischemia marker, and indicates live myocardium in jeopardy that often precedes cardiac arrest or acute MI. The intermittent or stuttering symptoms that precede MI are referred to as "prodromal symptoms." These symptoms correlate with cyclic ST changes and repeated episodes of spontaneous reperfusion and occlusion, occurring during a period of hours or days before the ischemia proceeds to damage. Premonitory, or preinfarct angina, has been associated with improved outcomes in patients with acute MI by providing ischemic preconditioning or opening collateral vessels. Acute MI prevention through prodromal symptoms recognition represents an opportunity for reducing heart attack fatality. In conjunction with the Screening for Heart Attack Prevention and Eradication (SHAPE) initiative, the Early Heart Attack Care program emphasizes prodromal symptom recognition in at-risk populations, facilitating early detection and prevention of fatal heart attacks. Similarly, the strategy behind the chest pain centre movement in the USA is to prepare the hospitals for proper screening of patients suspected of acute coronary syndromes and to detect patients with prodromal symptoms in the community. In the era of the remarkably facilitated communication of Google, iPhone, Facebook, and Twitter, new developments are urgently needed to incorporate information technology into the early detection of prodromal symptoms. An example of such a development is proposed under " http://www.checkmyheart.com " in this chapter.

Worldwide, heart attacks, also called myocardial infarctions, are a leading cause of death. Early detection and accurate prediction of heart attacks are crucial for effective medical intervention and patient care. In recent years, machine learning techniques have shown great promise in aiding the diagnosis and prediction of heart attacks. The Organization for World Health (WHO) reports that around 17 million individuals worldwide pass away from cardiovascular diseases (CVD), notably heart attacks and strokes, each year. In this study, 1026 patients, both men and women, are almost equally affected by CVDs. While heart attacks and strokes remain among the leading causes of mortality worldwide, the use of machine learning for predicting heart disease could potentially prevent premature deaths. A comparative study evaluated the performance of five well-known two-class classification algorithms: two-class boosted decision trees, two-class decision forests, two-class locally deep SVMs, two-class neural networks, and two-class logistic regression. Among these algorithms, the Two-Class Boosted Decision Tree method demonstrated outstanding prediction ability, achieving a 100% accuracy rating. Its exceptional recall and precision rates highlight its effectiveness in handling challenging classifications. To facilitate the development and deployment of machine learning models, Azure Machine Learning offers a range of tools and services. By leveraging Azure Machine Learning's capabilities, researchers and healthcare professionals can analyze large datasets containing patient information and medical records to identify patterns and risk factors associated with heart attacks.

These days we’ve an enhanced range of heart diseases together with enhanced risk of heart attacks. We all heard and observed that heart attack can kill your life in 3 attempts but now days because of heavy stress it could be in first attempt also. If conscious about our health regularly on regular basis then we can detect so many different diseases by detecting them previously, and Co2 would be also varies in the heart attack situation, so in this paper carbon dioxide analyses and identified the intense of CO2 in different level of activities. Life is precious. In this era many people lose their life to coronary failure. Heart attack detection is not easy task. In today’s world heart attack is more common, In order to overcome the situation and to reduce the death rate due to heart attack, this system is used and mainly it will useful for the society In this system we have a tendency to area unit implementing a heartbeat observance and coronary failure detection system exploitation the Internet of Things. In this sensor the operator can fix the low as well as higher level heart beat, where the system monitor the beat and send those data to the internet, in case if the heart beat level go beyond the; low rate which is set by the user, the alert will be given so that immediate action can be taken. One is that the transmittal circuit that is with patient and therefore the different is that the receiver circuits that is being supervised by the doctor or nurse. The main motive of the system which will take the heart beat rate and those data will be get displayed on the digitalized Monitoring screen.