Manuscript Number : SHISRRJ247282

Because of the rapidly increasing number of cars on the road, driving safety has received a lot of public attention lately. Although smoking poses a risk to driving safety, drivers frequently choose to overlook this fact. The current methods for detecting smoking either require extra devices or operate in a touch fashion. This encourages us to investigate if smoking occurrences in a driving environment can be detected by cellphones. In order to increase driving safety, we introduce Hear Smoking, a cigarette smoking detection system that solely makes use of smartphone sound sensorsWe generate an audio signal that the speaker will release and picked up by the microphone after looking into common smoking behaviors among drivers, such as hand and chest movements. To determine the movement patterns of the hands and chest, we compute the Relative Correlation Coefficient of the signals we have received. For the purpose of classifying hand movements, A trained convolutional neural network receives the processed data. Simultaneously, we design a mechanism to detect respiration. We also examine the composite smoking motion's periodicity in an effort to enhance system performance. Hear Smoking has achieved a real-time smoking detection accuracy of 93:44% on average events after rigorous testing in authentic driving scenarios. The initial section of the review delves into the significance of heart rate monitoring as a crucial physiological parameter and its association with various health conditions, emphasizing its potential as a key indicator for detecting adverse habits such as smoking. The paper then explores the historical progression of heart rate monitoring technologies, from traditional methods to the emergence of advanced wearable devices and non-invasive sensors. A substantial portion of the review is dedicated to examining the existing approaches and methodologies employed in heart rate monitoring and smoking detection systems. Various sensor technologies, such as photoplethysmography (PPG), electrocardiography (ECG), and accelerometers, are discussed in detail, along with their strengths and limitations. Additionally, algorithms for machine learning and signal processing were used. for the analysis of heart rate data are explored, highlighting their role in enhancing the accuracy and reliability of smoking detection.The challenges associated with heart rate monitoring and smoking detection are comprehensively addressed in the subsequent section. Factors such as noise interference, variability in individual physiological responses, and ethical considerations are discussed, shedding light on the intricacies of developing a robust and practical system. Moreover, the paper delves into the privacy concerns and ethical considerations related to implementing smoking detection systems, emphasizing the need for a balance between health monitoring and individual privacy.The review also presents a detailed analysis of recent advancements and innovations in heart rate monitoring and smoking detection technologies. This includes in the combination of deep learning methods and artificial intelligence (AI), which have shown promising results in improving the accuracy and real-time capabilities of smoking detection systems. Furthermore, the incorporation of Internet of Things (IoT) concepts and cloud-based solutions for data storage and analysis is explored, providing a glimpse into the future of connected health monitoring.In the final section, The final section of the study discusses the possible impact of automated heart rate monitoring and smoking detection systems on public health. The importance of early intervention and personalized health management is highlighted, emphasizing the role of these technologies in fostering a proactive approach towards lifestyle-related health issues. The review concludes with insights into the future directions of research in this domain, suggesting avenues for further improvement and integration with emerging technologies.