Heartbeat monitoring may play an essential role in the early detection of cardiovascular disease. When using a traditional monitoring system, an abnormal heartbeat may not appear during a recording in a healthcare facility due to the limited time. Thus, continuous and long-term monitoring is needed. Moreover, the conventional equipment may not be portable and cannot be used at arbitrary times and locations. A wearable sensor device such as Polar H10 offers the same capability as an alternative. It has gold-standard heartbeat recording and communication ability but still lacks analytical processing of the recorded data. An automatic heartbeat classification system can play as an analyzer and is still an open problem in the development stage. This paper proposes a heartbeat classifier based on RR interval data for real-time and continuous heartbeat monitoring using the Polar H10 wearable device. Several machine learning and deep learning methods were used to train the classifier. In the training process, we also compare intra-patient and inter-patient paradigms on the original and oversampling datasets to achieve higher classification accuracy and the fastest computation speed. As a result, with a constrain in RR interval data as the feature, the random forest-based classifier implemented in the system achieved up to 99.67% for accuracy, precision, recall, and F1-score. We are also conducting experiments involving healthy people to evaluate the classifier in a real-time monitoring system.

Wireless sensor networks (WSNs) utilize relay nodes (RNs) to enable multi-hop data transmission between sensor nodes (SNs) and the sink. Optimal RNs placement is crucial for ensuring network connectivity, reliability, and efficiency. WSN like undirected graph, so to optimal the RNs placement, can use shortest path algorithm. This paper investigates RNs placement optimization in WSNs using the A* algorithm in dual home of multi-tier architecture. Dual home architecture will address data transmission issues so that data will always be sent without being affected by dead relays. Multi-tiered architecture will solve problems over a large area, because data will be passed from SNs to nearby RNs to sinks. Simulations compare random, rectangular, and triangular RNs distribution patterns over varying area sizes, SN counts, and RNs counts. Results demonstrate the significant impact of area size and RNs quantity on connectivity metrics. Larger areas and fewer RNs dramatically reduce connected SNs and RNs connectivity. To Triangular pattern provide efficient connectivity versus rectangular pattern in most scenarios. Random pattern provided efficient connectivity in small area. The A* algorithm successfully optimizes RNs positions for connectivity across patterns and scenarios. This research provides insights into factors influencing optimal RNs placement and demonstrates the suitability of A* optimization for enhancing WSN reliability and performance.

Cardiovascular diseases (CDVs) remain a leading cause of death worldwide. Thus, the disease needs to be detected as early as possible. One of the solutions is using an automated ECG Signal prediction using machine learning or deep learning. Among the many techniques in automated ECG signal analysis, wavelet transform has been highlighted due to its effectiveness in denoising and feature extraction. Then, a Convolutional Neural Network (CNN) is performed to predict the heartbeat. In the group of many techniques in wavelet transform, it is necessary to find out which is better in heartbeat prediction not only to be trained and tested with a secondary dataset but also with a primary or real dataset of ECG signal. In this paper, we compare the wavelet transform techniques, such as Continuous Wavelet Transform (CWT), Discrete Wavelet Transform (DWT), and Stationary Wavelet Transform (SWT), and also do inferencing. Those techniques were trained and tested by MIT-BIH arrhythmia database. As a result, the highest test accuracy is achieved by CWT with 0.9908 accuracy. Then, by testing it with a 30-minute recording of the ECG signal, the shortest time in inferencing is achieved by DWT in 12.92 seconds. It also used the lowest memory with 109.98 MB and SWT achieved the lowest CPU usage in inferencing with 26.34%.

The classification of Electrocardiogram (ECG) signals plays a crucial role in monitoring and diagnosing cardiac conditions. With the advancements in wearable sensor technology, ECG signals can now be acquired conveniently in real-time using portable devices such as Raspberry Pi. However, the efficient extraction and selection of classification features from ECG signals remain a challenging task. In this study, we present a comparative analysis of classification features for automated ECG signal classification on Raspberry Pi. We evaluate and compare various feature extraction techniques, such as PQRS morphology, RR Interval, and wavelet. The performance of these features is assessed using a machine-learning algorithm random forest. To conduct the experiments, we use proven ECG signal data from MIT BIH arrhythmia, feature extraction techniques were applied to the preprocessed data to derive informative features for classification. The extracted features were used to train and test the machine-learning models. Furthermore, the classifier models were used to predict heartbeats types from wearable sensor data in real time and continuously. The results of our comparative analysis demonstrate the effectiveness and suitability of different feature extraction methods for ECG signal classification on the resource-constrained Raspberry Pi platform. We identify the most discriminative features and evaluate their impact on classification performance. Moreover, we explore the trade-offs between computational complexity and classification accuracy. We discuss the advantages and limitations of each feature extraction technique and provide insights into the feasibility of implementing real-time ECG signal classification systems on wearable devices. Overall, this study contributes to the field of ECG signal analysis by providing a comprehensive comparative analysis of classification features for ECG signal classification on the Raspberry Pi platform. The results and insights obtained from this research can guide the development of efficient and accurate wearable-based ECG monitoring systems for timely diagnosis and intervention in cardiac healthcare applications.

Belajardisini : The E-learning Framework Based on Gamification Concept

Pengembangan Infrastruktur Komunikasi Multigroup Pada Wi-Fi Direct