No abstract

Because of the numerous applications domains in which social media networks can be used, the huge volume of data and information uploaded by them is gaining significant interest. Publishing allows consumers to express their thoughts on products and services. Some feedbacks could also influence other users on those things. Therefore, extracting and identifying influencers from social media networks, also profiling their product perceptions and preferences, is critical for marketers to use efficient viral marketing and recommendation strategies. Our major goal in this research is to find the best machine learning model for characterizing influencers on social media networks. However, to achieve this objective, our strategy revolves around applying the PageRank algorithm to profile influential nodes throughout the social media network graph. The results of our experiment showed that the correlation is always different when adding a new parameter to machine learning models, also to determine the suitable model for our needs. In any event, the experiment outcomes are critical and significant to profiling influencers from social media platforms.

Physical activity is an activity of body movement by utilizing skeletal muscles that is carried out daily. One form of physical activity is an exercise that aims to improve health and fitness. Parameters related to health and fitness are heart and muscle activity. Strong and prolonged muscle contractions result in muscle fatigue. To measure muscle fatigue, the authors used electromyographic (EMG) signals through monitoring changes in muscle electrical activity. This study aims to make a tool to detect the effect of muscle fatigue on cardiac signals on physical activity. This research method uses Fast Fourier Transform (FFT) with one group pre-test-post-test research design. The independent variable is the EMG signal when doing plank activities, while the dependent variable is the result of monitoring the EMG signal. To get more detailed measurement results, the authors use MPF, MDF and MNF and perform a T-test. The test results showed a significant value (pValue <0.05) in the pre-test and post-test. The Pearson correlation test got a value of 0.628 which indicates there is a strong relationship between exercise frequency and plank duration. When the respondent experiences muscle fatigue, the heart signal is affected by noise movement artifacts that appear when doing the plank. It is concluded that the tools in this study can be used properly. To overcome noise in the EMG signal, it is recommended to use dry electrodes and high-quality components. To improve the ability to transmit data, it is recommended to use a Raspberry microcontroller.

No abstract

<span lang="EN-US">Mental health disorders affect many aspects of patient’s lives, including emotions, cognition, and especially behaviors. E-health technology helps to collect information wealth in a non-invasive manner, which represents a promising opportunity to construct health behavior markers. Combining such user behavior data can provide a more comprehensive and contextual view than questionnaire data. Due to behavioral data, we can train machine learning models to understand the data pattern and also use prediction algorithms to know the next state of a person’s behavior. The remaining challenges for this issue are how to apply mathematical formulations to textual datasets and find metadata that aids to identify the person’s life pattern and also <span>predict the next state of his comportment. The main idea of this work is to use a hidden Markov model (HMM) to predict user behavior from social media applications by analyzing and detecting states and symbols from the user</span> behavior dataset. To achieve this goal, we need to analyze and detect the states and symbols from the user behavior dataset, then convert the textual data to mathematical and numerical matrices. Finally, apply the HMM model to predict the hidden user behavior states. We tested our program and identified that the log-likelihood was higher and better when the model fits the data. In any case, the results of the study indicated that the program was suitable for the purpose and yielded valuable data.</span>