Neonatal death is still a concerning reality for underdeveloped and even for some of the developed countries. Worldwide data indicate that 26.693 babies out of 1,000 births according to Macro Trades. To reduce the death early prediction of endangered baby is crucial. An early prediction enables the opportunity to take ample care of the child and mother so that an early child death can be avoided. Machine learning was used to figure out whether a newborn baby is at risk. To train the predictive model historical data of 1.4 million newborn child data was used. Machine learning and deep learning techniques such as Logical regression, K nearest neighbor, Random Forest classifier, Extreme gradient boosting (XGboost), convolutional neural network, long short-term memory (LSTM). were implemented using the dataset to find out the most robust model which model is the most accurate to identify the mortality of a newborn. From all the machine learning algorithms, the XGboost and random classifier had the best accuracy with 94%, and from the deep learning model, the LSTM had the best outcome with 99% accuracy. Thus, using LSTM of the model shall be best suited to predict whether precaution for a child is necessary.
1 July 2023 in Indonesian Journal of Electrical Engineering and Computer Science
In this paper, with the assistance of some tools and a machine learning model, a smart wind turbine was formed that eliminates some expensive sensors and reduces sensor complexity. Squirrel cage induction generator (SCIG) and six rotor blades make up the proposed design, and depending on the wind's direction, the turbine itself can rotate the rotor hub to produce energy more effectively. Additionally, two stepper motors are coupled to the yaw mechanism with the aid of the rotor hub, and the entire controlling procedure will depend on the direction of the wind. The rotor hub must continuously revolve in the same direction as the wind to maximize wind energy utilization. Additionally, to correctly predict wind degrees, a machine learning model was deployed. Random forest regression was used to train and predict the wind direction. The model is deployed in Raspberry Pi, where the incoming sensor values are being stored. Using the generated data, machine learning model was trained and it can be concluded that the model can potentially replace some of the expensive sensors to reduce cost. The model can be used for similar weather conditions only based on machine learning model and fewer sensors.
This data article provides a dataset on occupational health and safety of welders in Bangladesh regarding eye injury, respiratory disorder, and associated risk factors. The data, collected on a pre-tested structured questionnaire, consist of demographic information (age: 10–77 years, median ∼30 years; working experience: 1–50 years), work environment features (working time per day, type of welding, use of protective equipment), and self-reported health consequences (e.g., burning eyes, headache after work, breathlessness). The data set includes raw data, symptom frequency summary tables, a health symptoms by lifestyle element correlation matrix, and a sample machine learning program for predicting post-work headaches. All raw data are placed in the public domain through the Mendeley Data repository for reuse. No conclusions were drawn in this paper; instead, we present the data and how it may be utilized to allow for further studies on occupational health hazards and prevention measures among welders.