Plastic waste needs to be handled properly according to its type to reduce its negative impact on the earth, such as the issue of global warming which is still being widely discussed among the public. Good and correct plastic waste management has a significant long-term impact on the issue of global warming. Using the optimization of the extreme programming (XP) method to develop a plastic waste management system. With the system development method used, namely extreme programming, this system helps the community to be aware of waste and manage waste as well and wisely as possible. Extreme programming flexibility supports all changes that occur during the process of building this plastic waste management system. The output produced in the construction of this system is the management and sale of plastic waste that can be recycled according to its type. With usability testing that has been carried out, this system has been evaluated and shows a result of 88.07%, this value means that the plastic waste management system is well accepted to be used in plastic waste management.

Cancer is the second highest cause of death in the world. In Indonesia, it is a disease with a high mortality rate. Most patients do not realize that they have lung cancer thus the treatment is sometimes too late. A prediction method with a high degree of accuracy is needed to detect lung cancer earlier. Previous research used data mining calcification methods with the Naïve Bayes algorithm to predict lung cancer. This research resulted in high recall values for the positive class (Yes class) but low for the negative class (No class). This research was made using the Random Forest algorithm which is known to have good performance. The modeling is optimized by applying the K-fold Cross Validation technique. The Random Forest algorithm produces a higher Accuracy value than the Naïve Bayes algorithm, which is 98.4%. This algorithm produces 100% Recall for the positive class, 80% for the negative class and provides a 100% correct prediction as can be seen from the AUC value of 1. Although a statistical test with a significance level of 5% shows the results of the two algorithms are not significantly different.

Preeclampsia is a disease often suffered by pregnant women caused by several factors such as a history of heredity, blood pressure, urine protein, and diabetes. The data sample used in this study is data on pregnant women in the 2020 time period recorded at health services in the former Cilacap Regency. This study was conducted to compare the final results of the Naive Bayes method and the certainty factor method in providing the results of a diagnosis of preeclampsia seen from the symptoms experienced by these pregnant women. The naïve Bayes approach provides decisions by managing statistical data and probabilities taken from the prediction of the likelihood of a pregnant woman showing symptoms of preeclampsia. Symptoms of preeclampsia, while the certainty factor method determines the certainty value of the diagnosis of preeclampsia in pregnant women based on the calculation of the CF value. The research output compares the two methods, showing that the certainty factor method provides more accurate diagnostic results than the Naive Bayes method. It happens because the CF method requires a minimum value of 0.2 and a maximum of 1 for each rule on the factors/symptoms involved, while the Naive Bayes method only requires values of 0 and 1 for each factor causing preeclampsia in pregnant women.

IBI (Indonesian Midwives Association) Cilacap Regency is a forum for the association of midwife medical personnel in the Cilacap Regency. The performance of midwives can be continuously improved through training that supports all health service activities in the community. One of them is training in the use of information systems to detect the presence of preeclampsia in pregnant women (SIPAKPRIH) from the first to the third trimester by selecting the causative factors experienced by pregnant women. Midwives can take advantage of the expert system to support the performance of midwives in terms of health services for the community, especially pregnant women and the babies/fetus they contain. The solution proposed through this PkM activity is to improve the performance of midwives, especially midwives in Cilacap Regency in supporting health service activities to the community that are useful for monitoring the health of mothers and babies during pregnancy. The output target of this PkM activity is to increase the skills and knowledge of midwives for monitoring the health of pregnant women who are detected with preeclampsia through optimizing SIPAKPRIH.