Curah hujan merupakan gejala alam dan banyak bergantung dari banyak faktor serta menjadi bagian yang sangat penting bagi kehidupan di bumi. Air hujan merupakan sumber daya yang banyak dimanfaatkan oleh manusia. Keadaan iklim yang tidak menentu menyebabkan curah hujan menuju ke arah (trend) meningkat atau menurun. Jaringan saraf tiruan merupakan algoritma yang secara umum sangat baik dalam permasalahan pengenalan pola, bekerja dengan menirukan jaringan saraf manusia yang dapat menyimpan informasi-informasi dan membentuk sebuah tujuan dari sistem saraf tersebut. Penggunaan jaringan saraf tiruan sebagai prediksi curah hujan di wilayah Kabupaten Wonosobo menggunakan metode backpropagation untuk mengukur tingkat curah hujan yang turun dalam kurun waktu tertentu, menggunakan data curah hujan stasiun 24 Wanganaji tahun 2009-2011 sebagai pelatihan dan pengujian. Arsitektur jaringan saraf yang digunakan adalah 12-10-1, terdiri dari 12 nilai masukan data curah hujan 12 bulan, 10 neuron hidden layer dan 1 nilai keluaran data curah hujan bulan berikutnya, MSE yang diperoleh pada pelatihan 0.00099899 dicapai pada epoch yang ke 161, dengan koefisien koerelasi R yang dihasilkan sebesar 0.99205, MSE pada pengujian jaringan diperoleh dengan nilai 0.17042.

Rainfall has important role for human life. Rainfall information can be used in several fields including agriculture. As a benchmark for planting periods, water infiltration management, and irrigation. The resources for calculating rainfall are rainfall gauges, ground-based radars and remote sensing satellites. Wonosobo area’s rainfall type is monsoon, meaning that it has one wet period and one dry period. It has fluctuating varied rainfall every month and the availability of rainfall data is uncertain each year. As a mountainous area, Wonosobo’s agricultural sector is very dominant for their economic. Weather Observation, especially rainfall, is important because it can be used by related parties, especially in the agricultural sector. In addition, to provide rainfall data in areas with no observation stations. This study aims to design and implement a rainfall prediction system by developing the Waterfall Model Development Life Cycle (SDLC) Software and implementing backpropagation artificial neural networks (ANN). System development using the SDLC waterfall model was chosen because it is simple, easy to understand and implement. ANN backpropagation is applied in the prediction system because of its advantage that can be applied to a problem related to prediction. Testing on the system built for training and validation produces training accuracy of 93.92% with validation of 73.04%, indicating that the system can be used and has been running expectedly. The best ANN architecture was obtained on the test with input layer 3, hidden layer 12, and output 1 values, learning rate 0.5 momentum 0.9. From the SSE 0.1 target, the SSE is 0.302868.

In the world of education, websites have a very important role in providing information related to the website owner's institution and can also be a medium for promotion. One of the websites we researched was the website of SMK Ma'arif 3 Somalangu. We consider that visitors or users also have a big influence on the website. Some of these reviews encourage us to choose the SUS (System Us-ability Scale) method in analyzing the use of the SMK Ma'arif 3 Somalangu website. From the results of measurements and analysis that have been carried out using SUS, the validity test states that it is valid with the results of Rhitung> Rtabel on the questionnaire items and in the Reliability test with the results of 0.637 which states the results are re-liable. The results showed that the score on the website of SMK Ma'arif 3 Somalangu is 97.43, which gets the predicate A, the Best Imaginable category, while the level of acceptance (feel) of visitors is margin high. The results describe that it is considered that the website of SMK Maarif 3 Somalangu is considered effective, efficient and satisfying for users/visitors and easy to use.

Social media applications currently play many roles and are part of various human activities, on the other hand social media is also very vulnerable to various crimes. Crimes that can occur on social media can include hate speech, defamation, fraud, gambling, pornography, and other harmful actions. This research applies the Digital Forensic Research Workshop (DFRWS) method to search for digital evidence on twitter social media application services that run on the Android operating system. Using MOBILedit Forensic Express and Belkasoft Evidence Center tools to search and analyse digital evidence. Utilising twitter social media application services such as sending messages, creating short statuses or tweets and retweeting. Activities performed by users on twitter social media application services become digital evidence acquired using MOBILedit Forensic Express and Belkasoft Evidence Center tools. Digital evidence retrieval using MOBILedit and Belkasoft tools obtained a comparison that MOBILedit Forensic Express found more data on the twitter social media application than the Belkasoft Evidence Center tool. The findings of digital evidence make several contributions to social media investigations that run on the Android operating system.