This study aims to compare the best method on the forecasting system of rainfall in Medan using Single Exponential Smoothing (SES), Naive Model, and Seasonal Autoregressive Integrated Moving Average (SARIMA) . The data used in this study is rainfall data for 10 years (2009 – 2019). From the simulation by comparing existing method, the best model is SES with  and value of MAPE (Mean Absolut Percentage Error) sebesar 2,47%. And then  SARIMA (1,01,1)(4,0,3)12 whit value of MAPE  is2,93%. Both of this model is high accurate model because value of MAPE resulted < 10%.

Penjaminan dan peningkatan mutu pendidikan tidak lepas kaitannya dengan manajemen mutu. Berkaitan dengan itu perlu adanya upaya pengendalian mutu (quality control) secara berkelanjutan. Lemahnya komitmen kepala sekolah, guru, tenaga pendidikan dalam melaksanakan sistem penjaminan mutu, serta keterbatasan jumlah kompetensi SDM dalam pemahaman SPMI di SMA Negeri 2 Tebing Tinggi membuat sistem penjaminan mutu sekolah tidak berjalan dengan maksimal.  Kegiatan Pengabdian kepada Masyaraat (PkM) ini bertujuan memberikan pendampingan dan sosialisasi sistem penjaminan mutu pendidikan mengikuti siklus SPMI yang disempurnakan berbasis digital untuk memastikan pelaksanaan SPMI berjalan dengan terus menerus dan berkelanjutan di SMA Negeri 2 Tebing Tinggi serta melakukan pemetaan mutu untuk membangun sistem pengawasan sekolah. Kegiatan PkM Pengembangan Sistem Penjaminan Mutu Sekolah Berbasis Digital dimulai dengan melakukan pemetaan mutu berdasarkan Standar Nasional Pendidikan (SNP), pembuatan Rencana Kerja Sekolah (RKS), pemenuhan mutu baik dalam pengolahan SNP pada proses pembelajaran, monitoring dan evaluasi pelaksanaan, penetapan standar baru, evaluasi hasil implementasi, dan pembuatan sistem penjaminan mutu sekolah berbasis digital. Kegiatan ini menghasilkan luaran berupa sistem penjaminan mutu sekolah berbasis digital yang memuat standar mutu, prosedur operasional baku, kurikulum, RKS, data siswa, guru, prestasi siswa, serta prestasi guru. Kata Kunci : Digital; Penjaminan Mutu; Sistem

Diabetic retinopathy is the leading cause of blindness suffered by working-age adults. The increase in the population diagnosed with DR can be prevented by screening and early treatment of eye damage. This screening process can be conducted by utilizing deep learning techniques. In this study, the detection of DR severity was carried out using the hybrid CNN-DELM method (CDELM). The CNN architectures used were ResNet-18, ResNet-50, ResNet-101, GoogleNet, and DenseNet. The learning outcome features were further classified using the DELM algorithm. The comparison of CNN architecture aimed to find the best CNN architecture for fundus image features extraction. This research also compared the effect of using the kernel function on the performance of DELM in fundus image classification. All experiments using CDELM showed maximum results, with an accuracy of 100% in the DRIVE data and the two-class MESSIDOR data. Meanwhile, the best results obtained in the MESSIDOR 4 class data reached 98.20%. The advantage of the DELM method compared to the conventional CNN method is that the training time duration is much shorter. CNN takes an average of 30 min for training, while the CDELM method takes only an average of 2.5 min. Based on the value of accuracy and duration of training time, the CDELM method had better performance than the conventional CNN method.

AbstrakHampir 70% siswa kelas satu dan dua di sekolah Amalia kemampuan membacanya rendah. Dan lebih dari 50% siswa kelas tiga keterampilan membaca khusunya membaca pemahaman juga masih rendah. Tak jauh berbeda dengan keterampilan membaca,, lebih dari 70% siswa kelas tiga memiliki kemampuan mengarang rendah. Begitu juga dengan TK Amalia lebih dari 50% siswanya belum memiliki kemampuan dan keterampilan membaca yang baik, dan kesadaran fonologis yang masih rendah. Peran serta guru dalam mengikuti pelathan-pelatihan yang bertujuan meningkatkan sumber daya juga masih rendah. Sekolah jarang diundang untuk mengikuti pelatihan-pelatihan yang diadakan oleh dinas setempat.Oleh karena itu perlu dilakukan kegiatan-kegiatan yang dapat meningkatkan pemahaman dan keterampilan guru dalam melakukan inovasi pembelajaran khusunya keterampilan literasi. Dengan kegiatan tersebut, dapat menumbuhkan minat membaca dan budaya suka baca pada siswa SD dan TK di Sekolah Amalia.Kata kunci : keterampilan literasi, mini book, minat membacaAbstractAlmost 70% of first and second graders at Amalia's school have a low reading ability. And more than 50% of students of grade 3 reading skills especially reading comprehension are still low. Not much different from reading skills, more than 70% of third graders have low writing skills. Likewise with Amalia kindergarten more than 50% of students do not have the ability and good reading skills, and phonological awareness is still low. Participation of teachers in follow-training training aimed at improving resources is also low. Schools are rarely invited to attend trainings organized by local agencies. Therefore it is necessary to do activities that can improve the understanding and skills of teachers in conducting learning innovations especially literacy skills. With these activities, can foster interest in reading and reading culture in elementary and kindergarten students at Amalia School.Keywords: literacy skills, mini book, reading interest

Poverty reduction is a crucial issue and the primary The North Sumatra Provincial government's main concern is lowering the poverty rate, which is a crucial issue. The Province of North Sumatra in Indonesia, one of many nations affected by the Covid-19 pandemic, is particularly troubled economically. In this study, poverty levels were mapped using the K-Means algorithm, and GRNN was then utilized for modeling and prediction. The data source used is time series data from 2010 to 2020 from the Central Statistics Agency (BPS), which includes variables X covering population, health, education, unemployment, and asset ownership and variable Y representing poverty level. The goal of this study is to choose the best model for estimating poverty levels in North Sumatra Province. The districts and cities of Deli Serdang and Medan have the greatest rates of poverty, according to the K-means algorithm's mapping of poverty levels. Additionally, the results of the predicting produced MSE values of 0.004659 and RMSE values of 0.00002108. The value of the smoothness parameter is 0.01.