The implementation of face recognition technique using CCTV is able to prevent unauthorized person enter the gate. Face recognition can be used for authentication, which can be implemented for preventing of criminal incidents. This re-search proposed a face recognition system using convolutional neural network to open and close the real-time barrier gate. The process consists of a convolutional layer, pooling layer, max pooling, flattening, and fully connected layer for detecting a face. The information was sent to the microcontroller using Internet of Thing (IoT) for controlling the barrier gate. The face recognition results are used to open or close the gate in the real time. The experimental results obtained average error rate of 0.320 and the accuracy of success rate is about 93.3%. The average response time required by microcontroller is about 0.562ms. The simulation result show that the face recognition technique using CNN is highly recommended to be implemented in barrier gate system.

Universities annually accept new students at the beginning of the new school year. In the acceptance of prospective students on the Seleksi Prestasi Akademik Nasional Perguruan Tinggi Keagamaan Islam Negeri (SPAN PTKIN) di State Islamic University Of Sunan Ampel Surabaya, many prospective students who do not register will have an impact on income of the State Islamic University Of Sunan Ampel Surabaya institution. If the institution can find out early on the probability of a prospective student who will resign, then the management can take action to retain the prospective student. To overcome this, data mining classification can be carried out. The methods used in this classification are decision trees and naïve bayes. The number of students who did not re register compared to reregister resulted in the data being imbalanced. Data imbalances can affect the accuracy of the classification results. The imbalance of the data used can result in an unsuitable model. The solution to handle the data imbalance is to use the SMOTE and ADASYN oversampling methods. The purpose of this study was to compare performance of the SMOTE and ADASYN methods. The results show that the SMOTE method can balance the data in a balanced way compared to ADASYN. From the test results, the SMOTE method is more suitable to use than the ADASYN method because the ROCAUC SMOTE value is higher than ADASYN.

Penelitian ini mencoba melakukan seleksi pemilihan santri berprestasi, yang nantinya akan direkomendasikan juga untuk mengikuti Program Beasiswa Santri Berprestasi, biasa disingkat PBSB. Sebelumnya di Pondok Pesantren Manbaul Hikam belum ada rekomendasi nama santri untuk mengikuti PBSB. Untuk saat ini, santri mengikuti PBSB hanya sebatas siapa yang ingin mendaftar, kemudian pihak sekolah mengantarkannya untuk mengikuti tes yang diadakan oleh Kemenag. Untuk memudahkan pihak sekolah dalam memperoleh nama - nama santri berprestasi, maka dibangunlah sistem pendukung keputusan pemiliihan santri berprestasi. Melalui sistem, pengguna dapat menambahkan data santri, data nilai santri, dan nilai bobot kriteria. Sistem akan memberikan rekomendasi nama - nama santri berprestasi menggunakan metode AHP dan VIKOR. Kedua metode tersebut dikombinasikan, AHP untuk menghitung bobot kriteria dan VIKOR untuk melakukan perangkingan alternatif. Penggunaan dua metode tersebut bertujuan untuk saling melengkapi kekurangan dari masing - masing metode. Pengujian sistem menggunakan black box, uji sensitivitas nilai vikor, akurasi, recall, dan presisi. Pengujian dilakukan menggunakan data santri tahun lulusan 2015 - 2016 untuk jurusan IPA dan IPS. Berdasarkan pengujian sensitivitas nilai VIKOR, disimpulkan alternatif santri dengan NIS 150106 dan 150129 memiliki sensitivitas perubahan ketika nilai variabel v diubah dengan menggunakan 0.4 dan 0.6. Hasil nilai rata - rata dari uji akurasi sebesar 90,5%, nilai recall 87,5%, dan nilai presisi 35%.

Learning applied in Indonesia from elementary school to undergraduate level generally uses face-to-face or direct learning methods. However, after the Covid-19 disease outbreak, all methods change to online learning methods at all levels and cultures. This affects all aspects of learning such as comfort, understanding and learning outcomes. To find out the difference in the results using face-to-face methods and online methods, a study was carried out on classifying learning media users from elementary school to university level using the k-means method. This study aimed to determine the differences in learning outcomes between the semester before the Covid-19 pandemic and the semester during the Covid-19 pandemic which applies online learning. The results of grouping data on online learning media users showed that all levels of education were considered sufficiently ready to implement online learning. As well as cultural differences in Indonesia have not had an impact on the commitment of schools to implement online learning during the Covid-19 disease outbreak.

Graduation is a series of processing stages that must be passed by each student, one of graduation requirement must complete the courses with a pre-determined amount, carrying out field work practice, research proposal exam, finalexam and must complete several requirements and other requirements which are set by the college. This process should be completed within the allotted time, if not, the student will be drop-out declared. Therefore, it needs a system that can predict and evaluate the history of student course that history has been made to optimize the learning process of the next lecture. Input of this system is the master's student, student academic data, and historical data subjects which has been pursued by the student. The input data will be processed by using the techniques of data mining with C4.5 algorithm. The outputs of this system of classification is in the form of students' academic performance that predicted their graduation and providing recommendations for graduation process timely or in the most appropriate time with the optimal result based on historical subjects that have been taken.Testing on training data student sets produced values of precision, recall, and accuracy for C4.5 mining respectively 100%, 50%, and 75%.