Electricity Real-Time Estimation (ERTE) System Universitas Lampung, melalui pemanfaatan IoT (Internet of Things), memberikan informasi mengenai pemakaian listrik tiga fase dalam waktu nyata dan menympannya secara historis. Data tersebut dapat digunakan untuk melakukan prediksi kebutuhan listrik masa depan. Jaringan Syaraf Tiruan merupakan metode yang memungkinkan melakukan prediksi berdasarkan pengamatan pada pola data yang ada seperti layaknya otak manusia. Penelitian dilakukan dalam empat bagian, pertama adalah penentuan lapisan masukan (input layer) terdiri dari tanggal, hari, hari libur, jam, ruangan, dan pemakaian listrik serta lapisan keluaran (output layer) terdiri dari prediksi kebutuhan listrik; kedua adalah pelatihan model; ketiga adalah pengujian Jaringan Syaraf Tiruan. Semua bagian tersebut dibagi ke masing-masing fase RST. Pada bagian keempat, dilakukan prediksi kebutuhan listrik berdasarkan hasil estimasi dari setiap fase. Setelah dilakukan pelatihan dan pengujian dari model jaringan syaraf tiruan, prediksi kebutuhan listrik tiga fase menggunakan Jaringan Syaraf Tiruan memiliki tingkat akurasi yang tinggi, yaitu 99,11%. Hal ini menunjukkan bahwa Jaringan Syaraf Tiruan dengan Backpropagation dapat digunakan untuk melakukan prediksi kebutuhan daya listrik dengan cukup akurat. Backpropagation menurunkan tingkat error yang cukup rendah sehingga hasil prediksi dapat dijadikan dasar dalam melakukan pengelolaan dan perencanaan perkiraan kebutuhan daya listrik untuk gedung yang menggunakan listrik tiga fase.

Cooler is an electronic device used to cool food and drinks. The current cooling system still uses refrigerants that can damage the ozone layer. The thermoelectric based cooling system can be used as an alternative since it produces sufficient temperature difference on both sides by considering its advantages that is more environmentally friendly. This research is aimed to design and built a cooling and heating system using a thermoelectric Peltier TEC 12715 based on microcontroller Arduino uno. This system uses the Peltier thermoelectric effects as coolant and warmer because it produces temperature difference on both sides. Based on this research, in the no load condition the system can produce a cold temperature of 21,3 ℃ and a hot temperature of 80,2 ℃ in the 40th minute of use. When given a load of 300 ml and 220 ml drink bottles, the system can produce a cold temperature of 22,2 ℃ and a hot temperature of 70,7 ℃ in the 40th minute of use. The TEC 12715 Peltier component used in this research produces the optimal temperature if a voltage of 12 volts and a current of 15 amperes are applied to each Peltier component. The designed system is able to operate repeatedly, properly, and continuously since it is directly connected to alternative current power which is common in households.

Banana is a fruit plant that is widely produced in Indonesia. Unfortunately, this plant is very susceptible to diseases which can reduce the quality and quantity of the crop. This paper proposes disease detection in banana plants using a thermal camera. The detection is carried out using image processing techniques with multilevel thresholding methods. The image is captured using a thermal camera, then the image is preprocessed to suit what is desired. After that, so that the position is the same as the image taken using a digital camera, the image produced by the thermal camera is carried out by an image registration process. The image processing result is compared with the ground truth image obtained from a digital camera to determine the effectiveness of the proposed method. The effectiveness of the proposed method is measured using the parameters Recall, Precision, F-measure, and Accuracy. The effectiveness of the proposed method is quite effective because it produces parameter values above 80%, namely the recall value of 86,59%, the Precision of 99,1%, the F-measure of 92%, and the accuracy of 89,78%.