– Broiler chickens or broiler chickens are one of the popular sources of nutrition in Indonesia. The production of broilers reaches 3.15 billion heads, with the most production center on Java’s island. The Covid-19 disaster that hit Indonesia caused broilers’ production to decrease due to the government’s social restrictions. To maximize production and reduce production efficiency, artificial Intelligent application innovations are carried out for temperature, humidity, and gas control in broiler chicken coops. Artificial Intelligent methods of developing machines can think like humans to help control and make decisions. This artificial Intelligent model uses a fuzzy logic  Pulse Width Modulator (PWM)model. The device used for control utilizes Internet of Things technology with a microcontroller as its primary device and sensor as an environmental data reader. The microcontroller used is ESP32 which has been embedded with Wifi to facilitate the transmission of data to the server. To read the sensors’ environmental conditions used by temperature sensors, humidity uses DHT11 and ammonia gas using MQ2. Environment data is sent to the server, which is useful for the user monitoring the cage environment’s condition remotely and, if needed, can be controlled by using the application interface. In this research, the process of system development using waterfall method, namely needs analysis, design, implementation and testing. The system’s application results were tested using two models, namely, trying the sensor reading value compared to the weight on the hygrometer and observation of the reaction of chickens in the cage. The test results obtained the difference in value between the sensor and hygrometer can be tolerated and the chicken reaction following the system’s cooling status.

No abstract

Convolutional Neural Network (CNN) is one of the Deep Learning methods that is able to carry out an independent learning process that is popular and appropriate in classifying. The development of technology in the field of Deep Learning, this study aims to assist farmers in identifying the types of infectious diseases that attack chickens based on faecal images using Convolutional Neural Network (CNN) so as to increase production yields. Several infectious diseases that attack chickens can be identified through their feces, including newcastle disease caused by a virus, pullorum caused by bacteria, and coccidiosis caused by parasites. To identify, it is necessary to classify the types of diseases that attack by using images of chicken feces. With deep learning using Keras/TensorFlow, 95.40% of chicken feces images are predicted to be infected with coccidiosis, 94.97% chicken feces images are predicted to be healthy, 90.21% chicken feces images are predicted to be infected with tetelo disease, and 96.50% chicken feces images are predicted to be infected with pullorum disease

Abstrak Objektif. Proses pemodelan karakter 3D memegang peranan penting dalam menghasilkan model karakter 3D yang baik. Proses ini merupakan proses awal yang harus dilalui oleh seorang desainer dalam membuat sebuah model karakter 3D. Setelah proses pemodelan dikerjakan dengan baik agar karakter tersebut bisa dibuat bergerak maka diperlukan proses rigging. Dengan proses pemodelan dan rigging tersebut model karakter 3D bisa digunakan untuk menghasilkan animasi sesuai dengan keinginan animator. Tentunya seorang animator akan memerlukan kerja keras untuk membuat suatu adegan gerakan apabila animasi yang dibuat masih manual. Untuk itu dengan memanfaatkan data BVH, animator akan lebih ringan dalam membuat adegan animasinya. Hasil animasi karakter di tunjukkan kepada 40 responden untuk menilai dan menghasilkan rata-rata tingkat humanoid animasi karakter bernilai 65%. Material and Metode. Menganimasikan model karakter 3D memanfaatkan hasil motion capture (.bvh) Hasil. Animasi karakter 3D dengan menggunakan hasil motion capture menghasilkan animasi yang humanoid. Kesimpulan. Hasil motion capture merupakan susunan tulang yang sudah dilengkapi dengan hasil perekaman gerakan sehingga untuk memproduksi animasi model karakter 3D akan lebih mudah karena animator tidak perlu menggambar tiap gerakan yang diinginkan. Abstrack Objective. The process of modeling 3D characters plays an important role in producing good 3D character models. This process is the initial process that must be passed by a designer in creating a 3D character model. After the modeling process is done well so that the character can be moved, a rigging process is needed. With the modeling and rigging process, 3D character models can be used to produce animations in accordance with the wishes of the animator. Of course, an animator will need to work hard to create a motion scene if the animation created is still manual. For this reason, by utilizing BVH data, animators will be lighter in making their animated scenes. The results of the character animation were shown to 40 respondents to rate and produce an average humanoid character animation level of 65%.   Materials and Methods. Menganimasikan model karakter 3D memanfaatkan hasil motion capture (.bvh) Results. 3D character animation using the results of motion capture produces humanoid animation. Conclusion. The result of motion capture is the arrangement of bones that has been equipped with the results of recording the motion so that to produce animated 3D character models will be easier because the animator does not need to draw every desired movement.