<p>Diseminasi merupakan proses dimana seseorang menyebarkan informasi atau pengetahuan sehingga menjangkau orang lain. Sebuah tipe interaksi yang dilakukan manusia sebagai makhluk sosial di berbagai tempat dan situasi. Termasuk semua aktivitas yang berjalan di Fakultas Ilmu Komputer (FILKOM). Tidak semua penghuni di dalamnya melakukan interaksi secara efisien. Akibatnya, mahasiswa dihadapi kesulitan dalam menjalani kegiatan baik sebagai mahasiswa ataupun saat lulus nanti. Portal media interaksi merupakan tempat melakukan interaksi sosial secara daring. Adanya portal media akan membantu menyelesaikan kurangnya interaksi antar sivitas akademik. Portal media dirancang dengan menggunakan metode Human Centered Design. Terdapat 4 tahapan yaitu menentukan konteks pengguna, spesifikasi kebutuhan, perancangan desain solusi, dan evaluasi desain. Rancangan portal media ini menyediakan berbagai macam fitur. Mulai dari penyediaan kontak seluruh sivitas akademika, tempat obrolan, pencarian anggota kegiatan fakultas, hingga pemusatan informasi-informasi terbaru. Evaluasi pengujian dilakukan dengan menerapkan 3 aspek <em>usability</em> (<em>effectiveness</em>, <em>efficiency</em>, dan <em>satisfaction</em>) dan <em>user</em> <em>experience</em>. Alat yang digunakan dalam pengujian adalah aplikasi Maze, kuesioner SUS, dan UEQ. Pengujian dibagi atas segmentasi alumni sebanyak 5 orang dan 10 orang mahasiswa. Hasil pengujian alumni untuk 3 aspek adalah 90%, 95% dan 73. Hasil UEQ mendapatkan 4 Excellent, 1 Good, dan 1 Above Average. Untuk mahasiswa menghasilkan rata-rata nilai sebesar 82%, 93%, dan 77,25. Hasil UEQ oleh mahasiswa yang didapatkan adalah 5 Excellent dan 1 Good.</p><p> </p><p><em><strong>Abstract</strong></em></p><p><em>Dissemination is a process when someone spreads information or reaches out to others. A type of interaction that humans do as social beings in various places and situations. Covers all activities that take place in The Faculty of Computer Science (FILKOM). Not all residents in it interact efficiently. As a result, students face difficulties in carrying out activities whether as students or when they graduate later. The interaction media portal is a place for online social interactions. The existence of a media portal will help the lack of interaction among academics. The media portal is designed using the Human Centered Design method. There are 4 stages, namely determining the user context, requirements specification, design solution, and design evaluation. The design of this media portal provides various features. Starting from providing contacts for all civitas academics, chat rooms, searching for faculty members, to centralizing the latest information. Requirements specifications obtained after understanding users using User Journey and generating user flows for the media portal. From this, the design is carried out starting from the wireframe, mockup, to prototype. Test evaluation is done by applying 3 aspects of usability (effectiveness, efficiency, and satisfaction) and user experience. Using the Maze application, SUS questionnaire, and UEQ in the testing process. The test is divided into segmentation for 5 alumni and 10 students. The alumni test results for 3 aspects are 90%, 95% and 73. The UEQ results get 4 Very Good, 1 Good, and 1 Above Average. For students, the average scores were 82%, 93%, and 77.25. The UEQ results obtained by students are 5 Excellent and 1 Good.</em></p><p><em><strong><br /></strong></em></p>

Exotic fruit is a fruit that is not widely known to the public. In Indonesia, there are many exotic fruits such as rambutan, passion fruit, mangosteen, longan, guava, and many more. Classification of exotic fruit images is needed because of the lack of knowledge from outsiders about exotic fruits in Indonesia. To his end, developing robust artificial intelligence using deep learning is necessary. CNN is the development of the Multilayer Perceptron (MLP) which is designed to process two-dimensional data and in the type of Deep Neural Network because of the high network depth and widely applied to image data. By utilizing the transfer learning method and a little fine-tuning, the efficient model like MobileNet expected to be better than without transfer learning in FruitNet model. Our contribution is applying efficient transfer learning MobileNet for Exotix Fruits in Indonesia which achieves 87% accuracy in average using more than 1000 images. The model performs better than previous model of FruitNet which only reaches 43% accuracy in average.