Journal homepage: https://shmpublisher.com/index.php/joscex  163 Room occupancy classification using multilayer perceptron Dandi Indra Wijaya 1 , Muhammad Kahfi Aulia 2 , Jumanto 3 , M. Faris Al Hakim 4 1,2,3,4 Department of Computer Science, Universitas Negeri Semarang, Indonesia Article Info ABSTRACT Article history: Received Aug 28, 2021 Revised Sep 3, 2021 Accepted Sep 7, 2021 A room that should be comfortable for humans can create a sense of absence and appear diseases and other health problems. These rooms can be from boarding rooms, hotels, office rooms, even hospital rooms. Room occupancy prediction is expected to help humans in choosing the right room. Occupancy prediction has been evaluted with various statistical classification models such as Linier Discriminat Analysis LDA, Classification And Regresion Trees (CART), and Random Forest (RF). This study proposed learning approach to classification of room occupancy with multi layer perceptron (MLP). The result shows that a proper MLP tuning paramaters was able estimate the occupancy with 88.2% of accuracy . Keywords: Multilayer Perceptron Room Occupancy Artificial Neural Network Machine Learning Binnary Classification This is an open access article under the CC BY-SA license. Corresponding Author: Dandi Indra Wijaya, Department of Computer Science, Universitas Negeri Semarang, Sekaran, Gunungpati, Semarang, Indonesia. Email: dandiindra29@students.unnes.ac.id 1. INTRODUCTION Habitability is something that must be met if someone wants to use a room to carry out activities. Rooms that should be inhabited by humans can cause discomfort and appear diseases and other health problems [1]. These rooms can be from boarding rooms, hotels, office rooms, even hospital rooms. Even though the room looks beautiful, there are other variables invisible to the human eye that can make a room uninhabitable, such as temperature and humidity. This can be caused by various things, from global warming, poor air ventilation, the lifestyle of the occupants of the room itself, and so on. In an office or work room, work productivity can reach its maximum level if the working room conditions meet the minimum standards so that a person can work effectively and efficiently [2]. The source of danger in the workroom is a hot work climate that can cause physiological impacts in the form of an increase in body temperature, blood pressure and pulse [3]. One of the causes of hot room is global warming. The impact of global warming is felt on a regional scale [4]. External conditions in the work environment consist of the suitability of room temperature to environmental conditions, relative humidity of the air, and air flow to body temperature. Uncomfortable conditions can interfere with concentration and cause not optimal work productivity. Visual comfort such as lighting can also affect work productivity [2]. Urbanization has negative impacts such as decreasing quality, increasing environmental damage, increasing greenhouse gas emissions, and socio-economic problems [5]. As a result of the increasing number of urban residents, uninhabitable and irregular residential areas have emerged which are faced by almost all cities in Indonesia [6]. The environment as measured by the comfort of the room can affect the price of the room and in a case study of renting a boarding house around the University of Samudra, the prices given to residents sometimes do not match the environmental conditions and quality of the room [7]. The need for ventilation air lanes must meet the comfort and health of indoor temperatures as an energy conservation effort [8].