Conventional weed control system is usually used by spraying herbicides uniformly throughout the land. Excessive use of herbicides on an ongoing basis can produce chemical waste that is harmful to plants and soil. The application of precision agriculture farming in the detection IntroductionFarm management systems based on information technology has been widely used to obtain optimum benefit, increase the efficiency of agricultural management [1], protecting the environment [2] and increasing agricultural productivity [3]. Farmers need information from a wide range of ICT tools to identify, analyze, and manage information in spatial and temporal diversity [4] as well as the specific characteristics of the land [5], so that the decision-making process to be more precise during soil preparation, seed selection, fertilizer regulation, management pesticides, watering schedules water and weed management [6].The process of identification of weeds in the field is very important to determine the effective control of this due to lack of proper weed control will cause improper use of herbicides, inefficiencies cost, time and energy [7]. Conventional weed control system is usually done by spraying herbicides uniformly throughout the land [8], it results in excessive use of herbicides will potentially generate waste in the form of chemical residues, emissions to air and soil [9]. Dependence on chemicals also harm human health [10] and the environment [11].The herbicides can be reduced by the application of precision farming application by spraying on right land by detecting weeds on land. Therefore, precision farming is needed to determine the level of weed vegetation in order to control the conditions and needs of the plant based on the specific characteristics of the land [12]. Precision farming is the application of information technology in agricultural management systems that allow rigorous treatment (precise treatment) agribusiness chain from upstream (on farm) to downstream (off farm) [13].Computer vision as one of the precision farming applications is very promising [14] which can be used for the identification and classification of plants. OpenCV is a library Public License can be used to detect the image of weeds. Weed detection in realtime is still difficult to implement in the field due to need a large place and the use of large electric power. The need for specification of minicomputer and small power consumption has attracted the attention of

Analyzing compute functions by utilizing the IAAS model for private cloud computing services in packstack development is one of the large-scale data storage solutions. Problems that often occur when implementing various applications are the increased need for server resources, the monitoring process, performance efficiency, time constraints in building servers and upgrading hardware. These problems have an impact on long server downtime. The development of private cloud computing technology could become a solution to the problem. This research employed Openstack and Packstack by applying one server controller node and two servers compute nodes. Server administration with IAAS and self-service approaches made scalability testing simpler and time-efficient. The resizing of the virtual server (instance) that has been carried out in a running condition shows that the measurement of the overhead value in private cloud computing is more optimal with a downtime of 16 seconds.

Augmented Reality Portal application of Human Herbal Medicinal Plants, it can be concluded that the AR portal application aims to visualize medicinal plants and as a means of knowledge and insight for the general public. That is by utilizing the sophistication of Augmented Reality Portal-based technology that can be accessed using an Android smartphone. The Augmented Reality Portal application of Medicinal Plants in the Insani Herbal Garden has been carried out in the trial phase, the results of the Structural Test show that the system is well structured, the results of the Functional Test show that every button on the system has functioned properly and the Validation Test includes distance testing with maximum results for objects to detect sound, which is 90 cm, slope trials with a distance of 90 cm, maximum results at 45 degrees with a time of 00.66 seconds, light level trials with object detection results faster when the sun is direct with time of 1 second, and testing the android specifications shows that the minimum operating system is android nougat 7.0 and supports AR Core.

The increasing number of vehicles has affected the air quality of Bogor city, one of them is CO gas (Carbon monoxide). CO is included in air pollution variables when the levels are higher than 100 - 300 ppm [1]. In line with one of smart city development strategy City of Bogor is Smart Living to realize a decent, comfortable, and efficient living environment. Bogor City Government conducted traffic engineering around Bogor Botanical Gardens and Bogor Palace with the introduction of One Direction System (SSA) around the clock [4]. This has an impact on the concentration of air pollution around the SSA. The development of sensor and internet technology makes it easy to develop integrated pollution monitoring systems [3]. An Arduino-based air pollution monitoring system is used to detect CO gas. If the concentration of exposure received by the MQ-7 sensor module exceeds the prescribed normal limit the CO gas concentration will be transmitted over the internet and aired on a text-based social media twitter. The device is designed using some components consisting of Arduino, Ethernet Shield, and MQ-7 sensor module. Programs are written and uploaded using C programming languages and the Arduino IDE 1.0.6 compiler. This prototype has been tested in the laboratory and applied to measure CO gas in five subdistricts of Bogor City-road. The results of this system are expected to be used by policymakers as basic information for decision making to reduce pollution level of Bogor City.

Facial Expression Detection is the recognition of a pattern where the input is a digital image and the output is a label of a person's emotions that have been made into a class, which class has been stored in the database as training data to find the closest or similar. Pattern recognition with training data or similar classes is done using artificial intelligence with various methods. This study aims to test the Local Binary Pattern and k-Nearest Neighbors methods to be implemented in facial expression detection and create a system on a computer to be able to know human facial expressions are happy or sad. Local Binary Pattern is defined as the ratio of the binary value of the pixel at the center of the image to the 8 values of the surrounding pixels. K-Nearest Neighbors algorithm with supervised learning which aims to find new patterns in the data by connecting new data patterns with existing data patterns. Based on the results of manual testing on sad expressions, the accuracy is 90% and happy expressions are 80%. Furthermore, the K- Fold Cross Validation test, at 5-Fold Cross Validation at 61.66% and at 10-Fold Cross Validation at 75%.