Browsing by Author "Minarni, Minarni"
Now showing 1 - 12 of 12
Results Per Page
Sort Options
Item ANALISA PENGARUH INTENSITAS CAHAYA RUANG TERHADAP KUALITAS GAMBAR PADA SISTEM DETEKSI TBS KELAPA SAWIT(perpustakaan UR, 2021-11) Panjaitan, Deborah Margaretha; Minarni, MinarniFFB (Fresh Fruit Bunches) of oil palm is one of the indonesian commodities that make it possible for Indonesia to be country of the largest CPO (Crude Palm Oil) export in the world. Automatic detection oil palm FFB is very important in the sorting and grading process. The detection of oil palm FFB can be based on color parameters. This study aims to design a program to detect oil palm FFB using a computer vision system with various of luminous. The system is equipped with a webcam, light source and software. This program also to record images, process images and classify them as detected oil palm FFB. Detector works based on the of the HSV value, especially in saturation. Output in this process is forms contour with a bounding box. The sample used in this study was 10 fruit FFB of tenera oil palm varieties. The FFB image of oil palm was recorded using a webcam at an angle of 90⁰. The results showed that the program's success in detecting oil palm FFB in this system depended on luminous of the room because of application in segmentaion color method Hue, Saturation, Value (HSV). The HSV program success in detecting 8 of 10 oil palm FFB with boundaries area contour more than 9000 pixels.Item ANALISA PERBEDAAN VARIETAS KELAPA SAWIT BERDASARKAN TINGKAT KEKERASAN(Elfitra, 2023-01) Rahman, Riky; Minarni, MinarniThe level of maturity of the FFB (Fresh Fruit Bunches) of oil palm is still a priority in determining the quality of CPO (Crude Palm Oil) both conventionally and modernly. Determination of the maturity level of oil palm FFB in Indonesia still uses the traditional method, namely by determining the color and looseness of the palm fruit that falls from the bunches. The level of hardness in this study is needed to determine the oil palm FFB according to maturity using a penetrometer. The sample in this study has 3 maturity levels, namely ripe, unripe, and overripe. The results obtained show that the hardness level test on oil palm FFB at the highest point is the raw maturity level, while the overripe maturity is at the lowest point.Item ANALISA SPEKTRUM INTENSITAS REFLEKTANSI SAMPAH PLASTIK MENGGUNAKAN PENCITRAAN MULTISPEKTRAL(Elfitra, 2023-01) Wahyudi, Dilham; Minarni, MinarniSorting plastic covering is very important before plastic waste was brought into landfill. Manual sorting process has disadvantages such as tediousness, infefficiency, in cost to time, and subjectivity. Multispectral imaging has advantages for plastic waste classification, because it can cover visible range of electromagnetic spectrum, and infrared range (700 – 2500 nm). Reflectance intensity was obtained for each pixel in Region of Interest to classify plastics category. Plastics waste has better response in Near-Infrared range. Results show that average reflectance intensity are different for each plastic category which is 0.170, 0.671, and 0.109 for PET, HDPE, and PP plastic, respectivelyItem ANALISA WARNA RGB SAMPAH BOTOL PLASTIK(Elfitra, 2023-01) Mahmudah, Dewi Anjarwati; Minarni, MinarniPlastic waste is one type of waste that needs to be handled. The amount of plastic waste that continues to increase disrupts the ecosystem. Plastic is one type of waste that is generally produced by Indonesian and it requires a proper management. Waste management in Indonesia is generally still carried out in a traditional way. Digital plastic waste management is need to process to facilitate the recycling process, especially plastic bottle waste by classifying bottle waste based on color. In this research, classification of plastic bottle waste has been carried out. Classification was carried out RGB values of the High Density Polyethylene (HDPE) plastic bottles with several color variations including black, red, blue, green, gray, yellow, and white. The results obtained show that the colour of transparent plastic bottles can be determined based on the RGB value of each sample.Item ANOTASI CITRA MULTISPEKTRAL UNTUK PEMBANGUNAN DATASET MODEL DETEKSI OBJEK PADA KEMATANGAN TANDAN BUAH SEGAR KELAPA SAWIT(Elfitra, 2023-04) Harmailil, Ihsan Okta; Minarni, MinarniComputer vision as an object detection method can be used as a basis for automation process of sorting and grading oil palm FFB (Fresh Fruit Bunches). Images annotation are necessary to build datasets hence object detection model can identify object features in images. This study aims to annotate multispectral images of oil palm FFB with 2 categories, namely ripe and unripe FFB. Image acquisition is carried out with LED-based multispectral imaging system. Annotation is done using the python program application, called Labelimg. The number of annotated image data is 60 images consist of 30 images of ripe FFB and 30 images of unripe FFB. The results of annotation are .txt files contained information about bounding box coordinate, class object, and image dimension.Item ANOTASI CITRA SAMPAH ORGANIK BERBASIS PYTHON UNTUK RANCANG BANGUN SISTEM DETEKSI OBJEK(Elfitra, 2023-01) Putri, Dinda Kamia Evkha; Minarni, MinarniWaste is still a problem faced in daily. A common problem that is closely related to waste is its inefficient management where organic waste is still found mixed with other types of waste in landfills. The solution that can be done to overcome waste management is to utilize the object detection method. Object detection is a method that can be used to determine the presence of objects in an image. This method can be used in waste sorting to make it more efficient than traditional methods. Image annotation is performed as an initial step in building an object detection system. Image annotation’s function is to provide the necessary information for the system to recognize object features in the image. This research aims to annotating the image of organic waste into two types, namely wet organic waste and dry organic waste. The images are acquired in several position variations so that the annotated images can produce models with various conditions that affect the results of object detection. Image annotation is done by utilizing Python-based software. The results of the image annotations that have been carried out are as many as 100 images of wet organic waste and 100 images of dry organic waste, so that there are a total of 200 images that have been annotated.Item DETEKSI TEGANGAN KELUARAN SENSOR ULTRASONIK TERHADAP BUAH-BUAHAN DENGAN KEMATANGAN YANG BERBEDA(Elfitra, 2023-01) Pratama, Muhammad Anra Bayu; Minarni, MinarniAtpresent a lot of agricultural work uses human power in carrying out agricultural production activities including sorting fruit. This process has drawbacks because humans have limitations in carrying out sorting activities and requires a long time, this method is often inaccurate and the results vary, due to different perceptions from each person. Therefore, with the existence of a sensor system for detecting fruit ripeness, it is hoped that it can be put to good use by farmers so that farmers' performance will be more efficient. The results obtained in this study were the detection of the stress of the tested fruits in the form of the output stress value and the maturity of the ripe and unripe fruits. The highest sound absorption occurred in ripe tomatoes with a voltage of 10-11 mV, while the lowest sound absorption occurred in unripe mangosteen with a voltage of 34-35 mV.Item IDENTIFIKASI TINGKAT KEKERASAN TANDAN SEGAR BUAH SAWIT BERDASARKAN TANAH TUMBUH MENGGUNAKAN PENETROMETER(Elfitra, 2023-01) Alvico, Muhammad Andre; Minarni, MinarniThe soil used for fresh fruit bunches of oil palm is mineral soils and peat soil FFB is the main source of crude palm oil (CPO), to obtain fruit with good quality. The sorting and grading processes will be important in the process of selecting high quality CPO. This study is aimed to identification the hardness level of oil palm fruit based on growing soil using a penetrometer. Oil palm of growing soils are collected by tenera oil palm of mineral and peat soils by three ripeness levels as unripe, ripe and overripe. Bunches of fresh palm fruit are taken 3 bunches for each ripeness. Each sample is taken five fruit, the hardness is detected by a penetrometer by pressing each midpoint of the palm fruit of each level of ripeness. The results obtained are quite good where each level of ripeness showed results different, where the more ripe the fruit from the FFB of oil palm will be the softer are obtained mineral soil and peat soil.Item KALIBRASI PERANGKAT LUNAK BERBASIS PYTHON UNTUK PENGUKURAN VOLUME BUAH MENGGUNAKAN METODE PENCITRAAN BERBASIS LASER(2020-06) Lase, Chrisvon; Minarni, MinarniVolume is one of the important quantities that can be used in sorting machine. Imaging method which uses camera and computer has been developed as an alternative method to estimate fruit volume because it is nondestructive and fast. Laser beam with line shape can be used to define the major and minor length of fruit image. This study aims to calibrate Python based software that has been made to determine fruit volume which used ellipsoid equation and Simpson rules. The calibration was performed in order to find the conversion of pixel to centimeter, and then the volume of fruit is in cm3. The result of the calibration was used for some samples such as plastic ball, kiwi fruits and oil palm fruit bunches. The results were compared to the manual calculation using ellipsoid approximation. This study showed that the pixel calibration is 121336 pixels/cm, and the measured volume is in the range from 100 cm3 to 7000 cm3. The difference from the manual results is around 1.37782 %.Item KARAKTERISASI SENSOR GAS MQ UNTUK SISTEM HIDUNG ELEKTRONIK(2020-01) Fadlilah, Annisa; Minarni, MinarniGas sensors of MQ series are economical sensors which often used in an electronic nose system. This study aims to characterize six gas sensors of MQ series for an electronic nose which are used to evaluate honey quality. The sensor used were MQ 2, MQ3, MQ4, MQ5, MQ6, and MQ9. The reason for choosing the MQ types are based on volatile compounds contained in honey types. The six sensors were connected to an Arduino microcontroller. An acquisition program using Arduino IDE was designed and used to obtain output voltages from each sensor. The six sensors were characterized based on their respons on samples of alcohol, honey, and date syrup. The results showed that only 3 sensors are sensitive to honey and date syrup, namely the MQ 3, MQ 4 and MQ 6 sensors while the other sensors such as MQ 2, MQ 5 and MQ 9 are sensitive to air, smoke and carbon monoxideItem PEMBUATAN SISTEM HIDUNG ELEKTRONIK OPTIK UNTUK MENENTUKAN KEMATANGAN BUAH SAWIT(Elfitra, 2022-04) Putri, Annisa; Minarni, MinarniThe ripeness level of oil palm FFB is one of the important factors that need to be considered in efforts to improve the quality of palm oil. Currently, an optical electronic nose system has been developed which is a development of the ordinary electronic nose system. Optical electronic nose system is widely used to evaluate fruit quality by determining the degree of ripeness. In this study, the optical electronic nose system was designed to characterize the maturity level of oil palm FFB by paying attention to the sensor output voltage at each maturity level fraction. This system utilizes an FDS100 photodiode detector as a sensor and an infrared LED as a light source. The sample used was tenera type of oil palm FFB with 3 variations in maturity level, namely raw (unripe), ripe (ripe), and overripe. The system consists of a sensor chamber which contains an LED and a photodiode, a sample chamber and a simple electronic circuit. The detection process was carried out on the fruit of the oil palm.The output voltage measurement was carried out using the PLX-DAQ program which has been connected to the Arduino Mega 2560 program. The data processing uses a python-based program with a numerical integration method using trapezoidal rules. The area of the trapezoidal region represents the voltage generated by the photodiode. The output voltage on the sensor was processed and further analyzed as a trapezoidal area to obtain the maturity classification results. The results showed that there are significant differences in voltage values from the detection results made by the photodiode sensor for the three maturity fractions. The value of the voltage generated in the overripe sample is higher than that for the ripe sample and the raw sample. The graph shows that the overripe sample has a lower peak. This means that the gas particles produced from the overripe palm sample are more than that for the other palm oil samples. This proves that the optical electronic nose system designed is able to detect the maturity level of the oil palm FFB well.Item PENENTUAN LUASAN TRAPEZOID DARI DATA FUNGSI TEGANGAN KELUARAN SENSOR GAS HIDUNG ELEKTRONIK(2021-02) Hermonica, Sri; Minarni, MinarniElectronic nose has been applied in agriculture to classify the level of fruit ripeness. The purpose of this research is determine the trapezoid area of the output voltage function of the electronic nose gas sensor. The samples were oil palm fruits of the Tenera variety. The gas sensors used were the MQ2, MQ3, MQ5 and MQ135. The highest trapezoid area is 152.84 Vs, 103.93 Vs, 93.41 Vs for overripe, ripe and unripe fraction, respectively. This shows that the area of the trapezoid is directly proportional to the level of fruit ripeness.