<![CDATA[Abstrak Penggunaan insektisida dalam pertanian meningkat pesat namun juga menghadapi tantangan terkait dampak negatifnya terhadap kesehatan manusia dan lingkungan. Salah satu insektisida yang umum digunakan adalah profenofos. Profenofos sering digunakan petani untuk mengendalikan hama pada tanaman cabai merah di Indonesia. Oleh karena itu, deteksi residu insektisida profenofos pada cabai penting untuk memastikan keamanan konsumsi cabai. Penelitian ini bertujuan untuk mengembangkan metode baru dalam mendeteksi residu insektisida profenofos pada cabai merah (Capsicum Annum L.) melalui augmentasi citra dan CNN (Convolutional Neural Network). Dalam penelitian ini, dilakukan penyiapan larutan insektisida, pengambilan citra cabai, pengujian dengan GC (Gas Chromatography) Agilent 6890N, pra-pemrosesan citra, dan implementasi pemodelan CNN. Dilakukan penyemprotan pada 15 cabai dengan konsentrasi 0 dan 10 mg/l, diikuti pengambilan citra menggunakan smartphone sehingga terdapat 30 citra. Selanjutnya, setiap citra diaugmentasi sebanyak 50 kali, menghasilkan total 1530 citra. Proses ini melibatkan rotasi, pergeseran, zoom, serta horizontal dan vertical flipping. Model CNN yang terdiri dari convolution layer dan fully connected dilatih dengan optimizer Adam, loss function categorical crossentropy, learning rate 0,0001, dan dilakukan pelatihan sebanyak 20 epoch. Hasil analisis menunjukkan bahwa model mencapai akurasi sebesar 85% dengan nilai precision, recall, dan F1-score masing-masing adalah 0,86; 0,85; dan 0,84. Berdasarkan hasil tersebut, dapat disimpulkan bahwa metode augmentasi citra dan CNN telah berhasil mendeteksi residu insektisida profenofos pada cabai merah dengan konsentrasi 0 dan 10 mg/l. Abstract The use of insecticide in agriculture is rapidly increasing but also faces challenges related to their negative impacts on human health and the environment. One commonly used insecticide is profenofos. Farmers frequently use Profenofos to control pests on red chili plants in Indonesia. Therefore, detecting profenofos insecticide residue on chili is crucial to ensure the safety of chili consumption. This study aims to develop a new method for detecting profenofos insecticide residues on red chilies (Capsicum Annum L.) through image augmentation and CNN (Convolutional Neural Network). In this study, insecticide solution preparation, chili image acquisition, testing with GC (Gas Chromatography) Agilent 6890, image preprocessing, and CNN model implementation were conducted. Insecticide solution spraying was conducted on 15 chilies with concentrations of 0 and 10 mg/l, followed by smartphone image acquisition, resulting in 30 images. Subsequently, each image was augmented 50 times, resulting in 1530 images. This process involves rotation, shifting, zoom, and horizontal and vertical flipping. The CNN model, consisting of convolution layers and fully connected layers, was trained with the Adam optimizer, categorical cross-entropy loss function, the learning rate of 0,0001, and trained for 20 epochs. The analysis results indicate that the model achieved an accuracy of 85% with precision, recall, and F1-score values of 0,86, 0,85, and 0,84, respectively. Based on these results, it can be concluded that the image augmentation and CNN method successfully detected profenofos insecticide residues on red chilies at concentrations of 0 and 10 mg/l.]]>
Copyrights © 2024
