Saat ini penggunaan smart teknologi pada bisnis tanaman hidroponik merupakan peluang bisnis yang sangat menguntungkan bagi para pelaku usaha. Nilai suatu teknologi dapat meningkatkan kualitas dan kuantitas tanaman hidroponik dan diharapkan adanya efisiensi biaya produksi. Perangkat teknologi cerdas dalam pengelolaan persediaan budidaya hidroponik berbasis IoT merupakan salah satu perangkat precision agriculture yang dikenal juga sebagai smart agriculture. Perangkat ini mampu mencampurkan pupuk dan air secara otomatis sehingga pelaku usaha bisnis tanaman hidroponik dapat mengurangi biaya tenaga kerja. Penelitian ini bertujuan untuk membandingkan analisis kelayakan para pelaku usaha dalam meningkatkan budidaya hidroponik dengan pola konvensional/ manual dan memanfaatkan Hydropo 4.0. Metode penelitian yang digunakan yaitu Net Present Value (NPV) dan Internal Rate of Return (IRR). Hasil penelitian ini menunjukkan bahwa model operasi dengan menggunakan Hydropo 4.0 lebih menguntungkan ketika jumlah populasi tanaman meningkat lebih dari 51,1% dari populasi tanaman pada saat pengujian. Berdasarkan perbandingan nilai IRR pada model operasi menggunakan Hydropo 4.0 akan meningkat apabila populasi tanaman ditingkatkan 698,85% dari jumlah populasi tanaman pada saat pengujian. Abstract[Feasibility of IoT Technology for Hydroponic Holticultural Gardens Using Hydropo 4.0 In Pasundan Natural Plantation, West Java] Presently, the use of smart technology in the hydroponic plant business is a profitable business opportunity for business people. The value of technology can increase the quality and quantity of plants as well as make the efficiency of production costs. Smart technological devices in the management of hydroponics plant culture based on IoT is one of the hydroponic culture supplies that are one of the precision agriculture devices, also known as smart agriculture. This device is capable of mixing fertilizer and water automatically so that hydroponic plant businesses can reduce labor costs. This study aims to compare the feasibility analysis of business actors improving hydroponic cultivation with conventional/manual patterns and utilizing Hydropo 4.0. The research method used by calculating the Net Present Value (NPV) and Internal Rate of Return (IRR) parameters. The result of this study indicate that operation model using Hydropo 4.0 will be more profitable when the number of plant populations increases by more than 51.1% of the plant population at the time of the test. Based on the comparison of the IRR value in the operation model using Hydropo 4.0, it will increase if the plant population is increased by 698.85% of the total plant population at the time of the test.Keywords: feasibility analysis; IoT; IRR; NPV

Breeding chickens and chicken eggs are poignant, and recent studies have applied computer science to optimize this field, including chicken egg harvesting prediction. However, existing research does not emphasize the importance of data transformation to obtain optimum chicken egg harvesting prediction. This paper proposes the normalization and standardization-bolstered support vector machine (NS-SVM) method, namely normalization, and standardization, to improve the prediction of chicken egg harvest using SVM. First, we obtain the chicken egg dataset from Africa using Kaggle. The problem and solution become urgent, whereas chicken egg production can ease businesspeople to invest in chicken eggs. We adopt the normalization and standardization method from previous research. However, the notation is to differentiate the method from legacy SVM. The dataset has up to 13 features. Then we apply standard pre- processing such as label encoding and random oversampling. We also review the dataset feature using the Pearson correlation coefficient (PCC). We use two SVM kernels: radial basis function (RBF) and the 2nd-degree polynomial. Then we again apply the same model but by applying normalization and standardization. We use cross- validation with 𝑲 = 𝟏𝟎 to measure the Accuracy of the compared models. The results show that normalization and standardization positively affect the prediction model of the two SVM kernels. The model with the highest performance is NS-SVM with a 2nd-degree kernel, namely 𝑨𝒄𝒄𝒖𝒓𝒂𝒄𝒚 = 𝟎. 𝟗𝟗𝟔. At the same time, the model with the lowest performance is SVM with RBF, namely𝑨𝒄𝒄𝒖𝒓𝒂𝒄𝒚 = 𝟎. 𝟗𝟖𝟔. In addition, the results of ROC AUC analysis show that the performance of our model on the imbalanced dataset with a moderate degree is 𝑨𝑼𝑪 = 𝟎.𝟗𝟐𝟕 to 𝟎.𝟗𝟗𝟑.