Leptospirosis outbreaks in various parts of the world have been linked to changes in the weather. Furthermore, the effects have been shown to occur at different lags of up to 10 months, affecting the performance of simulation models that predict leptospirosis occurrence. In Malaysia, the link between different weather parameters, at different time lags, has yet to be established despite an increasing number of cases in recent years. In this study, a combination of data mining and machine learning is used to analyze, capture, and predict the relation between leptospirosis occurrence and temperature, rainfall, and relative humidity using the Seremban district in Malaysia as a case study. First, the optimal time lags for rainfall were determined using graphical exploratory data analysis (EDA) while non-graphical EDA was used for temperature. Then, an artificial neural network (ANN) model is developed to classify the combination of selected features into disease occurrence and non-occurrence using back-propagation training, optimizing the number of hidden layers and hidden nodes. The success is measured using accuracy, sensitivity, and specificity of each model. EDA has shown that leptospirosis occurrence in Seremban is highly correlated with weekly average temperature at lag 16 weeks and weekly rainfall amount at lag 12-20 weeks. Using these selected features, the ANN model achieved the highest accuracy, sensitivity, and specificity at 84.00, 86.44, and 79.33%, respectively. Overall, the EDA approach has increased the accuracy of the predictive model by 13.30-31.26% from the baseline models.

This paper reviewed the weed problems in agriculture and how remote sensing techniques can detect weeds in rice fields. The comparison of weed detection between traditional practices and automated detection using remote sensing platforms is discussed. The ideal stage for controlling weeds in rice fields was highlighted, and the types of weeds usually found in paddy fields were listed. This paper will discuss weed detection using remote sensing techniques, and algorithms commonly used to differentiate them from crops are deliberated. However, weed detection in rice fields using remote sensing platforms is still in its early stages; weed detection in other crops is also discussed. Results show that machine learning (ML) and deep learning (DL) remote sensing techniques have successfully produced a high accuracy map for detecting weeds in crops using RS platforms. Therefore, this technology positively impacts weed management in many aspects, especially in terms of the economic perspective. The implementation of this technology into agricultural development could be extended further.

Waterborne disease has a worldwide distribution and it was frequently happening in developing countries but rarely happen in developed countries [1]. The waterborne disease belongs to the top five common diseases that cause of death. While leptospirosis is one of the top killers of water-borne diseases because more than 500 000 cases were recorded every year [2]. Malaysia is one of the developing countries and is one of the countries that face this disaster [3]. Generally, human will be infected with leptospirosis when they have direct contacts with the product of infected animals such as urine. Besides, they also can be infected by the indirect way by contact with the contaminated water or soil which consist of the leptospira species. This disease also can be infected through human to human transmission but based on the number of cases it is very rare [4]. This pathogen can survive in tropical and subtropical environments Abstract: Leptospirosis is one of the waters borne diseases that widespread in Asia Pacific regions, especially developed countries. Over the past few years, the clinical data have shown Seremban experienced a significant number of leptospirosis patient. To minimize the impact of this disease, this study has set one objective which is to develop one prediction model to predict the leptospirosis diseases confirmed-cases by using Back-Propagation Neural Network (BPNN). A growing number of studies has shown the climate can be a predictor in outbreak incidence. Likewise, climate variable such as rainfall, temperature, and relative humidity affect in many ways especially for the transmission of vector and pathogens. Thus, these 3 parameters will be the main input for this model. Technically, this study will focus on the accuracy and the sensitivity of the model by finding the relationship between the meteorological data and clinical data. The clinical data was provided from the ministry of health Negeri Sembilan, while the meteorological data was provided from the Drainage and Irrigation Department and the Malaysian Meteorological Department. This study acknowledges that the amount of rainfall was correlated with the leptospirosis cases in all region of Seremban states such as Mantin, Seremban, Perentian, and Sikamat. In this study, preliminary exploration was performed by finding the best time for the meteorological data to correlate with clinical data (1 until 5-month lag). The model achieved 70% accuracy in prediction by combining the sum of rainfall, relative humidity, and temperature with 3-month lag as an input of the BPNN model. In conclusion, the authors believe this achievement of the model is an early stage for the prediction model. This model can achieve more than 70% accuracy by adapting some exploratory data analysis for every single variable or predictor.

No abstract