Spatial Semantic Analysis and Origin-Destination Prediction Based on Extensive GPS Trajectory in Jakarta

Humasak Simanjuntak, Agnes Hutauruk, Haryati Situmorang, Yoshua Silitonga — Wed, 06 Aug 2025 00:00:00 +0000

The rapid growth of mobility data from GPS trajectories offers unprecedented opportunities to gain deep insights into human mobility behavior, with significant implications for urban planning, traffic management, public transportation optimization, emergency response, and smart city development. However, a key challenge lies in transforming raw GPS trajectory data, consisting of sequences of coordinates and timestamps, into meaningful, context-rich information that can support analysis and decision making. This study proposes a semi-supervised framework to enhance the contextual and semantic understanding of journeys, using Grab Jakarta GPS trajectory data as a case study. The framework involves extracting origin-destination pairs, augmenting the data with temporal (day, time) and spatial (postal code, land use) contexts through public datasets, assigning cluster labels to characterize groups of journeys, analyzing mobility patterns, and ultimately predicting trip destinations. Origin-destination clustering, performed using the DBSCAN algorithm, identified five meaningful clusters, achieving the highest silhouette score of 0.56 with epsilon = 7.0 and min_samples = 5. Subsequently, a regression-based prediction model was developed, employing nine algorithms, including three deep learning approaches. The LSTM model demonstrated the best performance, yielding a mean squared error of 0.0053 and a coefficient of determination (R²) of 86.20% in predicting trip destinations. These findings highlight the potential of integrating spatial-temporal enrichment and machine learning to derive actionable insights from GPS trajectory data.

A Web-Based Forecasting Approach to Estimating the Number of Low-Income Households Eligible for Social Food Aid Using Holt’s Double Exponential Smoothing

Fri, 28 Nov 2025 00:00:00 +0000

This work presents a web-based forecasting methodology for predicting the quantity of low-income households qualified for social food assistance utilizing Holt’s Double Exponential Smoothing (HDES) technique. Precise assessment is crucial for governmental bodies and social welfare organizations to guarantee efficient aid distribution and effective resource allocation. The proposed method amalgamates time series forecasting models with a web-based application to deliver real-time predictions and accessibility for decision-makers. Historical data on low-income household statistics were employed to formulate and authenticate the forecasting model. The findings indicate that HDES delivers dependable short-term predictions with low error rates, accurately reflecting patterns in the data. This online application offers policymakers an effective means for monitoring socio-economic trends and enhancing the responsiveness of social assistance initiatives. This research contributes by integrating statistical forecasting with web-based applications to aid social policy decisions.

Register: Jurnal Ilmiah Teknologi Sistem Informasi

Spatial Semantic Analysis and Origin-Destination Prediction Based on Extensive GPS Trajectory in Jakarta

A Web-Based Forecasting Approach to Estimating the Number of Low-Income Households Eligible for Social Food Aid Using Holt’s Double Exponential Smoothing