Embedded Files
At CSDI Lab, we work across disciplines where AI, data science, industrial engineering, and management science meet.
Human–Machine Collaboration & Robotics – how robots and AI systems work with humans to perform repetitive or complex tasks, combining automation, HCI, and process design.
Industrial AI & Machine Learning Applications – applying advanced AI to manufacturing, logistics, and enterprise challenges, with links to predictive analytics, optimization, and cyber-physical systems.
Time Series Analytics & Anomaly Detection – methods for discovering patterns and anomalies in sensor, financial, and operational data, supporting monitoring, forecasting, and risk management.
Optimization & Operations Research – mathematical and computational models to improve production planning, supply chains, and resource allocation.
Data Mining & Statistical Modeling – statistical and computational techniques for forecasting, clustering, classification, and knowledge discovery.
Decision Intelligence & Management Science – integrating AI and optimization with management principles to support decision-making at both strategic and operational levels.
Some of the selected past works are as the following:
Time series analysis and knowledge discovery
Time series analysis and knowledge discovery
Time series data is common in areas like healthcare, transportation, and manufacturing. A key challenge is finding unusual patterns, especially when data is unlabeled or has changing lengths. Our group develops methods to detect these patterns automatically. For example, we can identify irregular heartbeats or sudden traffic issues. These methods work in real time and are designed to fit many types of data and use cases.
Selected papers:
[1] Sutrisno, H. and F.K.H. Phoa, Anomalous variable-length subsequence detection in time series: mathematical formulation and a novel evolutionary algorithm based on clustering and swarm intelligence. Appl. Intell., 2023. 53: p. 29585-29603.
[2] Sutrisno, H. and F.K.H. Phoa, Spatial-temporal traffic anomaly detection in urban freeway systems: A two-stage optimization approach.
intelligent systems with machine learning
intelligent systems with machine learning
Intelligent operations aim to improve how systems perform by using real-time data, automation, and machine learning. Our group focuses on building smart systems that can monitor processes, detect issues early, and make decisions automatically. We use machine learning models to analyze large amounts of data and learn patterns that help systems adapt to changing conditions. For example, in manufacturing, we use sensor data to predict equipment failures and reduce downtime. In transportation, we develop models that respond to traffic patterns and suggest better routes. These systems can learn from experience and continue to improve over time. Our goal is to create operations that are efficient, responsive, and self-optimizing through the use of intelligent technologies.
Selected papers:
[1] Yang, C.-L. and H. Sutrisno, Reducing response delay in multivariate process monitoring by a stacked long-short term memory network and real-time contrasts. Comput. Ind. Eng., 2020. 153: p. 107052.
[2] Yang, C.-L., et al., Identification and Analysis of Weather-Sensitive Roads Based on Smartphone Sensor Data: A Case Study in Jakarta. Sensors (Basel, Switzerland), 2021. 21.
Computational optimization
Computational optimization
Optimization is used to make the best decisions in complex situations. It is important in logistics, planning, and business. Many problems today involve a large number of variables. Our group designed an algorithm that handles high-dimensional problems effectively. It uses smart search strategies and performs well even with thousands of variables. This work supports better decision-making in fast-changing environments.
Selected papers:
[1] Yang, C.-L. and H. Sutrisno, A clustering-based symbiotic organisms search algorithm for high-dimensional optimization problems. Appl. Soft Comput., 2020. 97: p. 106722.
Logistics and supply chain
Logistics and supply chain
Our team applies data analysis to real business problems. We have worked on tools for delivery planning, sales forecasting, and credit scoring. One example is a delivery system that lets trucks hand over goods to motorcycles when traffic is heavy. Another helps bakeries predict afternoon sales using morning data. We also built a model to help banks make safer loan decisions. These tools help reduce waste, save time, and improve service quality.
Selected papers:
[1] Sutrisno, H. and C.-L. Yang, A two-echelon location routing problem with mobile satellites for last-mile delivery: mathematical formulation and clustering-based heuristic method. Annals of Operations Research, 2023: p. 1 - 26.
Decision Analytics
Decision Analytics
Our team applies data analysis to real business problems. We have worked on tools for delivery planning, sales forecasting, and credit scoring. One example is a delivery system that lets trucks hand over goods to motorcycles when traffic is heavy. Another helps bakeries predict afternoon sales using morning data. We also built a model to help banks make safer loan decisions. These tools help reduce waste, save time, and improve service quality.
Selected papers:
[1] Yang, C.-L. and H. Sutrisno, Short-Term Sales Forecast of Perishable Goods for Franchise Business. 2018 10th International Conference on Knowledge and Smart Technology (KST), 2018: p. 101-105.
[2] Sutrisno, H. and S. Halim, Credit Scoring Refinement Using Optimized Logistic Regression. 2017 International Conference on Soft Computing, Intelligent System and Information Technology (ICSIIT), 2017: p. 26-31.
Page updated
Report abuse