DSDebaleen Das Spandan

Debaleen Das Spandan

*This is an algorithmically generated author record based on publicly available information.

Debaleen Das Spandan has a total of 9 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Exploiting Multi-modal Contextual Sensing for City-bus’s Stay Location Characterization: Towards Sub-60 Seconds Accurate Arrival Time Prediction

    by Ratna Mandal, Prasenjit Karmakar, Soumyajit Chatterjee, Debaleen Das Spandan, Shouvit Pradhan, Sujoy Saha, Sandip Chakraborty, Subrata Nandi

    Intelligent city transportation systems are one of the core infrastructures of a smart city. The true ingenuity of such an infrastructure lies in providing the commuters with real-time information about citywide transport like public buses, allowing them to pre-plan their travel. However, providing prior information for transportation systems like public buses in real-time is inherently challenging because of the diverse nature of different stay-locations where a public bus stops. Although straightforward factors like stay duration extracted from unimodal sources like GPS at these locations look erratic, a thorough analysis of public bus GPS trails for 1,335.365 km at the city of Durgapur, a semi-urban city in India, reveals that several other fine-grained contextual features can characterize these locations accurately. Accordingly, we develop BuStop , a system for extracting and characterizing the stay-locations from multi-modal sensing using commuters’ smartphones. Using this multi-modal information BuStop extracts a set of granular contextual features that allows the system to differentiate among the different stay-location types. A thorough analysis of BuStop using the collected in-house dataset indicates that the system works with high accuracy in identifying different stay-locations such as regular bus stops, random ad hoc stops, stops due to traffic congestion, stops at traffic signals, and stops at sharp turns. Additionally, we develop a proof-of-concept setup on top of BuStop to analyze the potential of the framework in predicting expected arrival time, a critical piece of information required to pre-plan travel at any given bus stop. Subsequent analysis of the PoC framework, through simulation over the test dataset, shows that characterizing the stay-locations indeed helps make more accurate arrival time predictions with deviations less than 60 seconds from the ground-truth arrival time.


  • Open Access

    Can I take class in that classroom now? In the perspective of Air Quality

    by Praveen Kumar Sharma, Debjit Chatterjee, Debaleen Das, Sujoy Saha

    Air quality is degrading over time due to industrial and technological growth. Indoor air quality can be 5-10% poor than that of outdoor. The classroom is one of the most susceptible locations of indoor environments where these pollutants affect the children physically as well as cognitively. Dealing with such scenarios requires knowledge of the concentration of pollutants in each classroom. There are air quality monitoring devices available in the market, which help keep track of the air quality inside a room. However, the available devices are costly, and their setup requires effort, time, and other resources. To address these problems, we first develop machine learning models that can calculate the air quality inside a room using readily available features and data from a simple thermo-hygrometer placed inside the room. Then we developed a mobile application with an easy-to-use graphical interface that helps the user feasibly get the air quality information of each room in a building. These resulted in an end-to-end system that provides a user the knowledge of the air pollutants in an indoor environment. A thorough analysis of the system by deploying it in a local area comprising multiple classrooms inside an educational institution indicates that the system works with an accuracy of 78%. Additionally, we have conducted a Post-Study System User Questionnaire (PSSUQ) survey with the help of 53 users. We have achieved an overall score of 1.75 from the survey indicating the high usability of the system.