M. Prathilothamai

Bio: M. Prathilothamai is an academic researcher from Amrita Vishwa Vidyapeetham. The author has contributed to research in topics: Computer science & Spark (mathematics). The author has an hindex of 3, co-authored 7 publications receiving 24 citations.

Drone Design for First Aid Kit Delivery in Emergency Situation

Abstract: Ambulance getting stuck in traffic has resulted in countless precious lives. Statistics have shown that especially in the Indian traffic conditions the chances of such scenarios are at peak. In this paper we are providing a solution to speed up the delivery procedure of first aid kit in situations including but not limited to (i) Ambulance getting stuck in traffic, (ii) War torn regions with limited medical supply etc. From the minor ailment to the more serious injury a first aid kit can help reduce the risk of infection or the severity of the injury. With drones changing the face of human technology, it can be used in the medical field to assert timely delivery of essential first aid to people in not easily accessible regions. When the user books an ambulance for the victim, if the ambulance is stuck in traffic, Automated drones can deliver personalized first aid kit to the user location so that the victim can be diagnosed by the remedy medicines with assistance of doctor using web app till the ambulance arrives to the victim location and takes the victim to hospital. Users can also request pharmacy for immediate remedy medicines in case of emergency.

Cost Effective Road Traffic Prediction Model using Apache Spark

Abstract: Objectives: We proposed a cost effective model to predict the traffic to inform the public about the current traffic condition to all persons who are entering the same lane. Analysis: In real time application like traffic monitoring, it needs to process huge volume of data in huge size. We analyzed the traffic prediction using the current technologies Apache Hadoop and Apache Spark framework. Spark is processing the 10 Terabytes of data in half-a-second. The main uniqueness from our approach is that we can predict the road traffic using Spark within half-a-second. Findings: Road traffic is predicted using Ultrasonic and PIR sensor within a half second. The proposed system uses the vehicle count and speed to predict the traffic condition. Existing system using hadoop will predict the traffic in few seconds. Whereas in the proposed system performance gets increased using Spark. Therefore, the results are more helpful in finding the road traffic condition. Improvement: The proposed system predicts it in a half a second by using Spark whereas the existing system predicted the road traffic by consuming more time.

Timely Prediction of Road Traffic Congestion Using Ontology

Abstract: In developing countries, traffic in a road network is a major issue. In this paper we investigate the tradeoff between speed versus accuracy of predicting the severity of road traffic congestion. The timely prediction of traffic congestion using semantic web technologies that will be helpful in various applications like better road guidance, vehicle navigation system. In the proposed work, ontology is created based on sensor and video data. By using rule inference of ontology on parallel processing of sensor and video data, our system gives the timely prediction of traffic congestion.

De-duplication of passports using Aadhaar

Abstract: Big data is an emerging technology that is becoming an essential part of national governance. Aadhaar is the unique identification scheme of India, handled by the Unique Identification Authority of India (UIDAI), which deals with big data. Every person above the age of 5 years has to register their demographic details (Name, Date of Birth, Address and Phone number) and biometric details (10 fingerprints and both iris) and then these details are used to verify the authenticity of the person when any services are required by him. Passport is a legal document that is carried by a person when he travels between countries, but in the case of the older passports with no biometric data, a person may have more than one legal passport with different demographic details. This paper does a case study on the existing de-duplication methods for passport enrolments and other such documents. In the case of newer passports, it takes 10 days to link with Aadhaar at the time of registration, hence the aim is to reduce the processing time of the linking and verification. String matching algorithms are used to compare the demographics, and techniques such as genetic programming and hashing are used for de-duplication. This case study also helps identify big and fast data platforms to identify such e-governance plans, by evaluating the accuracy and efficiency of existing algorithms. This system aims to predict the duplication of passports by linking Aadhaar and passport details, and to reduce the processing time of the Aadhaar database by using parallel algorithms.

Offline Navigation: GPS based Location Assisting System

Abstract: Objectives: We have developed an Offline Navigation Android1 application especially for the visually impaired people, the application also features a module through which the user, if lost track or has been abducted can reach back to the original location without the use of the internet. Methods/Statistical Analysis: We have used Google’s direction API2 for the route data, using this data the application guides the user with the help of Global Positioning System and Magnetic sensor. The main uniqueness of this application is, it works without the internet and consumes less battery charge. Findings: The developed application uses the data from the direction API (i.e., JSON format text) for navigating without displaying the map instead by reading out instructions, showing just direction and giving vibration feedback if deviating from the path. Thus the application differs from a typical navigation application. Application/Improvements: The developed application has a unique functionality for retracing a user’s path, and also consumes less space and computation compared to other navigation applications.

Vehicle Classification and Speed Estimation Using Combined Passive Infrared/Ultrasonic Sensors

Abstract: In this paper, a new sensing device that can simultaneously monitor traffic congestion and urban flash floods is presented. This sensing device is based on the combination of passive infrared sensors (PIRs) and ultrasonic rangefinder, and is used for real-time vehicle detection, classification, and speed estimation in the context of wireless sensor networks. This framework relies on dynamic Bayesian Networks to fuse heterogeneous data both spatially and temporally for vehicle detection. To estimate the speed of the incoming vehicles, we first use cross correlation and wavelet transform-based methods to estimate the time delay between the signals of different sensors. We then propose a calibration and self-correction model based on Bayesian Networks to make a joint inference by all sensors about the speed and the length of the detected vehicle. Furthermore, we use the measurements of the ultrasonic and the PIR sensors to perform vehicle classification. Validation data (using an experimental dual infrared and ultrasonic traffic sensor) show a 99% accuracy in vehicle detection, a mean error of 5 kph in vehicle speed estimation, a mean error of 0.7m in vehicle length estimation, and a high accuracy in vehicle classification. Finally, we discuss the computational performance of the algorithm, and show that this framework can be implemented on low-power computational devices within a wireless sensor network setting. Such decentralized processing greatly improves the energy consumption of the system and minimizes bandwidth usage.

Iot based school bus tracking and arrival time prediction

Abstract: Nowadays, parents are perturbed about school going children because of the increasing number of cases of missing students. On occasion, students need to wait a much longer time for arrival of their school bus. There exist some communication technologies that are used to ensure the safety of students. But these are incapable of providing efficient services to parents. This paper presents the development of a school bus monitoring system, capable of providing productive services through emerging technologies like Internet of Things (Iota). The proposed IoT based system tracks students in a school bus using a combination of RFID/GPS/GSM/GPRS technologies. In addition to the tracking, a prediction algorithm is implemented for computation of the arrival time of a school-bus. Through an Android application, parents can continuously monitor the bus route and forecast arrival time of the bus.

Hybrid Statistical and Machine Learning Methods for Road Traffic Prediction: A Review and Tutorial

Abstract: Mobility is one of the major dimensions of smart city design and development. Transportation analysis and prediction play important parts in mobility research and development. Recent years have seen many new types of transportation data emerging, such as social media and Global Positioning System (GPS) data. These data contains hidden knowledge, which can be used in many applications to improve city operations; road traffic prediction is one aspect of this. Researchers have traditionally used single traffic flow prediction methods, which work well only under specific conditions. Some work has emerged in recent years on combining these methods into various hybrid methods. However, this work is in its infancy, and further investigations are required. More importantly, these hybrid methods have mostly been developed on stand-alone, nondistributed platforms, limiting the data and problem sizes that can be addressed, as well as the accuracy that can be achieved. This chapter gives a review of traffic flow prediction and modeling methods and discusses the limitations of each method. A review of the various types of transportation traffic data sources is provided. Notable big data analysis tools, including the Apache Spark platform, are described. Finally, we describe a hybrid method for road traffic prediction and provide a tutorial on the process of hybrid traffic flow prediction. The hybrid method is based on the autoregressive integrated moving average (ARIMA) and support vector machine (SVM) methods.