Priti Chakurkar

Bio: Priti Chakurkar is an academic researcher from Massachusetts Institute of Technology. The author has contributed to research in topics: The Internet & Perspective (graphical). The author has an hindex of 2, co-authored 3 publications receiving 5 citations. Previous affiliations of Priti Chakurkar include Maharashtra Institute of Technology.

An Internet of Things (IOT) based monitoring system for efficient milk distribution

Abstract: Milk distribution and safety is of high concern as it involves the health of 90% of our society. Our project, milk distribution monitoring system targets the cold chain maintenance and milk spoilage avoidance. The system is based on Internet of Things and data mining. Traditionally milk is supplied in cans with minimum monitoring which may result in milk getting spoiled before its use specially during transportation at any point of time which causes vendors to know about milk spoilage only after the milk has been spoiled completely. To overcome these problems first data mining technique is employed to discover the routing plans so as to generate case-based routing plans for the drivers. Then the existing sensor based system will measure the pH value of milk and determine its quality. The system will direct to nearest milk booth with the highest proximity by using routing technique where data center serves as a cloud server to calculate the costs of a finding the nearest milk booth request, and these costs will be frequently updated by considering the location of van and the total number of milk booth in each areas whose data is accessible any time in the network. This routing algorithm will be used to offer a solution of finding an available milk booth if the PH value deviates from 6.7. This is implemented by a system prototype with wireless access in an open-source physical computing platform based on Ardiuno and using a smart phone that provides the communication and user interface for both the control system and the vehicles to verify the feasibility of the system. It will also give an alert SMS to vehicle driver so that collection of milk can be faster without more spoilage. This way it will maintain good quality and cost effective distribution of milk.

Music Plagiarism Detection using Audio Fingerprinting and Segment Matching

Abstract: With the recent growth of media platforms such as YouTube, Spotify, etc. These Platforms make content easily accessible but at the same time causes many problems like plagiarized content. Especially with audio content we can observe multiple types of plagiarism like unauthorized use of music for making remix music. To deal with this problem we use audio fingerprinting. It is the process of presenting an audio signal in a closed-packed way by extracting relevant characteristics of the audio signal. This in itself can be used to check the song, but it won't give an accurate result if the plagiarized song is copied from multiple different songs. To solve this particular problem, we use segment matching.

An Efficient Way to Manage Constrained Devices in Internet of Things

Abstract: Internet of thing is new communication system where globally identifiable real world objects are exchanging information with each other over an Internet infrastructure. The major objective of IOT is development of smart environments and self-aware things applications like smart transport, products, cities, buildings, rural areas, energy, health, living etc.As the Internet of Things (IoT) evolves, applications rely on devices without much human intervention. In order to well maintain these sensor devices, it is required to remotely monitor and control devices without consuming significant resources. Managing these remote devices effectively can lead to cost savings and operational efficiency, and designers must create solutions that allow customers to monitor and make changes on the fly instead of manually sending technicians to make changes in the field.This Paper focused on different aspects of Device Management and survey of different protocols used for Device Management in Internet of Things.This paper proposes Device Management life cycle in Internet of Things and provide overview of Device Management user interface.

Massive Open Online Courses (MOOCs): A Perspective from the Engineering Education

Abstract: The COVID Pandemic was a big hit not only for the education sector but also finance sector, industrial sector etc. Due to this adverse situation the physical classes were abruptly stopped and there was a chaos. During this arduous situation universities switched to E-learning. Students started taking MOOC courses. Massive Open Online Courses (MOOC) are online courses offered by diverse educators with the goal of enabling everyone to access content at reasonable prices from any location. This paper presents how Universities can influence students to enroll in courses. For this study purpose students at a University in Pune provided the data in the form of Feedback and Suggestions. Students can enroll in a Course for one of two reasons: to learn new things and develop their abilities, or to gain University Credits. The results showed that many students were completing MOOC courses for credit than for personal growth, a strong correlation between enrolling in a MOOC course for university credit and successful completion is observed. A strong need for University teachers to offer their expertise on these platforms to ensure global knowledge sharing was also observed. Keywords— MOOC; Self Learning; MOOC Platforms; Performance.

A Fundamental Study on Suicides and Rainfall Datasets Using basic Machine Learning Algorithms

Abstract: Suicides in India have been registering at an alarming rate. The rainfall rate in India is unpredictable due to changes in environment. Farmers faces huge losses due to this unpredictable rains. This leads into loss of lives and results the farmers into suicide state. Relative analysis of rainfall and suicide rate will support farmers to avoid losses due to rainfall and further suicides can be avoided. Prediction of rainfall and suicide rate is achieved in India using machine learning algorithms such as Linear regression, Logistic regression, Support Vector Machine and Random Forest. Relative analysis provides better prediction results which greatly supports the farmers and avoid losses.

A Lightweight Framework for Efficient M2M Device Management in oneM2M Architecture

Abstract: Recent years have witnessed an explosion in the number and types of physical devices connected to the Internet. This exponential growth in the volume of objects poses challenges in terms of managing the connected M2M devices. A unified approach for efficient management of the M2M devices while preserving scalability is necessary. This paper proposes an M2M device management framework that can be deployed in a cloud system, M2M gateway or even inside a mobile application. CoRE Link Format is used for lightweight description of smart M2M devices. The capabilities of CoRE Link are extended to describe legacy M2M devices as a part of Internet of Things ecosystem. Open Mobile Alliance Lightweight M2M (OMA LwM2M) Technical Specifications are used in the framework to provide M2M service enablement for end users. Self-management of the M2M device configurations is outlined. The capabilities of the framework are exposed using RESTful web services. oneM2M architecture for device management is described which integrates the proposed framework. Its software implementation is examined to be ultra-lightweight. Utilization of CoRE Link settles the heterogeneity of the managed devices and promotes interoperability. Finally the paper summarizes the contributions and concludes with future directions.

An Internet of Things (IOT) based Smart Parking Routing System for Smart Cities

Abstract: Recently, the number of cars on the road has been growing due to the increase in car manufacturing in parallel with customer services provided to help the new driver to buy cars at affordable prices. On the other hand, we find that the infrastructure of big cities cannot support this number of cars and with the disorganization of parking places in the city this problem will lead us to have serious problem in the city which involves the increase of drivers requests to find the nearest parking places to avoid traffic congestion in those areas. In parallel today we talk about the concept of smart cities and how can we use the evolution of the Internet of Things (IoT) to improve the quality of the smart city. Several efforts have been made on the Internet of Things to improve the reliability and the productivity of public infrastructure. Many problems have been handled and controlled by the IoT such as vehicle traffic congestion, road safety and the inefficient use of car parking spaces. This work introduces a novel technique based on a distributed cloud architecture of IoT to manage the parking systems combined with a distributed swarm intelligence technique using the Ant System algorithm to improve the process of finding the nearest car parking in the minimum time based on the state of traffic on this road. This prototype will help drivers to find the nearest car parking and improve the exploitation of the available car parking in the city.

Need for Predictive Data Analytics in Cold Chain Management

Abstract: Predictive analytics is an advanced technique that uses historical data to predict future outcomes with the help of machine learning algorithms. Cold chain logistics companies greatly depend on accuracy, timeliness, and efficiency to meet the requirements. A smart cold chain management system includes the proper monitoring and controlling of parameters such as temperature, vibrations, light, and humidity of the perishable food during the whole cold chain. In this work, predictive data analytics is proposed to make real-time predictions about time–temperature relationship considering various internal and external factors to avoid temperature abuse during transportation and thus predict the quality of food.

MetaAID 2.0: An Extensible Framework for Developing Metaverse Applications via Human-controllable Pre-trained Models

Abstract: Pre-trained models (PM) have achieved promising results in content generation. However, the space for human creativity and imagination is endless, and it is still unclear whether the existing models can meet the needs. Model-generated content faces uncontrollable responsibility and potential unethical problems. This paper presents the MetaAID 2.0 framework, dedicated to human-controllable PM information flow. Through the PM information flow, humans can autonomously control their creativity. Through the Universal Resource Identifier extension (URI-extension), the responsibility of the model outputs can be controlled. Our framework includes modules for handling multimodal data and supporting transformation and generation. The URI-extension consists of URI, detailed description, and URI embeddings, and supports fuzzy retrieval of model outputs. Based on this framework, we conduct experiments on PM information flow and URI embeddings, and the results demonstrate the good performance of our system.