An IoT based smart traffic control system
An automated Pi based traffic control system using webcams and sensors that help in reducing traffic density in busy traffic junctions. The design of this traffic infrastructure can help to avoid traffic congestions. This paper describes a system where webcams are integrated with the Raspberry Pi to operate the lanes of traffic junction based on the count of traffic and RFID Sensors for emergency vehicles to be prioritized for the safety of passengers. As a result, the improvement in the traffic system can be exponentially improved, which can lead to progressive in the overall traffic system.
Published by: Bevara Atchyuth, Irugatla Sarat Kumar, Swarna Datla, Ganta Ajay Rahul
Author: Bevara Atchyuth
Paper ID: V5I2-1294
Paper Status: published
Published: March 18, 2019
Semantic text analysis using machine learning
As the amount of information on the World Wide Web grows, it becomes increasingly burdensome to and just what we want. While general-purpose search engines such as Ask.com and Bing high coverage, they often provide only low precision compared to others, even for detailed and relative queries. When we know that we want information about a certain type, or on a certain topic, a domain-specific search engine can be a powerful tool. Like www.campsearch.com allows complex queries over summer camps by age-group, size, location, and cost. Domain-specific search engines are becoming increasingly popular because they increase accuracy not possible with general, Web-wide search engines. Unfortunately, they are also burdensome and time-consuming to maintain. In this paper, we use machine learning techniques to greatly automate the creation and maintenance of domain-specific search. It describes new research in semi-supervised learning, text classification, and information extraction. We have built a demonstration system using these technics like Web Scrapping, Fuzzy C-Means and Hierarchy Clustering for a search engine which gives accurate results which is a more advantage when compared to other Search engines. Searching with a traditional, general purpose search engine would be extremely tedious or impossible to perform search operations. For this basis, domain-specific search engines are becoming popular. This article mainly concentrated on Project an effort to automate many aspects of creating and maintaining domain-specific search engines by using machine learning techniques. These techniques permit search engines to be created quickly with less effort and are suited for re-use across many domains.
Published by: Bhargavi Joga, Sarath Sattiraju, Venkatesh Kandula, Narayana Murthy Kallempudi, Mandava Kranthi Kiran
Author: Bhargavi Joga
Paper ID: V5I2-1312
Paper Status: published
Published: March 18, 2019
Review – IoT used for health monitoring
The day-by-day development of the Internet of Things causes a revolution in modern technology, which makes our life easier and automated. Due to a busy schedule and irregular lifestyle, health hazard is not an age-dependent factor in the recent era. Under these circumstances, Internet of Things has provided a much easier solution for remote real-time health monitoring of patients from the hospital as well as home. One such healthcare application is to monitor the patient health status Internet of Things makes medical equipment more efficient by allowing real-time monitoring of patient health, in which sensor acquire data of patient's and reduces the human error. The significant challenges in the implementation of the Internet of Things for healthcare applications are monitoring all patient’s from various places. Thus Internet of Things in the medical field brings out the solution for effective patient monitoring at a reduced cost. The purposed work will explain the concept of monitoring of patients health using a microcontroller and different sensors and the reports are accessible through the mobile application.
Published by: Devyani Mashale, Dr. Rupali J. Shelke
Author: Devyani Mashale
Paper ID: V5I2-1327
Paper Status: published
Published: March 18, 2019
An arduino based intelligent shopping system-mechatronics approach
Internet of Things (IoT): Let devices and physical objects connect each other by their sensing, communicating and processing capabilities. This paper develops an intelligent shopping using the shopping cart system to provide IoT service in a hypermarket. The major instances are difficulty in finding the specified products and standing in a big queue in the billing section. This really takes a long time and creates customer un-satisfaction to the owner. Each cart is provided with an RFID based smart shopping system with an IoT enabled technology. It proposes the quick pathfinding schemes which help the customer to find the location of the product. The main facility that the proposed model provides the customer only needs to carry an RFID smart card. It also provides a centralized and automated billing system using RFID technology. The whole information will be sent to IoT cloud server through a GSM module. If the product is purchased the number of product availability is low. The IoT cloud server alerts the seller through SMS. The system facilitates faster billing and standing in a queue reduces the average time required for shopping.
Published by: Dr. J. Krishnakumar, A. Aruljothi, M. Pavadharani, A. Saraswathi
Author: Dr. J. Krishnakumar
Paper ID: V5I2-1334
Paper Status: published
Published: March 18, 2019
Digital image steganography using LSB and pseudo-random technique
This paper purposed an image based steganography that uses the Least Significant Bits (LSB) techniques and pseudo-random encoding technique on images to enhance the security of the communication. In the L-SB approach, the fundamental thought is to replace the Least Significant Bits (LSB) of the cover picture with the Bits of the messages to be covered up without pulverizing the property of the cover image significantly. The LSB-based method is the most difficult one as it is hard to separate between the cover-object and stego-object if few LSB bits of the cover are replaced. In Pseudo-Random technique, an arbitrary key is utilized as a seed for the Pseudo-Random Number Generator is required in the inserting procedure. Both the systems utilized a stego-key while installing messages inside the cover picture. By utilizing the key, the chance of getting attacked by the attacker is reduced.
Published by: Naveen Kalia, Manit Kapoor, Dr. Naveen Dhillon
Author: Naveen Kalia
Paper ID: V5I2-1351
Paper Status: published
Published: March 18, 2019
Bio-medical texture characterization using DOST
We present a new efficient approach for detecting tumor of cancer in the human body based on a recently published discrete orthonormal space-frequency transform known as the DOST. We develop a frequency-domain implementation of the DOST in two dimensions for the case of dyadic frequency sampling. This manual detection may have chances of false detection. So a computerized method for cancer detection is needed. A feature selection algorithm based on statistical two-sample t-test method is used for the selection of significant coefficients from the high dimensional DOST(Discrete Orthonormal Stockwell Transform) coefficients. The selected significant coefficients are used as features for the classification of human body tumor as benign or malignant.
Published by: Sravani Palika, K. S. N. Sarat Chandra, K. Lavanya, S. A. Bhavani
Author: Sravani Palika
Paper ID: V5I2-1350
Paper Status: published
Published: March 18, 2019
