Android Malware Detection through Online Learning
Android malware constantly evolves so as to evade detection. The entire malware population to be non-stationary. Contrary to this fact, most of the prior works on machine learning based android malware detection have assumed that the distribution of the observed malware characteristics (i.e., features) does not change over time. The problem of malware population drift and propose a novel online learning based framework to detect malware, named CASANDRA (Context-aware, Adaptive and Scalable Android malware detector). In order to perform accurate detection, a novel graph kernel that facilitates capturing apps security-sensitive behaviors along with their context information from dependence graphs is proposed. Besides being accurate and scalable, CASANDRA has specific advantages: first, being adaptive to the evolution in malware features over time; second, explaining the significant features that led to an apps classification as being malicious or benign.
Published by: Vinu Thadevus Williams, Dr. K. S. Angel Viji
Author: Vinu Thadevus Williams
Paper ID: V3I6-1455
Paper Status: published
Published: December 23, 2017
Enhancement of Performance of ASP for Organics Removal using Return Sludge as Flocculent in Primary Settling Tank
Renewable energy production and environmental crisis are the recent issues prevailing in the society. Economic growth of the country depends largely on the availability of the renewable energy. Wastewater treatment systems are huge consumers of electricity for accomplishing the task of a safe and healthy environment. Wastewater systems account for about 1- 5 % of total electricity consumption in a country. It is stated that energy consumption contribution per person is about average values of 12-15 kWh/ person-year considering 80% of water @ 180 L per capita per day is contributing to sewage reaching to STP for treatment and BOD of 50g/d. Hence, there is an urgent demand for reducing this consumption for an overall development of our country. Among the aerobic processes, activated sludge process (ASP) represents the most widespread technology for wastewater treatment in India. In ASP major part of the energy consumption (about 60%) occurs in the aeration tank to provide a proper environment for the treatment of wastewater. In wastewater treatment plants, it is very difficult to make power savings in general because the process is continuous, and, on the other hand the treatment technology is based on processes (physical, chemical and especially biological) that cannot be switched off or disconnected from the main supplies. The other option is only to modify the processes in order to save energy. A case study for performance analysis of conventional Activated Sludge Process with use of excess sludge as a flocculent in the Primary Settling Tank was carried out to enhance the operational efficiency of secondary treatment unit and improve the settling characteristics in the Primary settling tank. The performance was assessed by setting up a laboratory scale ASP setup and commissioning the reactor at suitable HRT of 6h scaling down it from 12h. The study aims at improving the settling property of primary settling tank thereby reducing the organic load in aeration tank and reducing the energy consumption of the treatment plant. Many encouraging results were observed which supported the concept that efficiency of primary settling tank can be increased by the addition of the suitable quantity of activated sludge. It was observed that compared to the conventional control (all recycled biomass going to AT), the improvement inorganics removal in our modified system was 38% at 30+40% recycle combination. This can result in overall reduction of the maintenance cost of STP plants in our country.
Published by: Anjali, A. B Gupta
Author: Anjali
Paper ID: V3I6-1228
Paper Status: published
Published: December 23, 2017
Seawater Purification Using Earth Source Energy
Lack of fresh water is a general concern and will increasingly become a threat to societies in the future. The water problem is particularly acute during the summer season in the Mediterranean region when the number of people staying there increases considerably. The number of tourists is expected to double by 2025. Drinking water scarcity is likely to increase because of a changing climate. This represents a massive economic, social and environmental threat to semi-arid regions such as the Mediterranean. An important technology to tackle this problem is desalination making fresh drinking water from saline seawater. Most of the current methods, however, are neither cost-efficient and environmentally friendly. Therefore, there is an urgent need to develop a technology that would fulfill both criteria.
Published by: V. Dharani Devi, V. Arun Rajha, K. Jamuna, M. Nandhini
Author: V. Dharani Devi
Paper ID: V3I6-1250
Paper Status: published
Published: December 23, 2017
Proposed Theory for I-Bicycle
— “I-Bicycle” refers to a bicycle with hub-less rear wheel. The main idea behind this project is to develop a hub-less or spoke-less wheel. This bicycle overcomes some drawbacks of the bicycle being used nowadays such as heavy design due to presence of spokes, power consumption issues, space issues. The advantages associated with this bicycle are light weight due to absence of hubs or spokes, additional space in the wheel due to absence of spokes, aesthetic look to the design and lowered center of gravity. The bicycle runs with a “rack and pinion system” connected to the rear-wheel. The paddle gear is connected to the pinion whereas the pinion is meshed with the internal teeth of the rear-wheel rim. This bicycle can be used to overcome the above mentioned issues and it's a great innovation in the design of the conventional bicycle which gives the operator a fresh feel while using it and it's awesome and very aesthetic when it comes to the appearance of the bicycle.
Published by: Pijush Ghosh, Ashwin Kharwa, Parag Marde, Pratik Raut
Author: Pijush Ghosh
Paper ID: V3I6-1238
Paper Status: published
Published: December 23, 2017
Using Low Level Features -Fingerprint Liveness Detection from Single Image
Fingerprint-based authentication systems have developed rapidly in the recent years. However, current fingerprint-based biometric systems are vulnerable to spoofing attacks. Moreover, the single feature-based static approach does not perform equally over different fingerprint sensors and spoofing materials. In this paper, propose a static software approach. Propose to combine low-level gradient features from speeded-up robust features, pyramid extension of the histograms of oriented gradient and texture features from Gabor wavelet using dynamic score level integration. Extract these features from a single fingerprint image to overcome the issues faced in dynamic software approaches, which require user cooperation and longer computational time.
Published by: Vinu Thadevus Williams, Dr. K. S. Angel Viji
Author: Vinu Thadevus Williams
Paper ID: V3I6-1443
Paper Status: published
Published: December 22, 2017
Health Care Application System using IoT
In-home health care services based on the Internet-of-Things (IoT) have great business potential. In this paper, an intelligent home-based platform, the Health-IoT, is proposed and implemented. In particular, the platform involves an open-platform-based intelligent medicine box (Med-Box) with enhanced connectivity and interchangeability for the integration of devices and services. Flexible and wearable bio-medical sensor like heart rate and temperature, ECG sensor etc are incorporated in this. The proposed platform seamlessly fuses IoT devices with in-home healthcare. Services for an improved user experience and service efficiency. The feasibility of the implemented Health-IoT platform has been proven in field trials. Medicine box and the wearable sensors are connected to Server via an Android-based smartphone through Bluetooth, which has an interface for the patient to see his medicine conception and health status the remotely connected web page is operated from hospital which has provision for giving the prescription and view all patients consultation details and test details consulted doctors etc. The Medicine conception details and alert are given to mobile app via this website with is connected through the internet, If the patient forgot to take medicine or take a wrong one which can be alerted through the app. And here discussed how to implement in a real-world system. Analyze system capacity by testing devices and modules.
Published by: Vinu Thadevus Williams, Dr. K. S. Angel Viji
Author: Vinu Thadevus Williams
Paper ID: V3I6-1442
Paper Status: published
Published: December 22, 2017
