College of Engineering, Pune

About: College of Engineering, Pune is a based out in . It is known for research contribution in the topics: Computer science & Sliding mode control. The organization has 4264 authors who have published 3492 publications receiving 19371 citations. The organization is also known as: COEP.

Fabric Defect Detection Using Wavelet Filter

Abstract: Fabric defect detection is now an active area of research for identifying and res olving problems of textile industry, to enhance the performance and also to maintain the quality of fabric. The traditional system of visual inspection by human beings is extremely time consuming, high on costs as well as not reliable since it is highly error prone. Defect detection a cl assification are the major challenges in defect inspection. Hence in order to overcome these drawbacks, faster and cost effective automatic defect detection is very necessary. Considering these necessities, this paper proposes wavelet filter method. It also explains in detail its various techniques of getting final output like preprocessing, decomposition, thresholding, and noise eliminating.

Machine-to-Machine Communication for Device Identification and Classification in Secure Telerobotics Surgery

Abstract: The capacity of machine objects to communicate autonomously is seen as the future of the Internet of Things (IoT), but machine-to-machine communication (M2M) is also gaining traction. In everyday life, security, transportation, industry, and healthcare all employ this paradigm. Smart devices have the ability to detect, handle, store, and analyze data, resulting in major network issues such as security and reliability. There are numerous vulnerabilities linked with IoT devices, according to security experts. Prior to performing any activities, it is necessary to identify and classify the device. Device identification and classification in M2M for secure telerobotic surgery are presented in this study. Telerobotics is an important aspect of the telemedicine industry. The major purpose is to provide remote medical care, which eliminates the requirement for both doctors and patients to be in the same location. This paper aims to propose a security and energy-efficient protocol for telerobotic surgeries, which is the primary concern at present. For secure telerobotic surgery, the author presents an Efficient Device type Detection and Classification (EDDC) protocol for device identification and classification in M2M communication. The periodic trust score is calculated using three factors from each sensor node. It demonstrates that the EDDC protocol is more effective and secure in detecting and categorizing rogue devices.

Understanding the cascade of GCM and downscaling uncertainties in hydro-climatic projections over India

Abstract: India is a major agrarian country strongly impacted by spatio-temporal variations in the Indian monsoon. The impact assessment is usually accomplished by implementing projections from general circulation models (GCMs). Unfortunately, these projections cannot capture the dynamicity of the monsoon and require either statistical (SD) or dynamical (DD) downscaling of the GCM projections to a finer resolution. Both downscaling techniques can capture the spatio-temporal variation in climatic variables but are marred by uncertainty in the projections resulting from the choice of the GCM and downscaling method, which affects climate change adaptations. Here, we assessed uncertainties in the projections of hydro-climatic variables over India by considering multiple downscaling techniques, multiple GCMs, and their combined effects (referred as the total uncertainty). Multiple hydrological variables were simulated by implementing the variable infiltration capacity model that considered outputs from DD (derived by the coordinated regional climate downscaling experiment, CORDEX) and SD forced with multiple GCM simulations. Our results showed that the SD projections captured the observed spatio-temporal variability of hydro-climatic variables more efficiently than the DD projections. Importantly, contribution from the downscaled projections to the total uncertainty was significantly smaller compared to the inter-GCM uncertainty. We believe uncertainty analysis is an important component of good scientific practice; however, several researchers appear to be rather reluctant to embrace the concept of uncertainty in making projections, predictions, and forecasting. It remains a common practice to show climate change exercises to decision-makers/stakeholders, without uncertainty bounds. Here, a successful attempt was made to identify the key sources of uncertainty and adequately bracket the uncertainty, indicating a requirement of the code of practice to provide formal guidance, particularly for climate-change impact assessments. This consequently emphasized the importance of follow-up research to understand the inter-GCM uncertainty, which has a significant impact on sustainable agriculture and water resources management in India.

Ontology for Detection of Web Attacks

Abstract: Intrusion Detection System (IDS) must reliably detect malicious activity. The expansion of web application also exponentially increases cyber threats. Current survey shows that application layer is more vulnerable to web attacks. There are more than 75% of attacks are deployed at application layer and out of that 90% are vulnerable to attacks. In this paper, we address issues of existing IDS i.e. low false positive rate, low false negative rate and data overload. We discuss about use of semantic web in the Intrusion Detection Systems. This article presents a proposition of using Semantic Web and Ontology concepts to define an approach to analyze Security logs with the goal to identify possible security issues. It extracts semantic relations between computer attacks and intrusions in an Intrusion Detection System. Ontology provides to enable, reuse of domain knowledge and it is also easier to understand and update legacy data.