Conference Papers
Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506
Browse
7 results
Search Results
Item Durability of Bricks Coated with Red mud Based Geopolymer Paste(Institute of Physics Publishing michael.roberts@iop.org, 2016) Singh, S.; Basavanagowda, S.N.; Aswath, M.U.; Ranganath, R.V.The present study is undertaken to assess the durability of concrete blocks coated with red mud - fly ash based geopolymer paste. Concrete blocks of size 200 x 200 x 100mm were coated with geopolymer paste synthesized by varying the percentages of red mud and fly ash. Uncoated concrete blocks were also tested for the durability for comparison. In thermal resistance test, the blocks were subjected to 600°C for an hour whereas in acid resistance test, they were kept in 5% sulphuric acid solution for 4 weeks. The specimens were thereafter studied for surface degradation, strength loss and weight loss. Pastes with red mud percentage greater than 50% developed lot of shrinkage cracks. The blocks coated with 30% and 50% red mud paste showed better durability than the other blocks. The use of blocks coated with red mud - fly ash geopolymer paste improves the aesthetics, eliminates the use of plaster and improves the durability of the structure. © Published under licence by IOP Publishing Ltd.Item Machine Learning Models with Optimization for Clothing Recommendation from Personal Wardrobe(Institute of Electrical and Electronics Engineers Inc., 2020) Jain, M.; Singh, S.; Chandrasekaran, K.; Rathnamma, M.V.; Ramana, V.In the present-day scenario, several clothing recommender systems have been developed for the online e-commerce industry. However, when it comes to recommending clothes that a person already possesses, i.e, from their personal wardrobe, there are very few systems that have been proposed to perform the task. In this paper, we tackle the latter issue, and perform experimental analysis of the various Machine Learning techniques that can be used for carrying out the task. Since the recommendations must be made from a user's personal wardrobe, the recommender system doesn't follow a traditional approach. This is explained in detail in the following sections. Further, the paper contains a complete description of the results obtained from the experiments conducted, and the best approach is specified, with appropriate justification for the same. © 2020 IEEE.Item Mitigating Masquerade using Nonce in Symmetric Key Distribution - Survey(Institute of Electrical and Electronics Engineers Inc., 2020) Pandiya, C.; Singh, S.; Chandavarkar, B.R.Key distribution deals with mechanisms for secure distribution of keys. Since symmetric key cryptography requires both parties(encryption and decryption) to use the same key, the security of key distribution techniques is pivotal to the secrecy of overall exchange. This process generally uses master keys and session keys for key distribution and can be further strengthened by making use of nonces. A nonce is a non-repeating value (number used once) which may or may not be random. Such a value can be incorporated in cryptographic algorithms so as to make guessing and predicting difficult for an adversary during the exchange of messages between two entities over the network. This can help in mitigating masquerading and replay attacks. A masquerade attack is a kind of active attack wherein one entity pretends to be a different entity. Some other kinds of active attacks such as replay attack and modification of messages can also be grouped under the umbrella of masquerade attack. Such attacks often take advantage of the predictable nature of certain steps during the exchange of messages between two entities over the network. In this paper, we explore the usage of nonces in various cryptographic and network security applications in symmetric key distribution environment so as to prevent active attacks like masquerade attacks. © 2020 IEEE.Item Trustworthiness of COVID-19 News and Guidelines(Springer, 2023) Singh, S.; Nagar, L.; Lal, A.; Chandavarkar, B.R.COVID-19 pandemic is a serious health concern issue over the past couple of years. It spreads mostly due to bio-contacts, which leads people to follow social distancing and stay away from social gatherings. It leads the people to bound themselves to stay with their family members at their home only, being at home, staying idle, or following work from home schedule by working online through the Internet over the electronic gadgets such as mobiles, laptops, desktops, etc. It leads the people to attach to online activities more for spending their time at their home, which enormously increases people interest in social media platforms such as Twitter, Facebook, etc. As it was a major pandemic period, it created panic and a fearful situation in society. It makes the people believe any news and guidelines spreading through social media platforms irrespective of checking their trustworthiness and truthiness of it. This pandemic period created a seriously bad impact on society’s emotional, physical, and mental health that is a great loss to a country even all over the world. Under this, many unwanted messages are spreading for one’s interest or a group to polarize their interest. In a panic situation, it is highly required of a solution that prevents the spread of these negative vibes to maintain the overall health of society. This chapter tries to implement an optimal solution using various kinds of layers and different optimization functions. It particularly gives better performance in the case of sequential data using machine learning (ML) and deep learning (DL) frameworks trained with the dataset for identifying the fake news and guidelines spread over on COVID-19. To train the model, a dataset was taken from the Twitter Application Programming Interface (API). Finally, the truthiness detection technique with social interaction is completed using Twitter dataset. The efficacy of the suggested method is demonstrated by the obtained results on a Twitter dataset. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.Item Linux-like Socket Statistics Utility for ns-3(Association for Computing Machinery, 2023) Rudra, A.R.; Somayaji, S.L.; Singh, S.; Mokashi, S.D.; Rakshit, A.; Khan, D.; Tahiliani, M.Collecting statistics in network experiments is crucial for understanding the behavior of the network protocols and identifying any anomalies or performance issues. Without accurate and comprehensive statistics, it is difficult to analyze network traffic, identify bottlenecks, and make informed decisions about network protocol improvements. One of the key features of ns-3 is its ability to collect detailed statistics about network behavior during simulations. It supports various modules to collect statistics, such as Flow Monitor to collect flow level statistics, trace sources to collect information about specific events that occur during simulation, packet captures (PCAP) that can be read and analyzed using various PCAP-compatible tools and ASCII traces for debugging and generating custom reports. Besides, ns-3 also provides a flexible and extensible framework for users to create their own custom statistics collection modules. Nevertheless, collecting and analyzing data from simulations using these tools can be a complex process and requires a good understanding of the ns-3 simulation framework and its internal data structures. This paper discusses the design and development of a Linux-like socket statistics (ss) utility for ns-3 which makes the task of gathering network statistics much simpler. The main objective of this work is to develop a user-friendly API that enables ns-3 users to easily generate socket statistics. We validate the proposed API by comparing the results obtained from the trace sources already present in ns-3, and observe a high degree of consistency between our API and the trace source results. In addition, we analyze the impact of the proposed API on ns-3 performance in terms of resource consumption. © 2023 ACM.Item Impact of Building Configurations on Fluid Flow in an Urban Street Canyon(Springer Science and Business Media Deutschland GmbH, 2024) Singh, S.; Singh, L.; Jitendra Pal, S.The problem of pollution dispersion in urban areas is significant in the densely populated cities. The topography and barriers in the form of buildings impact the atmospheric fluid flow. The resulting phenomena known as pollution traps cause an artificial dispersion in the buildings’ proximity, affecting the health of ordinary road commuters. The primary source of pollution on the street canyons is exhaust gases from the vehicle movements. However, the concern is associated with the poor dispersion of pollutants under normal wind conditions. The primary reason behind the poor dispersion is the buildings that act as obstacles to the atmospheric wind flow. Thereby it is essential to comprehend the behaviour of pollutants under given shape constraints and flow conditions to improve urban air quality. The present study investigates the wind flow in the proximity of a six-storey building for a medium street canyon configuration under the logarithm inlet velocity profile that acts as atmospheric boundary layer (ABL). Effect of important parameters such as the building height, the wind direction (0, 30, 45, 60, and 90°), and building configurations (straight road, both side building, and only upwind side building with downwind side building) are investigated to gain valuable insights into pollutant dispersion. The analysis of turbulence and velocity profile in the domain at nose level (1.5 m above ground level) leeward sidewalk and windward sidewalk shows turbulent intensity decreases at the nose (breathing) level with building height; however, it increases when the approach angle is 450 suggesting the formation of dominant pockets of pollutants. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.Item Diabetic Retinopathy Detection Using Novel Loss Function in Deep Learning(Springer Science and Business Media Deutschland GmbH, 2024) Singh, S.; Annappa, B.; Dodia, S.Globally, the number of diabetics has significantly increased in recent years. Several age groups are affected. Diabetic Retinopathy (DR) affects those with diabetes for a long time. DR is a side effect of diabetes that affects the retina’s blood vessels and is caused by high blood sugar levels. Therefore, early detection and treatment are preferred. Manual recognition concerns and a lack of technology support for ophthalmologists are the most complex problems. Nowadays, Deep Learning (DL) based approaches are used significantly for creating DR detection systems because of the ongoing development of Artificial Intelligence (AI) techniques. This paper uses the APTOS dataset of retina images to train four deep Convolution Neural Network (CNN) models using a novel loss function. The four DL models used are VGG16, Resnet50, DenseNet121, and DenseNet169 to explain their rich properties and improve the classification for different phases of DR. The experimental results of this study demonstrate that VGG16 produced the lowest accuracy of 73.26% on the APTOS dataset, while DenseNet169-based detection gives the most significant result of 96.68% accuracy among the four approaches. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.