Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
119 results
Search Results
Item A holistic approach to influence maximization(Springer International Publishing, 2017) Sumith, N.; Annappa, B.; Bhattacharya, S.A social network is an Internet-based collaboration platform that plays a vital role in information spread, opinion-forming, trend-setting, and keeps everyone connected. Moreover, the popularity of web and social networks has interesting applications including viral marketing, recommendation systems, poll analysis, etc. In these applications, user influence plays an important role. This chapter discusses how effectively social networks can be used for information propagation in the context of viral marketing. Picking the right group of users, hoping they will cause a chain effect of marketing, is the core of viral marketing applications. The strategy used to select the correct group of users is the influence maximization problem. This chapter proposes one of the viable solutions to influence maximization. The focus is to find those users in the social networks who would adopt and propagate information, thus resulting in an effective marketing strategy. The three main components that would help in the effective spread of information in the social networks are: the network structure, the user's influence on others, and the seeding algorithm. Amalgamation of these three aspects provides a holistic solution to influence maximization. © Springer International Publishing AG 2017. All rights reserved.Item Prediction of crime hot spots using spatiotemporal ordinary kriging(Springer Verlag service@springer.de, 2019) Deshmukh, S.S.; Annappa, B.Prediction can play a very important role in many types of domains, including the criminal justice system. Even a little information can be gained from proper police assignments, which can increase the efficiency of the crime patrolling system. Citizens can also be aware and alert for possible future criminal incidents. This was identified previously, but the proposed solutions use many complex features, which are difficult to collect, especially for developing and underdeveloped countries, and the maximum accuracy obtained to date using simple features is around 66%. Few of these countries have even started collecting such criminal records in digital format. Thus, there is a need to use simple and minimal required features for prediction and to improve prediction accuracy. In the proposed work, a spatiotemporal ordinary kriging model is used. This method uses not only minimal features such as location, time and crime type, but also their correlation to predict future crime locations, which helps to increase accuracy. Past crime hot spot locations are used to predict future possible crime locations. To address this, the Philadelphia dataset is used to extract features such as latitude, longitude, crime type and time of incident, and prediction can be given for every 0.36 square km per day. The city area is divided into grids of 600 × 600 m. According to the evaluation results, the average sensitivity and specificity obtained for these experiments is 90.52 and 88.63%, respectively. © Springer Nature Singapore Pte Ltd. 2019.Item Distributed Cloud Deep Learning Architecture for Complex Image Analysis and Run-time Prediction Tool(Springer Science and Business Media Deutschland GmbH, 2021) Kumar, S.; Thomas, E.; Horo, A.; Annappa, B.Hyperspectral imaging is a rare research tool and has been transformed into a commodity product found in a wide field. Currently, standard data processing methods that specialize in special hyperspectral accumulation structures are required. Also, with the advent of data collection and development in the field of sensory devices, it has rendered previous processing tools in vain. To manage this huge increase in the amount of data, a consistent cloud distribution method is required. Hyperspectral images (HSIs) have several spectral band channels that make the study very difficult. In this paper, an in-depth reading method of the novel with a modified autoencoder is proposed as a cloud-based use of HSI analysis, which provides a measure of lesser error rates and high accuracy of classification models. In line with this, a list of four tools has been proposed to calculate the actual number of workers, cores, and iterations required to achieve the desired accuracy for a specified amount of run-time. This will help cloud managers get a basic idea of computational needs and help them allocate resources more efficiently. The entire architecture was simulated on Spark servers and was verified experimentally by checking that the proposed architecture performs the function of efficient management and analysis of large HSI. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.Item Foundations of healthcare informatics(Elsevier, 2021) Annappa, B.; Manoj Kumar, M.V.; Thomas, L.Health informatics fundamentally deals with the acquisition (recording), processing, interpreting, and using of healthcare (patient) data by domain experts. Healthcare informatics generally refers to the management of data/information in healthcare rather than the application of computers in it-which is centered on patient care. The sheer amount of data and imperfection in decision making imply the usage of information systems (particularly process-aware information systems, called PAIS) in managing the healthcare process. Health informatics mainly offers tools for controlling the healthcare process and facilitating the acquisition of medical knowledge (recording). It offers a reliable and fast communication path among the people involved in the healthcare process. © 2021 Elsevier Inc. All rights reserved.Item Deep Learning for COVID-19(Springer Science and Business Media Deutschland GmbH, 2022) Bs, B.S.; Manoj Kumar, M.V.; Thomas, L.; Ajay Kumar, M.A.; Wu, D.; Annappa, B.; Hebbar, A.; Vishnu Srinivasa Murthy, Y.V.S.Ever since the outbreak in Wuhan, China, a variant of Coronavirus named “COVID 19” has taken human lives in millions all around the world. The detection of the infection is quite tedious since it takes 3–14 days for the symptoms to surface in patients. Early detection of the infection and prohibiting it would limit the spread to only to Local Transmission. Deep learning techniques can be used to gain insights on the early detection of infection on the medical image data such as Computed Tomography (CT images), Magnetic resonance Imaging (MRI images), and X-Ray images collected from the infected patients provided by the Medical institution or from the publicly available databases. The same techniques can be applied to do the analysis of infection rates and do predictions for the coming days. A wide range of open-source pre-trained models that are trained for general classification or segmentation is available for the proposed study. Using these models with the concept of transfer learning, obtained resultant models when applied to the medical image datasets would draw much more insights into the COVID-19 detection and prediction process. Innumerable works have been done by researchers all over the world on the publicly available COVID-19 datasets and were successful in deriving good results. Visualizing the results and presenting the summarized data of prediction in a cleaner, unambiguous way to the doctors would also facilitate the early detection and prevention of COVID-19 Infection. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.Item Clinical decision support system for early disease detection and management: Statistics-based early disease detection(IGI Global, 2021) Thomas, L.; M V, M.K.; Annappa, B.Medical error is an adverse event of a failure in healthcare management, causing unintended injuries. Proper clinical care can be provided by employing a suitable clinical decision support system (CDSS) for healthcare management. CDSS assists the clinicians in identifying the severity of disease at the time of admission and predicting its progression. In this chapter, CDSS was developed with the help of statistical techniques. Modified cascade neural network (ModCNN) was built upon the architecture of cascade-correlation neural network (CCNN). ModCNN first identifies the independent factors associated with disease and using that factor; it predicts its progression. A case progressing towards severity can be given better care, avoiding later stage complications. Performance of ModCNN was evaluated and compared with artificial neural network (ANN) and CCNN. ModCNN showed better accuracy than other statistical techniques. Thus, CDSS developed in this chapter is aimed at providing better treatment planning by reducing medical error. © 2021, IGI Global.Item A secure and scalable framework for group communication(2006) Annappa, B.; Rani, G.P.Critical networking issues in group communication involve security, scalability and dynamic membership changes. Security provides confidentiality, authenticity, and integrity of messages exchanged between group members. Tree Group Diffie Hellman is an efficient key agreement protocol for peer groups. But, it is not scalable beyond 100 members. On the other hand, large multicast groups don't support dynamic membership changes. In this Paper, we propose a new framework, which addresses the problems of scalability and dynamic membership change. © 2006 IEEE.Item Petri net based verification of a cooperative work flow model(2009) Annappa, B.; Jiju, P.; Chandrasekaran, K.; Shet, K.C.This paper exploits the theory of Petri nets to verify reachability and soundness of a cooperative workflow model. First, we outline a cooperative workflow model, which is a modified version of Bonita workflow model. Bonita is open source cooperative workflow management software which is an ongoing project from object web consortium. Then we describe the cooperative workflow model using a special kind of Petri net called Wf-net. Next we employ WF-net for verification of the model for reachability and soundness properties. The Petri net based verification shows that the model is reachable and sound. ©2009 IEEE.Item SystemTap tapsets for the real-time Linux kernel(2010) Kesarwani, N.; Patra, L.; Annappa, B.Latency is an essential factor for measuring effectiveness of realtime applications. An effective realtime system aims at guaranteeing a practical deadline for a task, rather than improving throughput of the system. A subset of these applications includes the ones, which deploy realtime operating systems (RTOS). Linux RTOS has varied applications, few of them being at business trading centre, submarines, missile launching systems, satellite navigation system, etc. Considering the criticality of these systems, its top most priority that these RTOS should be almost near to perfection as they form the core. Hence, these systems need to be tested thoroughly, before they are applied anywhere. SystemTap is one such scripting tool which extracts information from a running kernel, which is unlike the traditional method of using printks. We aim at testing the performance of given RTOS by writing SystemTap scripts for various scenarios(provided by RTOS development teams) that arose as a result of problems faced in the past. © 2010 IEEE.Item Meta-level constructs in content personalization of a web application(2010) Annappa, B.; Chandrasekaran, K.; Shet, K.C.In today's business environment, web applications become more and more complex but they still need to be flexible for changes, easy to maintain and the development life cycle need to be short. A reflective technique seems to be the best way to achieve flexibility of the web applications when adding the personalization features like recommendations, special offers, etc. Most of the algorithms help to achieve personalization; but, little attention has been paid to the design and modeling process of internet applications. Personalization will help to cope with increasing complexity of Business Enterprise level Applications. High-level, cleanly layered solutions open up promising possibilities to overcome these difficulties. This paper gives an insight into the content personalization of a web application using meta-level constructs. ©2010 IEEE.