@sdmcet.ac.in
Professor and Head, Department of Computer Science and Engineering
SDM College of Engineering and Technology
BE(CSE), ME(CSE) and PhD(Engineering)
Distributed System, Smart Space, Intelligent System, Ubiquitous Computing
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
S. G. Gollagi, M. M. Math, and U. P. Kulkarni
Springer Science and Business Media LLC
Ranganath Yadawad and Umakant P. Kulkarni
Springer Science and Business Media LLC
Harish H. Kenchannavar, Prasad M. Pujar, Raviraj M. Kulkarni, and Umakant P. Kulkarni
Institute of Electrical and Electronics Engineers (IEEE)
S. G. Gollagi, M. M. Math, and U. P. Kulkarni
Springer Science and Business Media LLC
As the data or information gets increased in various applications, it is very much essential to make the retrieval and modeling easier and simple. Number of modeling aspects already exists for this crisis. Yet, context awareness modeling plays a significant role in this. However, there requires some advancement in modeling system with the incorporation of advanced technologies. Hence, this survey intends to formulate a review on the context-aware modeling in two aspects: context data retrieval and context data modeling. Here, the literature analyses on diverse techniques associated with context awareness modeling. It reviews 60 research papers and states the significant analysis. Initially, the analysis depicts various applications that are contributed in different papers. Subsequently, the analysis also focuses on various features such as web application, time series model, intelligence models and performance measure. Moreover, this survey gives the detailed study regarding the chronological review and performance achievements in each contribution. Finally, it extends the various research issues, mainly the adoption of Evolutionary algorithms, which can be useful for the researchers to accomplish further research on context-aware system.
Sharwari Solapure, Harish Kenchannavar, and Umakant P. Kulkarni
IEEE
Recently, Low Power and Lossy Networks (LLNs) has become a subject of interest for different real time applications. These networks are often optimized to save energy and better utilization of limited resources. RPL (Routing Protocol for Low Power and Lossy Networks) protocol allows efficient routing in this type of network. The objective function (OF) of RPL is calculating the route path as per the routing metrics used by OF. The new RPL-OFs are designed as per the IoT application need in the earlier research. This proposed work is the extension of previous research work. The designed RPL-OFs are used to analyze the Quality of Service (QoS) performance of the IoT system by using performance evaluation of the parameters: Packet Delivery Ratio, Latency Delay, Energy consumption and network lifetime. The analysis result will definitely help the researchers to contribute more towards RPL protocol research.
Rashmi Salavi, M. M. Math, and U. P. Kulkarni
Wiley
Umesh M. Kulkarni, Harish H. Kenchannavar, and Umakant P. Kulkarni
Informa UK Limited
ABSTRACT Wireless sensor networks (WSNs) are applicable in most of the domains of engineering. Presently, Heterogeneous WSN (HWSN) is gaining more importance than homogeneous WSN. One of the major challenges of a HWSN is efficient deployment which can provide good coverage. The deployment strategy in WSN can be static or dynamic. It is found that there is a need of dynamic deployment that intelligently places the sensor nodes in the deployment area. This intelligence is possible by one of the artificial neural networks concept like self-organizing map (SOM). This work presents a dynamic decision-making algorithm (DDMA) for deployment of sensors using SOM such that the nodes will adjust their locations to uncovered area by failed sensor node in the changing sensing environment. The DDMA is compared with LEA2C and ECBS which are variants of LEACH. The results show that proposed DDMA performs better than the existing algorithm in-terms of decreased node depletion rate by 35% and 25% more coverage. The experimental analysis also show that SOM-based DDMA performs better than the non-SOM-based DDMA deployment for HWSN in terms of 5% better energy conservation, 30% better network lifetime, 75% more coverage in the deployment area and 90% reduced node depletion rate. This work presents a dynamic decision-making algorithm (DDMA) for deployment of sensors using self-organising map (SOM) such that the nodes will adjust their locations to uncovered area by failed sensor node in the changing sensing environment. The DDMA is compared with variants of LEACH with existing LEA2C and ECBS. The results show that proposed DDMA performs better than the existing algorithm in-terms of decreased node depletion rate by 35% and 25% more coverage. The experimental analysis is performed between SOM-based and non-SOM-based DDMA algorithms. Results show that SOM-based DDMA performs better than the non-SOM-based DDMA deployment for heterogeneous WSN in terms of 5% better energy conservation, 30% better network lifetime, 75% more coverage in the deployment area and 90% reduced node depletion rate. GRAPHICAL ABSTRACT
Deepa Saibannavar, Mallikarjun M. Math, and Umakant Kulkarni
Springer International Publishing
Harish H. Kenchannavar, Shrivatsa D. Perur, U. P. Kulkarni, and Rajeshwari Hegde
Springer Singapore
Ranganath Yadawad and Umakant P Kulkarni
IEEE
The rapid progress in the field of IoT has been enriching the idea of Ubiquitous Computing. The Internet of Things(IoT) ecosystem involves HCI i.e. it involves users and technologies that helps in satisfying users' needs in terms of smart environment. For such environments it is necessary to structure all the data and define relationships among all the data that makes smart context. This paper proposes a concept, which is a step towards standardizing self-aware hierarchical structure for the data repository, that enables any IoT device to be smart and hence facilitates context aware communication among IoT devices.
Prasad M. Pujar, Harish H. Kenchannavar, Raviraj M. Kulkarni, and Umakant P. Kulkarni
Springer Science and Business Media LLC
AbstractIn this paper, an attempt has been made to develop a statistical model based on Internet of Things (IoT) for water quality analysis of river Krishna using different water quality parameters such as pH, conductivity, dissolved oxygen, temperature, biochemical oxygen demand, total dissolved solids and conductivity. These parameters are very important to assess the water quality of the river. The water quality data were collected from six stations of river Krishna in the state of Karnataka. River Krishna is the fourth largest river in India with approximately 1400 km of length and flows from its origin toward Bay of Bengal. In our study, we have considered only stretch of river Krishna flowing in state of Karnataka, i.e., length of about 483 km. In recent years, the mineral-rich river basin is subjected to rapid industrialization, thus polluting the river basin. The river water is bound to get polluted from various pollutants such as the urban waste water, agricultural waste and industrial waste, thus making it unusable for anthropogenic activities. The traditional manual technique that is under use is a very slow process. It requires staff to collect the water samples from the site and take them to the laboratory and then perform the analysis on various water parameters which is costly and time-consuming process. The timely information about water quality is thus unavailable to the people in the river basin area. This creates a perfect opportunity for swift real-time water quality check through analysis of water samples collected from the river Krishna. IoT is one of the ways with which real-time monitoring of water quality of river Krishna can be done in quick time. In this paper, we have emphasized on IoT-based water quality monitoring by applying the statistical analysis for the data collected from the river Krishna. One-way analysis of variance (ANOVA) and two-way ANOVA were applied for the data collected, and found that one-way ANOVA was more effective in carrying out water quality analysis. The hypotheses that are drawn using ANOVA were used for water quality analysis. Further, these analyses can be used to train the IoT system so that it can take the decision whenever there is abnormal change in the reading of any of the water quality parameters.
G.M. Shivanagowda, R.H. Goudar, and Umakanth P. Kulkarni
Inderscience Publishers
Bhagyashri Abhay Kelkar, Sunil F. Rodd, and Umakant P. Kulkarni
Elsevier BV
Water Technology is a new approach for assessing water quality. Water technology is the method by which the water quality can be improved so as to accept the water for a specific use. In this paper, an IoT based water quality assessment has been carried out. The IoT system consists of electronic devices and associated sensors to capture water quality. Experimental samples for water quality check were chosen from, river Malaprabha. The water samples are collected from a water quality monitoring station near Khanapur town, Belagavi district, in the state of Karnataka, India. The water quality parameters assessed here are temperature, pH, Dissolved Oxygen (DO), Total Dissolved Solids (TDS), Biological Oxygen Demand (BOD), Conductivity and Nitrate (NO3). The proposed IoT system collects the real-time water quality data at every regular time interval. The need for real-time assessment is because, in recent years the water is getting polluted at an alarming level, due to urbanization and industrialization, that results in pollutions like an Urban waste, industrial waste, and agricultural waste, etc... disposed into water. Thus making, the use of water even harder for day-to-day anthropogenic activities. The IoT system developed can be used to monitor and assess the water quality parameters.
Siddalingeshwar Patil and Umakant Kulkarni
IEEE
Machine Learning is one of the finest fields of Computer Science world which has given the innumerable and invaluable solutions to the mankind to solve its complex problems. Decision Tree is one such modern solution to the decision making problems by learning the data from the problem domain and building a model which can be used for prediction supported by the systematic analytics. In order to build a model on a huge dataset Decision Tree algorithm needs to be transformed to manifest itself into distributed environment so that higher performance of training the model is achieved in terms of time, without compromising the accuracy of the Decision Tree built. In this paper, we have proposed an enhanced version of distributed decision tree algorithm to perform better in terms of model building time without compromising the accuracy.
Bhagyashri A. Kelkar, Sunil F. Rodd, and Umakant P. Kulkarni
World Scientific Pub Co Pte Lt
Subspace clustering is a challenging high-dimensional data mining task. There have been several approaches proposed in the literature to identify clusters in subspaces, however their performance and quality is highly affected by input parameters. A little research is done so far on identifying proper parameter values automatically. Other observed drawbacks are requirement of multiple database scans resulting into increased demand for computing resources and generation of many redundant clusters. Here, we propose a parameter light subspace clustering method for numerical data hereafter referred to as CLUSLINK. The algorithm is based on single linkage clustering method and works in bottom up, greedy fashion. The only input user has to provide is how coarse or fine the resulting clusters should be, and if not given, the algorithm operates with default values. The empirical results obtained over synthetic and real benchmark datasets show significant improvement in terms of accuracy and execution time.
Rashmi R. Salavi, Mallikarjun M. Math, and U. P. Kulkarni
Springer Singapore
With the advent in Internet and networking applications, security is a major concern in the current era of Information Technology. The huge amount of information exchanged over the Internet is vulnerable to security threats and attacks. Cryptography provides secure exchange of encrypted data by sharing a key. The major concern with this approach is data privacy as anybody with the key can access the data. Moreover, user loses control over data once it is uploaded to the cloud and must rely on cloud service provider. User must share a key with cloud service provider to perform any operations like searching, sorting, etc., or need to download and decrypt the data and then perform the operation. These approaches lead to privacy issue and repeated encryption decryption, even for small computation. These concerns are addressed by Homomorphic Encryption (HE), which enables the cloud service provider to carry out computations on ciphered data without decrypting it. With the advent of HE scheme, in 2009, the Fully Homomorphic Encryption (FHE) scheme was invented by C. Gentry, which allows any computational function to operate on encrypted data. But the practical implementation of FHE is still in research. This survey focuses on various traditional and modern cryptography techniques along with the different schemes of HE and FHE.
Nita Kakhandaki, Shrinivas B Kulkarni, Ramesh K., and Umakant P Kulkarni
IGI Global
A brain hemorrhage is one type of stroke, which is caused due to artery burst in the brain, killing the brain cells due to bleeding. Therefore, to reduce the criticality among the patients, for treatment, the doctors depend on accurate reports on the location of hemorrhage. Magnetic resonance imaging (MRI) is one of the best imaging modality when functional and structural abnormalities need to be found. To aid the identification of presence of abnormality, a novel NB-PKC algorithm for effective recognition of brain hemorrhages in MRI is proposed. A series of preprocessing is done, then the image undergoes binary thresholding process for applying an image mask on the hemorrhage region. Then for segmentation a modified multi-level segmenting algorithm is applied, using minimal local binary pattern and GLCM, combined features are extracted and finally for classification a novel Naïve Bayes- Probabilistic Kernel Classification is applied. These techniques designed could accurately identify the position and classified whether the image had an abnormality or not and could reduce human errors.
Umesh M. Kulkarni, Harish H., and Umakant P.
The Science and Information Organization
Wireless Sensor Networks (WSN) is becoming a crucial component of most of the fields of engineering. Heterogeneous WSN (HWSN) is characterized by wireless sensor nodes having link (communication), computation or energy heterogeneity for a specific application. WSN applications are constrained by the availability of power hence; conserving energy in a sensor network becomes a major challenge. Literature survey shows that node deployments can have good impact on energy conservation. Works show that self-adaptable nodes can significantly save energy as compared to other types of deployment. This work uses the concept of self-adaptation of nodes to conserve energy in a HWSN. A deployment strategy driven by some dynamic decision making capability can boost the overall performance of a WSN. The work presents an analysis of three types of deployments: like keeping all nodes fixed, all node moving and high energy nodes moving with respect to throughput, delay and energy consumption. Experimental results show that self-adaptable dynamic deployment gives 10% better throughput and 6% better energy conservation than static deployment strategies.
U.P. Kulkarni, S.B. Kulkarni, K.C. Shindhe, and A.N. Joshi
IEEE
The trend of getting autonomy status to Engineering College is moving fast forward under Technical Education Quality Improvement Program (TEQIP), a scheme of Government of India or otherwise as a symbol of pride but has forgotten the most important educational philosophy called Outcome Based Education (OBE). The OBE philosophy is supposed to ensure that, all students emerge as ‘successful’ by promoting learning successfully. OBE gives an opportunity for students to truly catch up and erase the records of earlier mistakes. However, the true spirit of OBE is not seen in Educational Institute who are accredited under OBE philosophy of National Board of Accreditation (NBA)[6]. Author of this paper presents a policy based concept so that all autonomous Institutions may follow to claim OBE tag for their Educational philosophy.