Uma Boregowda
Research Subjects
Uma Boregowda has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Arun Nagaraja
Jain University, Bangalore, India
4 shared publications Venugopal Chakravarthy
2 shared publicationsVenugopal R. Chakravarthy
2 shared publications- A. Geetha Kiran
Department of Computer Science, Malnad College of Engineering, Hasssan, India
1 shared publication A. Geethakiran
Department of Computer Science and Engineering, Malnad College of Engineering, Hassan, Karnataka
1 shared publicationA. M. Vinod
Department of Master of Computer Applications, Malnad College of Engineering,Hassan, Karnataka
1 shared publication
Latest Publications
- Open Access
- 28 May 2024
- Published by Springer Nature in Journal of Umm Al-Qura University for Engineering and Architecture
- Vol. 15 (4) , 467-485
A Convolution Neural Network with Skip Connections (CNNSC) approach for detecting micronutrients boron and iron deficiency in banana leaves
Banana plants require a precise balance of 16 essential nutrients to flourish, with micronutrients playing a pivotal role in smaller proportions than macronutrients. Insufficient micronutrient provision in Banana plants can impede growth, hinder flowering, and diminish fruit production. Precise identification of deficiencies is imperative for farmers aiming to cultivate nutrient-dense crops and enhance their yields. Micronutrients such as Boron contribute to hormone regulation, while Iron facilitates enzyme function, DNA synthesis, and overall metabolic processes in plants. Observable manifestations of Boron and Iron deficiencies on banana leaves are crucial indicators necessitating intervention. The present work proposes a novel deep learning methodology, employing a CNN model with Skip Connections (CNNSC), to detect Boron and Iron deficiencies in banana foliage. The CNNSC model, featuring thirteen layers, surpasses established architectures like VGG16, DenseNet, and Inception V3. Training the model on a specialized curated dataset comprising 11,000 nutrient-deficient images, with a split of 70% for training and 30% for testing, has yielded promising outcomes. Key performance metrics, encompassing accuracy, loss, precision, F1-score, recall, and the confusion matrix underscore the efficacy of the model, achieving an impressive accuracy rate of approximately 95%.
- 28 May 2024
- Published by Springer Nature in Journal of Umm Al-Qura University for Engineering and Architecture
- Vol. 15 (4) , 467-485
Open AccessA Convolution Neural Network with Skip Connections (CNNSC) approach for detecting micronutrients boron and iron deficiency in banana leaves
Banana plants require a precise balance of 16 essential nutrients to flourish, with micronutrients playing a pivotal role in smaller proportions than macronutrients. Insufficient micronutrient provision in Banana plants can impede growth, hinder flowering, and diminish fruit production. Precise identification of deficiencies is imperative for farmers aiming to cultivate nutrient-dense crops and enhance their yields. Micronutrients such as Boron contribute to hormone regulation, while Iron facilitates enzyme function, DNA synthesis, and overall metabolic processes in plants. Observable manifestations of Boron and Iron deficiencies on banana leaves are crucial indicators necessitating intervention. The present work proposes a novel deep learning methodology, employing a CNN model with Skip Connections (CNNSC), to detect Boron and Iron deficiencies in banana foliage. The CNNSC model, featuring thirteen layers, surpasses established architectures like VGG16, DenseNet, and Inception V3. Training the model on a specialized curated dataset comprising 11,000 nutrient-deficient images, with a split of 70% for training and 30% for testing, has yielded promising outcomes. Key performance metrics, encompassing accuracy, loss, precision, F1-score, recall, and the confusion matrix underscore the efficacy of the model, achieving an impressive accuracy rate of approximately 95%.
- Open Access
- 20 May 2022
- Published by MDPI AG in Future Internet
- Vol. 14 (5) , 157
Quality-of-Service-Linked Privileged Content-Caching Mechanism for Named Data Networks
The domain of information-centric networking (ICN) is expanding as more devices are becoming a part of connected technologies. New methods for serving content from a producer to a consumer are being explored, and Named Data Networking (NDN) is one of them. The NDN protocol routes the content from a producer to a consumer in a network using content names, instead of IP addresses. This facility, combined with content caching, efficiently serves content for very large networks consisting of a hybrid and ad hoc topology with both wired and wireless media. This paper addresses the issue of the quality-of-service (QoS) dimension for content delivery in NDN-based networks. The Internet Engineering Task Force (IETF) classifies QoS traffic as (prompt, reliable), prompt, reliable, and regular, and assigns corresponding priorities for managing the content. QoS-linked privileged content caching (QLPCC) proposes strategies for Pending Interest Table (PIT) and content store (CS) management in dedicated QoS nodes for handling priority content. QoS nodes are intermediately resourceful NDN nodes between content producers and consumers which specifically manage QoS traffic. The results of this study are compared with EQPR, PRR probability cache, and Least Frequently Used (LFU) and Least Fresh First (LFF) schemes, and QLPCC outperformed the latter-mentioned schemes in terms of QoS-node CS size vs. hit rate (6% to 47%), response time vs, QoS-node CS size (65% to 90%), and hop count vs. QoS-node CS size (60% to 84%) from the perspectives of priority traffic and overall traffic. QLPCC performed predictably when the NDN node count was increased from 500 to 1000, showing that the strategy is scalable.
- 20 May 2022
- Published by MDPI AG in Future Internet
- Vol. 14 (5) , 157
Open AccessQuality-of-Service-Linked Privileged Content-Caching Mechanism for Named Data Networks
The domain of information-centric networking (ICN) is expanding as more devices are becoming a part of connected technologies. New methods for serving content from a producer to a consumer are being explored, and Named Data Networking (NDN) is one of them. The NDN protocol routes the content from a producer to a consumer in a network using content names, instead of IP addresses. This facility, combined with content caching, efficiently serves content for very large networks consisting of a hybrid and ad hoc topology with both wired and wireless media. This paper addresses the issue of the quality-of-service (QoS) dimension for content delivery in NDN-based networks. The Internet Engineering Task Force (IETF) classifies QoS traffic as (prompt, reliable), prompt, reliable, and regular, and assigns corresponding priorities for managing the content. QoS-linked privileged content caching (QLPCC) proposes strategies for Pending Interest Table (PIT) and content store (CS) management in dedicated QoS nodes for handling priority content. QoS nodes are intermediately resourceful NDN nodes between content producers and consumers which specifically manage QoS traffic. The results of this study are compared with EQPR, PRR probability cache, and Least Frequently Used (LFU) and Least Fresh First (LFF) schemes, and QLPCC outperformed the latter-mentioned schemes in terms of QoS-node CS size vs. hit rate (6% to 47%), response time vs, QoS-node CS size (65% to 90%), and hop count vs. QoS-node CS size (60% to 84%) from the perspectives of priority traffic and overall traffic. QLPCC performed predictably when the NDN node count was increased from 500 to 1000, showing that the strategy is scalable.
- Open Access
- 21 February 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 39184-39196
Similarity Based Feature Transformation for Network Anomaly Detection
The fundamental objective behind any network intrusion detection system is to automate the detection process whenever intrusions occur in the network. The problem of the network anomaly detection is to determine, if the network incoming traffic is legitimate (or) anomalous. Automated detection systems designed to identify incoming anomalous traffic patterns usually apply widely used machine learning techniques. However, irrespective of any system model which is developed to identify anomalous traffic, all these models requires comparing anomalous and normal traffic patterns. Such comparisons implicitly depend on the ability of the underlying machine learning model to gauge the similarity between a known legitimate observation and the target. The efficiency of any network anomalous detection system depends on the use of distance (or) similarity measures and how they are actually applied. A novel distance function which can be applied to determine the similarity between two conditional feature pattern vectors is an important contribution of present research. Feature dimensionality is another important issue for any machine learning algorithm. In the present work, feature reduction is achieved using the proposed feature transformation technique. However, our approach for feature transformation uses the proposed gaussian distance function to achieve dimensionality reduction to represent the original input dataset in the new transformation space. We have also proposed new computation expressions for determining equivalent deviation and threshold in gaussian space. Experiments are performed on KDD and NSL-KDD datasets by considering widely applied classifier algorithms in various state-of-art research contributions. For performance validation of machine learning models, k-fold cross validation is applied by setting k to 10 through considering evaluation parameters such as accuracy, precision and recall. Experiment results have proved that our approach for anomaly detection that applies the proposed feature transformation technique proved comparatively better to detection methods CANN, GARUDA, and UTTAMA addressed in the recent research literature.
- 21 February 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 39184-39196
Open AccessSimilarity Based Feature Transformation for Network Anomaly Detection
The fundamental objective behind any network intrusion detection system is to automate the detection process whenever intrusions occur in the network. The problem of the network anomaly detection is to determine, if the network incoming traffic is legitimate (or) anomalous. Automated detection systems designed to identify incoming anomalous traffic patterns usually apply widely used machine learning techniques. However, irrespective of any system model which is developed to identify anomalous traffic, all these models requires comparing anomalous and normal traffic patterns. Such comparisons implicitly depend on the ability of the underlying machine learning model to gauge the similarity between a known legitimate observation and the target. The efficiency of any network anomalous detection system depends on the use of distance (or) similarity measures and how they are actually applied. A novel distance function which can be applied to determine the similarity between two conditional feature pattern vectors is an important contribution of present research. Feature dimensionality is another important issue for any machine learning algorithm. In the present work, feature reduction is achieved using the proposed feature transformation technique. However, our approach for feature transformation uses the proposed gaussian distance function to achieve dimensionality reduction to represent the original input dataset in the new transformation space. We have also proposed new computation expressions for determining equivalent deviation and threshold in gaussian space. Experiments are performed on KDD and NSL-KDD datasets by considering widely applied classifier algorithms in various state-of-art research contributions. For performance validation of machine learning models, k-fold cross validation is applied by setting k to 10 through considering evaluation parameters such as accuracy, precision and recall. Experiment results have proved that our approach for anomaly detection that applies the proposed feature transformation technique proved comparatively better to detection methods CANN, GARUDA, and UTTAMA addressed in the recent research literature.
- Open Access
- 6 June 2019
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Intrusion detection using dimensionality reduced soft matrix
- 6 June 2019
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessIntrusion detection using dimensionality reduced soft matrix
- Open Access
- 6 June 2019
- Published by Association for Computing Machinery (ACM)
- p. 1-7
A generalized research study on distance measures, learning algorithms and datasets
- 6 June 2019
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessA generalized research study on distance measures, learning algorithms and datasets
- 5 March 2019
- Published by Springer Nature in Foundations of Science
- Vol. 25 (4) , 1049-1075
UTTAMA: An Intrusion Detection System Based on Feature Clustering and Feature Transformation
- 5 March 2019
- Published by Springer Nature in Foundations of Science
- Vol. 25 (4) , 1049-1075
UTTAMA: An Intrusion Detection System Based on Feature Clustering and Feature Transformation
- 1 January 2016
- Published by Rajarambapu Institute of Technology in Journal of Engineering Education Transformations
Effective Teaching through Programming Assignments
Students and educators are the main components of any teaching system wherein educators play an important role. The vision of every educator is to make every student a successful IT professional in the current industry scenario. To meet the requirements of the IT industry, we need to enhance the quality of our students through effective teaching. Many studies have shown that life skills along with technical skill decide the success of a person. Hence, an attempt is made to improve both technical and life skills of students through regular engineering courses, instead of having separate courses on communication skills and ethical values. The idea of enhancing the skills of students through our proposed approach is experimented for the "Algorithm Design and Analysis" course. Our experimented process of effective teaching through programming assignments has given a very satisfactory result and the students are also happy about their accomplishments in the course.
- 1 January 2016
- Published by Rajarambapu Institute of Technology in Journal of Engineering Education Transformations
Effective Teaching through Programming Assignments
Students and educators are the main components of any teaching system wherein educators play an important role. The vision of every educator is to make every student a successful IT professional in the current industry scenario. To meet the requirements of the IT industry, we need to enhance the quality of our students through effective teaching. Many studies have shown that life skills along with technical skill decide the success of a person. Hence, an attempt is made to improve both technical and life skills of students through regular engineering courses, instead of having separate courses on communication skills and ethical values. The idea of enhancing the skills of students through our proposed approach is experimented for the "Algorithm Design and Analysis" course. Our experimented process of effective teaching through programming assignments has given a very satisfactory result and the students are also happy about their accomplishments in the course.
- 1 December 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 6-11
A Framework for Multiple Parallel Task Graphs (PTG) Scheduler
Many applications in scientific computations exhibit both data and task parallelism. Several studies have proved that designing parallel applications using both task and data parallelism is an effective approach than pure data or pure task parallel models. This mixed parallelism achieves both higher scalability and performance. Mixed parallel applications are represented as Parallel Task Graph (PTG), a graph of data parallel tasks. Scheduling such a mixed-parallel application is NP-complete even on a single homogeneous cluster. To maximize resource utilizations and to increase cluster throughput, multiple applications are scheduled concurrently on a cluster. Scheduling multiple applications is challenging as different applications compete for the shared resources and also fairness must be ensured. A new method to perform concurrent schedule of multiple PTGs on a cluster is proposed in this work. Further a complete framework to schedule PTGs submitted at different instants of time and to vary processor allotment for each application during their depending on processor availability is proposed. From simulation experiments, it is observed that the proposed method to schedule multiple PTGs performs better than other methods found in the literature. The suggested scheduler framework to handle online submission of PTGs is proved to be a promising one.
- 1 December 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 6-11
A Framework for Multiple Parallel Task Graphs (PTG) Scheduler
Many applications in scientific computations exhibit both data and task parallelism. Several studies have proved that designing parallel applications using both task and data parallelism is an effective approach than pure data or pure task parallel models. This mixed parallelism achieves both higher scalability and performance. Mixed parallel applications are represented as Parallel Task Graph (PTG), a graph of data parallel tasks. Scheduling such a mixed-parallel application is NP-complete even on a single homogeneous cluster. To maximize resource utilizations and to increase cluster throughput, multiple applications are scheduled concurrently on a cluster. Scheduling multiple applications is challenging as different applications compete for the shared resources and also fairness must be ensured. A new method to perform concurrent schedule of multiple PTGs on a cluster is proposed in this work. Further a complete framework to schedule PTGs submitted at different instants of time and to vary processor allotment for each application during their depending on processor availability is proposed. From simulation experiments, it is observed that the proposed method to schedule multiple PTGs performs better than other methods found in the literature. The suggested scheduler framework to handle online submission of PTGs is proved to be a promising one.
- 1 August 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 143-146
A Hybrid Task Scheduler for DAG Applications on a Cluster of Processors
With the advent of large scale computing environment, there is a need for scheduling methods which allow multiple DAG-structured applications to share the cluster resources with the objectives of increasing the throughput and maximizing the resource utilization. The number of processors allotted to each application is decided during runtime, depending on the number and nature of applications being scheduled together. The static schedule generated is fixed for a specified number of processors and also the quality of schedule is handicapped by the estimated execution time of tasks in the application. Since the number of processors allotted for each DAG is not known a priori in a multiple DAG scheduling environment, instead of a static schedule, a dynamic scheduler which relies on actual execution time of tasks is better. But its performance is limited as the only information it has is the number of tasks scheduled on each processor. The knowledge of an application in terms of its structure, estimated execution time of tasks and relative importance of tasks, can be used by a dynamic scheduler for better scheduling of tasks resulting in decreased application execution time. With the use of a priori application information, different scheduling policies for a hybrid scheduler are proposed and their performance is compared with the scheduler found in literature. The results obtained demonstrate the suitability of the proposed hybrid scheduler in multiple DAGs scheduling environment.
- 1 August 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 143-146
A Hybrid Task Scheduler for DAG Applications on a Cluster of Processors
With the advent of large scale computing environment, there is a need for scheduling methods which allow multiple DAG-structured applications to share the cluster resources with the objectives of increasing the throughput and maximizing the resource utilization. The number of processors allotted to each application is decided during runtime, depending on the number and nature of applications being scheduled together. The static schedule generated is fixed for a specified number of processors and also the quality of schedule is handicapped by the estimated execution time of tasks in the application. Since the number of processors allotted for each DAG is not known a priori in a multiple DAG scheduling environment, instead of a static schedule, a dynamic scheduler which relies on actual execution time of tasks is better. But its performance is limited as the only information it has is the number of tasks scheduled on each processor. The knowledge of an application in terms of its structure, estimated execution time of tasks and relative importance of tasks, can be used by a dynamic scheduler for better scheduling of tasks resulting in decreased application execution time. With the use of a priori application information, different scheduling policies for a hybrid scheduler are proposed and their performance is compared with the scheduler found in literature. The results obtained demonstrate the suitability of the proposed hybrid scheduler in multiple DAGs scheduling environment.
- 30 April 2014
- Published by Academy and Industry Research Collaboration Center (AIRCC) in International Journal of Computer Science and Information Technology
- Vol. 6 (2) , 187-198
Sharing of Cluster Resources among Multiple Workflow Applications
- 30 April 2014
- Published by Academy and Industry Research Collaboration Center (AIRCC) in International Journal of Computer Science and Information Technology
- Vol. 6 (2) , 187-198
Sharing of Cluster Resources among Multiple Workflow Applications