Dr Dnayaneshwar K Kirange

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Engineering, Computer Science Applications, Analysis, Multidisciplinary

Scopus Publications

Shortest Path Forwarding in Software-Defined Networks Using RYU Controller
Kishan P. Patel, Jıtendra P. Chaudhari, Hiren K. Mewada, Hardik S. Jayswal, Rajeshkumar V. Patel, and Dnyaneshwar K. Kirange
Seventh Sense Research Group Journals



Towards Automated Lip Reading: Developing Marathi Lip Reading Datasets and Neural Network Frameworks
Apurva Kulkarni and Dnyaneshwar Khemachandra Kirange
IEEE
This paper introduces an innovative method for automating lip-reading, with a specific focus on the Marathi language. Lip-reading plays a crucial role in aiding those with hearing impairments, but automating it presents significant challenges, especially for languages like Marathi lacking sufficient datasets. To tackle this, we propose a novel approach to automatic lip-reading, accompanied by the development of a specialized Marathi dataset. Leveraging advancements in computer vision and deep learning, our model deciphers linguistic content from lip movements, trained on this dataset. We employ various neural network architectures, including feed-forward, recurrent, and convolutional networks, to extract vital visual features crucial for accurate language interpretation Our primary goal is to provide a robust solution for automated lip-reading tailored specifically to regional languages like Marathi, aiming to enhance accessibility for individuals with hearing impairments, particularly in linguistically diverse contexts. This paper primarily discusses detailed exploration of dataset creation, neural network architectures for lip-reading system, we demonstrate the feasibility and potential impact of our approach. Our study underscores the significance of giving priority to regional languages in technological advancements to promote inclusivity for all individuals.


A survey on deep learning methods for brain tumor and liver lesion detection
Suraj Patil and D. K. Kirange
AIP Publishing



A Novel Hybrid U-Net with Custom Triplet Flatten Loss Function for Liver Lesion Detection
Suraj Patil and Dnyaneshwar K. Kirange
IACSIT Press
—Liver cancer ranks sixth among all cancers diagnosed globally. Due to the heterogeneous shape and size of the liver, the manual segmentation of the liver and lesions is a challenging task and time-consuming process. Most of the previous studies in this regard use traditional techniques of image processing to segment the liver and then use handcrafted features to detect lesions and tumors in the liver. The entire process is semi-automatic and results in a loss of information that affects the performance of prediction. Also, deep learning methods employed for liver lesion detection suffer from the misclassification of lesions due to an imbalance of pixel intensities and high processing computational costs. As a result, a new variant U-Net model is designed with a combination of ResNet-18 and ResNet-34 that automatically utilizes 3D contextual information of tumor tissue and detects lesions in the liver. In addition to these, a custom flattened triplet cross entropy function is designed that overcomes the problem of misclassification of lesions due to class imbalance. The novel methodology was evaluated using the benchmark LiTS17 dataset, and the best results were achieved with an accuracy, sensitivity, and specificity of 99.95%, 99.70%, and 99.85%, respectively. We were able to get a considerable reduction in error rate as well as excellent accuracy. The biomedical sector will be transformed as a result of this research.


Ensemble of Deep Learning Models for Brain Tumor Detection
Suraj Patil and Dnyaneshwar Kirange
Elsevier BV



An Approach to Detect Overlapping Diseases in Tomato Leaf Using CNN
Rizwanoddin Syed, H. D. Gadade, and D. K. Kirange
IEEE
India is the world’s largest agricultural country and the world’s it is on second position in the list of tomato producers. There is a need for lots of advancement in technology. Tomato yields differ based on how they are produced. The most important factor that affects the crop production quality and quality is the Leaf disease in these tomato plants. As a result, it’s vital to correctly diagnose and characterise these diseases. Tomato production is influenced by a variety of diseases. Early detection of the tomato plant diseases would help us to minimize the impact of the disease on tomato plants and maximize the production of crop. Various novel methods of diagnosing certain diseases have been widely used. The existing research has shown that the Convolution Neural Network-based approach gives us impressive results compared to traditional approaches. This work will address the same problem of disease detection. In the proposed methodology, CNN will be used along with image segmentation for detecting multiple or overlapping diseases in the same leaf. The proposed model will first use a image segmentation module for generating multiple instances of the same image, then we will use the some of trained CNN model to find the affected disease in the given leafs. By using the above results, we will suggest the disease control methods to the end-user.


Machine Learning Based Identification of Tomato Leaf Diseases at Various Stages of Development
H. D. Gadade and D. K. Kirange
IEEE
Mosaic, early blight, late blight, Septoria virus, leaf mold, Brown spot, and spider mite are the nine common types of tomato leaf diseases. The early and accurate analysis of tomato leaf disease can increase the productivity and quality of the tomato product. The existing research in image processing does not guarantee an accurate diagnosis of the disease. Also, existing methods are complex. In this paper, an accurate and robust method for tomato leaf disease identification as well as classification into various stages of development using machine learning is proposed. The work is carried out in two stages. Firstly the tomato leaf images will be classified into appropriate disease types. Then in the second phase, the tomato leaf disease is diagnosed at various stages of development. Identifying the stage of development of tomato leaf would help to decide the type and amount of treatment required for the plant. The diseased leaf images which are taken from the PlantVillage dataset have been classified into high, medium, low, and normal severity grading. The images are preprocessed using median filtering. For feature extraction, the system using shape, color, and texture features is evaluated. The performance evaluation is also done on various classification techniques including SVM, KNN, Naive Bayes, Decision Trees, and LDA. The research indicated that the proposed model provides a robust solution for tomato leaf disease severity grading.


Tomato leaf disease diagnosis and severity measurement
Haridas D. Gadade and D. K. Kirange
IEEE
Indian economy is mostly dependent on agriculture. One of the highly used food crops in India is Tomato. Hence detection and analysis of leaf disease on tomato plants so as to increase the yield is highly essential. It becomes very hard to manually detect and analyze the tomato leaf diseases. Hence, in this paper we have proposed a segmentation-based approach for automatic segmentation of infected regions. The segmented area is further analyzed for disease classification and severity measurement. Leaf disease detection technique proposed here involves various stages including preprocessing, segmentation, feature extraction, training and classification followed by the severity measurement from the disease segmented region. We have analyzed the performance of different features extraction techniques including color, texture and shape features along with various classification techniques. The performance of the proposed system really inspires the farmers to use the automated system for detection and severity measurement of tomato plant disease.


Educational Data Mining Survey for Predicting Student’s Academic Performance
Sharayu N. Bonde and D. K. Kirange
Springer International Publishing



Diabetic retinopathy detection and grading using machine learning
Kirange D.K. and
The World Academy of Research in Science and Engineering
Diabetic Retinopathy (DR) is a constantly deteriorating disease, being one of the leading causes of vision impairment and blindness. Subtle distinction among different grades and existence of many significant small features make the task of recognition very challenging. In addition, the present approach of retinopathy detection is a very laborious and time-intensive task, which heavily relies on the skill of a physician. Automated detection of diabetic retinopathy is essential to tackle these problems. Early-stage detection of diabetic retinopathy is also very important for diagnosis, which can prevent blindness with proper treatment. In this paper, we developed a novel system which performs the early-stage detection by identifying all microaneurysms (MAs), the first signs of DR, along with correctly assigning labels to retinal fundus images which are graded into five categories. We have tested our system on the largest publicly available IDRiD diabetic retinopathy dataset, and achieved 77.85% accuracy with Gabor features and Naïve Bayes Classification.


Artificial Intelligence: A Survey on Lip-Reading Techniques
Apurva H. Kulkarni and Dnyaneshwar Kirange
IEEE
Lip reading is a visual way of “listening” to someone. This is done by looking at the speakers face to follow their speech patterns in order to recognize what is being said. Lip-reading technology mainly includes face detection, lip localization, feature extraction, training the classifier through corpus and finally recognition of the word/sentence through lip movement. An intelligent system will be trained by giving user's lip-movement frames sequences as input and will identify lip movement and the said word using either visual information or both audio and visual information. Deep learning is an emerging branch of artificial intelligence which mimics the human brain. It has different layers in the model which is used to process minute details like neurons in brain. This paper mainly focuses on the survey of different lip reading techniques and different language datasets in the era of deep learning. Various Automatic lip reading techniques are discussed and summarized.


Survey on Evaluation of Student's Performance in Educational Data Mining
Sharayu N. Bonde and D. K. Kirange
IEEE
Educational information mining is rising field that spotlights on breaking down educational information to create models for enhancing learning encounters and enhancing institutional viability. Expanding enthusiasm for information mining and educational frameworks, make educational information mining as another developing exploration group. Educational Data Mining intends to remove the concealed learning from expansive Educational databases with the utilization of procedures and apparatuses. Educational Data Mining grows new techniques to find information from Educational database and it is utilized for basic decision making in Educational framework. The knowledge is hidden among the Educational informational Sets and it is extractable through data mining techniques. It is essential to think about and dissect Educational information particularly understudies execution. Educational Data Mining (EDM) is the field of study relates about mining Educational information to discover intriguing examples and learning in Educational associations. This investigation is similarly worried about this subject, particularly, the understudies execution. This study investigates numerous components theoretically expected to influence student's performance in higher education, and finds a subjective model which best classifies and predicts the student's performance in light of related individual and phenomenal elements.


Analyzing the effect of database dimensionality on performance of adaptive apriori algorithm
Shubhangi D. Patil, Ratnadeep R. Deshmukh, Dnyaneshwar K. Kirange, and Swapnil Waghmare
Springer Singapore



Iris recognition using radon transform and GLCM
Kanchan S Bhagat, Pramod B. Patil, Ratnadeep R. Deshmukh, D.K. Kirange, and Swapnil Waghmare
IEEE
Iris recognition for some time now has been a challenging exercise. This perhaps is due to the use of inappropriate descriptors during the feature extraction stage. In this paper, a Radon Transform is used as an iris signature descriptor. Blood vessels are segmented from iris image. After blood vessel segmentation, the radon transform is applied on the segmented image. The GLCM, Gabor and Local Binary Patterns are used for feature extraction. Well known SVM classifier is used for classification of the iris data. The performance of the system is evaluated on DRIVE and High Resolution Image Databases. The system performs better for the radon transform signature. This proposed approach of iris recognition using blood vessel segmentation is robust and secure and has the ability to recognize retinal images from the photographs of the known iris images. The system is more efficient in terms of accuracy as well as time complexity. The GLCM features when applied on Radon signatures gives improved results for both datasets of DRIVE and HRF.


Adaptive Apriori Algorithm for frequent itemset mining
Shubhangi D. Patil, Ratnadeep R. Deshmukh, and D.K. Kirange
IEEE
Obtaining frequent itemsets from the dataset is one of the most promising area of data mining. The Apriori algorithm is one of the most important algorithm for obtaining frequent itemsets from the dataset. But the algorithm fails in terms of time required as well as number of database scans. Hence a new improved version of Apriori is proposed in this paper which is efficient in terms of time required as well as number of database scans than the Apriori algorithm. It is well known that the size of the database for defining candidates has great effect on running time and memory need. We presented experimental results, showing that the proposed algorithm always outperform Apriori. To evaluate the performance of the proposed algorithm, we have tested it on Turkey student's database as well as a real time dataset.

RECENT SCHOLAR PUBLICATIONS

Towards Automated Lip Reading: Developing Marathi Lip Reading Datasets and Neural Network Frameworks
A Kulkarni, DK Kirange
2023 4th International Conference on Intelligent Technologies (CONIT), 1-6 2024



Shortest Path Forwarding in Software-Defined Networks Using RYU Controller
DKK Kishan P. Patel1 , Jıtendra P. Chaudhari 2 , Hiren K. Mewada3, Hardik S ...
SSRG International Journal of Electrical and Electronics Engineering 11 (5 2024



Recursive feature elimination and optimized hybrid ensemble approach for early heart disease prediction
J Chaudhari, H Mewada, Y Kosta, K Bhagat, S Kirange
International Journal of Computing and Digital Systems 14 (1), 1-xx 2023



A survey on deep learning methods for brain tumor and liver lesion detection
S Patil, DK Kirange
AIP Conference Proceedings 2760 (1) 2023



An Optimized Deep Learning Model with Feature Fusion for Brain Tumor Detection.
S Patil, D Kirange
International Journal of Next-Generation Computing 14 (1) 2023



A Novel Hybrid U-Net with Custom Triplet Flatten Loss Function for Liver Lesion Detection
DKK Suraj Patil
IJCTE- International Journal of Computer Theory and Engineering 15 (2), 82-89 2023



Ensemble of deep learning models for brain tumor detection
S Patil, D Kirange
Procedia Computer Science 218, 2468-2479 2023



An approach to detect overlapping diseases in tomato leaf using cnn
R Syed, HD Gadade, DK Kirange
2022 4th International Conference on Advances in Computing, Communication 2022



Deep learning for tomato leaf disease detection for images captured in varying capturing conditions.
HD Gadade, DK Kirange
2022



Improved Salp Swarm Optimization-based Fuzzy Centroid Region Growing for Liver Tumor Segmentation and Deep Learning Oriented Classification.
S Patil, D Kirange, R Hablani
International Journal of Next-Generation Computing 13 (5) 2022



Deep Learning for Tomato Leaf Disease Detection for Images Captured in Varying Capturing Conditions
DDKK Haridas D. Gadade
JJM 15 (1), 2191 - 2200 2022



Forecasting COVID 19 Cases on Radiological Images Using Deep Learning and VGG Model
DDKK Dr Nandini Chaudhari,Dr Avani Vasant,Dr Nitesh Sureja,Dr Darshana H Patel
Jundishapur Journal of Microbiology 15 (1), 117-732 2022



Machine learning based identification of tomato leaf diseases at various stages of development
HD Gadade, DK Kirange
2021 5th International Conference on Computing Methodologies and 2021



A Survey on Deep Learning Methods for Brain Tumor and Liver Lesion Detection
DKK Suraj Patil
International Conference on global entrepreneurship Trends & empowerment 2021



Tomato leaf disease diagnosis and severity measurement
HD Gadade, DK Kirange
2020 fourth world conference on smart trends in systems, security and 2020



END POINT ANALYSIS FOR DETECTING PITCH BOUNDARIES OF SPOKEN INDIAN DEVNAGARI LANGUAGE NUMERICAL USING AUTOCORRELATION TECHNIQUE
DJPC Dr Pramod B. Patil, Dr Shubhangi D Patil, Dr D K Kirange, Dr K S Bhagat
High Technology Letters,ISSN NO : 1006-6748 26 (5), 424-427 2020



Ealuation of Bandwidth Utilization in SDN
DSDP Dr. J P Chaudhari ,Dr. D K Kirange ,Dr. K S Bhagat
Journal of Xidian University ISSN No. 1001-2400 14 (5), 1758-1767 2020



Software Defined Networks using Mininet
SDP Pramod B Patil., Kanchan S. Bhagat., D K Kirange
International Journal of Recent Technology and Engineering (IJRTE),ISSN 2020



Machine Learning Approach towards Tomato Leaf Disease Classification
D.K.Kirange, H. D. Gadade
International Journal of Advanced Trends in Computer Science and Engineering 2020



PREDICTIVE MODELLING OF BRAIN TUMOR DETECTION USING DEEP LEARNING
VN Suraj Patil , Dr D. K. Kirange
JOURNAL OF CRITICAL REVIEWS,ISSN- 2394-5125 7 (04), 1805-1813 2020

MOST CITED SCHOLAR PUBLICATIONS

Ensemble of deep learning models for brain tumor detection
S Patil, D Kirange
Procedia Computer Science 218, 2468-2479 2023
Citations: 64



ASPECT BASED SENTIMENT ANALYSIS SEMEVAL-2014 TASK 4
RRD D. K. Kirange
Asian Journal of Computer Science And Information Technology 4 (8), 72-75 2014
Citations: 64



Emotion Classification of News Headlines Using SVM
RRD D. K. Kirange
Asian Journal Of Computer Science And Information Technology 2 (5), 104 –106 2012
Citations: 61



Sentiment Analysis of News Headlines for Stock Price Prediction
DRRD Mr. D. K. Kirange
COMPUSOFT, An international journal of advanced computer technology 5 (3 2016
Citations: 52



Tomato leaf disease diagnosis and severity measurement
HD Gadade, DK Kirange
2020 fourth world conference on smart trends in systems, security and 2020
Citations: 40



Machine Learning Approach towards Tomato Leaf Disease Classification
D.K.Kirange, H. D. Gadade
International Journal of Advanced Trends in Computer Science and Engineering 2020
Citations: 28



Machine learning based identification of tomato leaf diseases at various stages of development
HD Gadade, DK Kirange
2021 5th International Conference on Computing Methodologies and 2021
Citations: 26



Diabetic Retinopathy Detection and Grading Using Machine Learning
NC D. K. Kirange, J.P. Chaudhari , K. P. Rane , K. S. Bhagat
International Journal of Advanced Trends in Computer Science and Engineering 2019
Citations: 21



Emotion classification of restaurant and laptop review dataset: Semeval 2014 task 4
DK Kirange, RR Deshmukh
International Journal of Computer Applications 113 (6) 2015
Citations: 18



Adaptive Apriori Algorithm for frequent itemset mining
SD Patil, RR Deshmukh, K D K
System Modeling & Advancement in Research Trends (SMART), IEEE Conference, 7 2016
Citations: 17



Classifying News Headlines for Providing User Centered E-Newspaper Using SVM
DKKRR Deshmukh
nternational Journal of Emerging Trends & Technology in ComputerScience 2013
Citations: 16



PREDICTIVE MODELLING OF BRAIN TUMOR DETECTION USING DEEP LEARNING
VN Suraj Patil , Dr D. K. Kirange
JOURNAL OF CRITICAL REVIEWS,ISSN- 2394-5125 7 (04), 1805-1813 2020
Citations: 14



Artificial intelligence: a survey on lip-reading techniques
AH Kulkarni, D Kirange
2019 10th International Conference on Computing, Communication and 2019
Citations: 12



Survey on Evaluation of Student's Performance in Educational Data Mining
SN Bonde, DK Kirange
2018 Second International Conference on Inventive Communication and 2018
Citations: 12



Educational data mining survey for predicting student’s academic performance
SN Bonde, DK Kirange
Proceeding of the International Conference on Computer Networks, Big Data 2020
Citations: 9



Iris recognition using radon transform and GLCM
KS Bhagat, PB Patil, RR Deshmukh, DK Kirange, S Waghmare
International Conference on Advances in Computing, Communications and 2017
Citations: 7



ASPECT AND EMOTION CLASSIFICATION OF RESTAURANT AND LAPTOP REVIEWS USING SVM
RRD D.K.Kirange
International Journal of Current Research 8 (03), 28352-28356 2016
Citations: 4



Software Defined Networks using Mininet
SDP Pramod B Patil., Kanchan S. Bhagat., D K Kirange
International Journal of Recent Technology and Engineering (IJRTE),ISSN 2020
Citations: 3



An approach to detect overlapping diseases in tomato leaf using cnn
R Syed, HD Gadade, DK Kirange
2022 4th International Conference on Advances in Computing, Communication 2022
Citations: 2



Deep learning for tomato leaf disease detection for images captured in varying capturing conditions.
HD Gadade, DK Kirange
2022
Citations: 2