Dr. Nagendra Panini Challa
@vitap.ac.in
Assistant Professor Senior Grade-2 / School of Computer Science and Engineering (SCOPE)
VIT-AP University, Amaravati, India
RESEARCH INTERESTS
Machine Learning, Artificial Intelligence
Scopus Publications
Scopus Publications
Sagar Mousam Parida, Sagar Dhanraj Pande, Nagendra Panini Challa, and Bhawani Sankar Panigrahi
European Alliance for Innovation n.o.
This research paper aims to investigate the significance of electrical products, specifically earbuds and headphones, in the digital world. The processes of decision-making and purchasing of audio accessories are often characterized by a significant investment of time and effort, as well as a complex interplay of competing priorities. In addition, various methodologies are employed for the selection and procurement of audio equipment through the utilization of machine learning algorithms. This study aimed to gather responses from a diverse group of participants regarding their preferences for the latest functionalities and essential components in their gadgets. The data was collected through a questionnaire that provided multiple options about the specifications of the audio accessories for the participants to choose from. The study employed seven distinct input factors to elicit responses from participants. These factors included brand, type, design, fit, price, noise cancellation, and folding design. The quantification of each input parameter was executed through the utilization of a scaling function in the Fuzzy Logic Interface, which assigned the labels “Yes” or “No” to each parameter. In this study, the Mamdani approach, which is a widely used fuzzy reasoning tool, was employed to develop a fuzzy logic controller (FLC) consisting of seven input and one output processes. In this study, standard fuzzy algorithms were employed to enhance the accuracy of the process of selecting an audio accessory in accordance with the user's specific requirements on the basis of Fuzzy threshold where “Yes” signifies about the availability of such audio accessory and “No” refers to the non-availability and readjustment of the input parameters.
Attaluri Harshitha, Beebi Naseeba, Narendra Kumar Rao, Abbaraju Sai Sathwik, and Nagendra Panini Challa
European Alliance for Innovation n.o.
Research in agriculture is expanding. Agriculture in particular relies heavily on earth and environmental factors, such as temperature, humidity, and rainfall, to forecast crops. Crop prediction is a crucial problem in agriculture, and machine learning is an emerging study area in this area. Any grower is curious to know how much of a harvest he can anticipate. In the past, producers had control over the selection of the product to be grown, the monitoring of its development, and the timing of its harvest. Today, however, the agricultural community finds it challenging to carry on because of the sudden shifts in the climate. As a result, machine learning techniques have increasingly replaced traditional prediction methods. These techniques have been employed in this research to determine crop production. It is critical to use effective feature selection techniques to transform the raw data into a dataset that is machine learning compatible in order to guarantee that a particular machine learning (ML) model operates with a high degree of accuracy. The accuracy of the model will increase by reducing redundant data and using only data characteristics that are highly pertinent in determining the model's final output. In order to guarantee that only the most important characteristics are included in the model, it is necessary to use optimal feature selection. Our model will become overly complex if we combine every characteristic from the raw data without first examining their function in the model-building process. Additionally, the time and area complexity of the Machine learning model will grow with the inclusion of new characteristics that have little impact on the model's performance. The findings show that compared to the current classification method, an ensemble technique provides higher prediction accuracy.
Kamepalli S. L. Prasanna and Nagendra Panini Challa
Springer Science and Business Media LLC
Nagendra Panini Challa, Abbaraju Sao Sathwik, Jinka Chandra Kiran, Kokkula Lokesh, Venkata Sasi Deepthi Ch, and Beebi Naseeba
European Alliance for Innovation n.o.
An intelligent system known as a fashion suggestion system gives consumers personalised fashion advice based on their tastes, style, body shape, and other variables. The system analyses a user's data and predicts the best fashion products for them using data analytics, machine learning, and artificial intelligence approaches. Intelligent fashion suggestion is currently desperately needed due to the explosive expansion of fashion-focused trends. We create algorithms that automatically recommend users' attire based on their own fashion tastes. We investigate the use of deep networks to this difficult problem. Our technology, called FashionNet, is made up of two parts: a matching network for determining compatibility and a feature network for feature extraction. We create a two-stage training method that transfers a broad compatibility model to a model that embeds personal choice in order to achieve personalised recommendation.
Abbaraju Sai Sathwik, Beebi Naseeba, Jinka Chandra Kiran, Kokkula Lokesh, Venkata Sasi Deepthi Ch, and Nagendra Panini Challa
European Alliance for Innovation n.o.
In the field of medicine, it is very important to prognosticate diseases early to cure them from their initial stages. Monkeypox is a viral zoonosis with symptoms similar to the smallpox as it spreads widely with the person who is in close contact with the affected. So, it can be diagnosed using various new age computing techniques such as CNN, RESNET, VGG, EfficientNet. In this work, a prediction model is utilized for better classification of Monkeypox. However, the implementation of machine learning in detecting COVID-19 has encouraged scientists to explore its potential for identifying monkeypox. One challenge in using Deep learning (DL) and machine learning (ML) for this purpose is the lack of sufficient data, including images of monkeypox-infected skin. In response, Monkeypox Skin Image Dataset is collected from Kaggle, the largest of its kind till date which includes images of healthy skin as well as monkeypox and some other infected skin diseases. The dataset undergoes through different data augmentation phases which is fed to different DL and ML algorithms for producing better results. Out of all the approaches, VGG19 and Resnet has got the best result with 92% recognition accuracy.
Kokkula Lokesh, Nagendra Panini Challa, Abbaraju Sai Satwik, Jinka Chandra Kiran, Narendra Kumar Rao, and Beebi Naseeba
European Alliance for Innovation n.o.
The early detection of Alzheimer's disease, a neurodegenerative ailment that affects both cognitive and social functioning, can be accomplished using deep learning technology. Deep learning is more accurate and efficient than human diagnosis in detecting functional connectivity and changes in the brain networks of people with MCI. Early detection of Mild Cognitive Impairment (MCI) can reduce the disease's development. However, achieving high accuracy levels is difficult due to the dearth of reliable biomarkers. The dataset was picked up from the Kaggle database. It contains magnetic resonance images of the brain, each image being unique and in different stages of the disease for classification purpose for our project, as it was most suitable for our project’s needs. We developed a deep learning model using learning AZ net, Dense net, Resnet, Efficient Net and Inception Net with a maximum accuracy of 99.96% for classifying Alzheimer's disease stages and early detection using transfer learning and other approaches.
Kamepalli S. L. Prasanna and Nagendra Panini Challa
World Scientific Pub Co Pte Ltd
The clinical diagnosis of heart disease in most situations is based on a difficult amalgamation of pathological and clinical information. Because of this complication, there is a significant level of curiosity among many diagnostic healthcare professionals and researchers who are keenly interested in the efficient, accurate, and early-stage forecasting of heart disease. Deep Learning Algorithms aid in the prediction of heart disease. The main focus of this paper is to develop a method for predicting heart disease through Modified Rough K means[Formula: see text] (MRK[Formula: see text]) clustering along with the Restricted Boltzmann Machine (RBM). This paper is categorized into two modules: (1) Propose a clustering component based on Modified Rough K-means[Formula: see text]; (2) disease prediction based on RBM. The input Cleveland dataset is clustered using the stochastic probabilistic rough k-means[Formula: see text] clustering technique in the module for clustering. The clustered data is acquired and used in the RBM, and this hybrid structure is then used in the heart disease forecasting module. Throughout the testing procedure, the most valid result is chosen from the clustered test data, and the RBM classifier that correlates to the nearest cluster in the test data is based on the smallest distance or similar parameters. Furthermore, the output value is used to predict heart disease. There are three different types of experiments that are performed: In the first experiment comprises modifying the rough K-means[Formula: see text] clustering algorithm, the second experiment evaluates the classification result, and the third experiment suggests hybrid model representation. When the Hybrid Modified Rough k-means[Formula: see text] - RBM model is compared with any single model, it provides the highest accuracy.
Lisa Gopal, Harbaksh Singh, Panguluri Mounica, N. Mohankumar, Nagendra Panini Challa, and P. Jayaraman
Elsevier BV
Abbaraju Sai Sathwik, Beebi Naseeba, Bheri Saiteja, Nagendra Panini Challa, Nagaraju Jajam, and Pranavesh KumarTalupuri
IEEE
A significant global public health problem that affects many people is depression. Twitter has grown in popularity as a venue for people to express their feelings and experiences, making it a valuable source of information for figuring out the attitudes and trends around depression. We employed Multinomial Naive Bayes, Support Vector Machines, and Logistic Regression as well as three machine learning models to analyse this data. Our goal was to categorise tweets into positive and negative attitudes, find the most frequently used terms and phrases, and investigate how these patterns varied depending on the gender, age, and location of the tweets.
Jinka Chandra Kiran, Beebi Naseeba, Abbaraju Sai Sathwik, Thadikala Prakash Badrinath Reddy, Kokkula Lokesh, Tatigunta Bhavi Teja Reddy, and Nagendra Panini Challa
European Alliance for Innovation n.o.
One kind of cancer that arises from an overabundance of white blood cells produced by the patient's bone marrow and lymph nodes is leukaemia. Since white blood cells are the primary source of immunity, or the body's defence, it is imperative to determine the type of leukocyte cell the patient has leukaemia from as soon as possible. Failure to do so could result in a more serious condition. Haematologists typically use a light microscope to examine the necessary cell traces in order to classify and identify the features of the cell cytoplasm or nucleus in order to diagnose leukaemia in a patient. One form of cancer is leukaemia, which develops when a patient's bone marrow and lymph nodes produce an excessive amount of white blood cells. It is vital to determine the type of leukocyte cell the patient has leukaemia from as soon as possible because postponing diagnosis can worsen the situation. Our white corpuscles are the primary source of immunity, which is the body's defence. In order to define and identify the features found in the cell cytoplasm or nucleus, hematopathologists typically use a light microscope to examine the necessary cell traces in order to diagnose leukaemia in patients.
Jajam Nagaraju, Abbaraju Sai Sathwik, Bheri Saiteja, Nagendra Panini Challa, and Beebi Naseeba
IEEE
The market is filled with cutthroat competition for businesses in the Insurance industry. Customers are the lifeblood of the Insurance industry. They would rather keep the customers they already have rather than try to bring in new ones because bringing in new customers requires a significant investment up front. Because they are losing long-term customers, Insurance operators are seeing their market share in the Insurance industry decrease. Business analysts and customer relationship management (CRM) analysts need to understand and analyse the behavioral patterns of existing customer churn data in order to reduce the amount of customers who leave a company. The hybrid LGBM and XGBoost model, Logistic Regression model, and Random Forest model were the three models that were used in the study to construct a valid and accurate churn prediction model for the Insurance industry. In addition, the results of the empirical evaluation suggest that the Logistic Regression model, which was chosen by the AUC metric, is the most appropriate model to use. The hybrid LGBM and XGBoost model performs well in all aspects of churn prediction as compared with other solo models. These findings provide an understanding of the characteristics and preferences of customers, which enables one to predict customers who are likely to churn and the reasons for churning so that preventative measures can be taken in advance.
Pranavesh Kumar Talupuri, Beebi Naseeba, Nagendra Panini Challa, and Abbaraju Sai Sathwik
IEEE
This research work puts forward a comparative study of four prominent deep learning models - ResNet, InceptionNet, MobileNet and EfficientNet — for the classification and detection of Acute Lymphoblastic Leukemia (ALL) from microscopic single blood cell images. Leukemia, a critical hematological malignancy, demands accurate and swift diagnosis to facilitate effective treatment. The advent of deep learning has revolutionized medical image analysis, enabling automated and efficient disease detection. In this work, we evaluate the performance of ResNet, InceptionNet, MobileNet, and EfficientNet, all of which have demonstrated exceptional capabilities in various computer vision tasks. The proposed study involves the construction of a dataset containing diverse blood cell images, which then undergoes preprocessing and augmentation to ensure model robustness and generalization. Subsequently, the four deep learning architectures are implemented, pretrained on large-scale image datasets, and fine-tuned on the leukemia dataset. Training, validation, and testing phases are conducted under controlled experimental conditions. The results reveal nuanced differences in the performance of ResNet, InceptionNet, MobileNet, and EfficientNet for leukemia detection and classification. The evaluation metrics provide insights into their strengths and limitations, helping guide selection based on specific application requirements. This study clarifies how various architectures impact model performance in the context of medical image analysis.
B Narendra Kumar Rao, R Ranjana, Nagendra Panini Challa, and S. Sreenivasa Chakravarthi
IEEE
Despite the fact that traffic sign segmentation has been publicized for a long time, the majority of past research has centered on traffic signs using graphics. This study aims to propose method for evaluating all sorts of traffic signals based on observations, including in surveillance video streams captured by a vehicle camera, both icon and word signs. Extraction of traffic sign areas of interest (ROIs), exploration and sentiment analysis of ROIs, and post-processing are the three steps of the system. To identify the Regions of interest from each shot of road markings, the most stable fractal dimension regions on grey and calibrated RGB channels are employed. The researchers suggest a multi-convolutional neural network that was trained using a large quantity of data, including fake road markings and pictures extracted from real-time scenarios, Then it refines and emphasizes them based on the most recent their descriptions. Finally, post-processing gathers all of the investors when making an isolating pronouncement. The utility of the suggested technology has been shown through experimental data. This effort aims to improve highest level of quality by flashing drivers about hazards and risks.
Narendra Kumar Rao B, Nagendra Panini Challa, E S Phalguna Krishna, and S. Sreenivasa Chakravarthi
IEEE
To achieve positive detection results, a variety of face landmark methods supported by the convolutional neural network have been developed. The instability landmarks thus emerge in video frames as a result of CNNs, on the other hand, are extremely sensitive to input picture noise. This paper provides a light and effective face landmark identification technology based on a lightweight U-Net model based on semantic segmentation and an Optical Flow (Active) Approach (OFA) for solving the problem of landmark shaking. The OFA employs a quick optical flow approach to determine the motion path of the landmark, as well as a route to increasing landmark maintenance. A lightweight U-Net model is used to predict face landmarks with a reduced size of the model and lower computational. To subsume unstable shaking, the predictable face landmarks are given into the OFA technique as well. Finally, various benchmark datasets are used to produce a comparison of many common methodologies as well as the proposed detection process. A lightweight U-Net model is used to model face landmarks in reduced model size and lower computational. To subsume the unstable shaking, the predicted face landmarks are given into the OFA technique as well. Finally, various benchmark datasets are used to produce a comparison of many common methodologies as well as the proposed detection process.
Beebi Naseeba, Abbaraju Sai Sathwik, Jinka Chandra Kiran, and Nagendra Panini Challa
IEEE
In recent years online shopping has gained a huge boom. With this increase, most of the features of online shopping are developed but some features like negotiating with shopkeepers are not available which is sometimes possible in offline purchasing. In this paper we have proposed a Chatbot to conduct product negotiations. Customers can interact with the Chatbot to receive help obtaining a fair price for a product (s). With such a system, which has an impact on key aspects of online buying, there is a chance that the budget of the customer or the product seller could be compromised. To avoid such situations, we have developed an algorithm in Machine learning which works along with prediction of old available data to provide a product price. Sometimes, price prediction is less accurate because some algorithms are inappropriate for a given dataset or because irrelevant features or properties of the data are employed. Due to the potential financial losses associated with even one incorrect price prediction, Ecommerce businesses do not only rely on price prediction systems. Some models also fail when data scales or some feature is unavailable after time on which model prediction was dependent. Our model's accuracy and dependability are maintained by managing these modifications.
Abbaraju Sai Sathwik, Beebi Naseeba, and Nagendra Panini Challa
IEEE
Heart complications has become very common disease among all the age group persons across the globe. The computation techniques available in the market are based different traditional machine learning models. These models are successful based on the type of datasets they have adapted. In this work two models are combined to form a hybrid model (HRFLM) which is suitable for cardiovascular risk prediction. This model utilized different attributes like stress levels, ECG data and others which are ideal for cardiovascular risk prediction. The stress levels are considered as key attribute which is vital for evaluating this hybrid model. The results show that the proposed model has obtained 98.36% accuracy in predicting the cardiovascular disease when compared with other traditional models.
Nagendra Panini Challa, C. Shanmuganathan, M. Shobana, Ch. Venkata Sasi Deepthi, and N. Bharathiraja
Inderscience Publishers
BeebiNaseeba, S Bhaskar Nikhil, Niranjan S Nair, AsutoshDoppalapudi, Nagendra Panini Challa, and Roopsai Katta
IEEE
Detection and classification of tumors in brain using MRIs is a quite strenuous errand when done manually. Automation of these processes becomes an important task to fulfill. Magnetic Resonance Images (MRI) are widely used for medical imaging as the they provide an excellent image quality for tumors, tissues and other parts inside the body. Early interception or detection of tumors in the brain can play a significant role in treatment. Further, classifying the type of tumor based on their location in the brain can assist surgeons to treat the affected patient efficiently. Deep learning techniques are extensively applied for extraction of features and classification of images into different classes. Identification and classification of medical images like MRI scans is commonly done using CNN or Convolutional Neural Network architectures in deep learning. This paper proposes a transfer learning approach based on different pre-trained CNN architectures such as VGG-19 and ResNet101. A custom hybrid model based on a pre-trained Inception-Resnet-v2 with attributes of both Inception and ResNet architectures is proposed. Comparative analysis of all the models were done with accuracy and AUC as the evaluation metrics. The highest accuracy was procured by the Inception-Resnet-v2 based hybrid model, which came up to be 99.30%.
Nagendra Panini Challa, Beebi Naseeba, Gudigntla Vyshnavi, Thanneeru Priyanka, Nagaraju Jajam, and Kamepalli SL Prasanna
IEEE
Osteoarthritis (OA) disease most caused in elderly people which causes muscle and skeleton system damage. [1] Early prediction of this disease helps to reduce its severity. This paper presents a decent literature review of different prediction models related to OA. Due to the availability of different technical algorithms, the image-based prediction to detect the presence of osteoarthritis is carried out from a dataset available on Kaggle. This work was carried out with different deep learning models like Efficient-V2L, MobileNet, VGG16, and GoogleNet. The findings justify that the Efficient-V2L model has obtained a good accuracy with 93.96% and performs well to predict OA when compared with other existing models.
Nagaraju Jajam, Nagendra Panini Challa, Kamepalli SL Prasanna, and Venkata Sasi Deepthi Ch
Institute of Electrical and Electronics Engineers (IEEE)
Nagendra Panini Challa, K. Reddy Madhavi, B. Naseeba, B. Balaji Bhanu, and Chandragiri Naresh
Springer Nature Switzerland
Kamepalli S L Prasanna, Nagendra Panini Challa, and Jajam. Nagaraju
IEEE
Heart Disease (HD) is one of the most common lifestyle diseases caused by high blood pressure. A lack of stress in the workplace causes an unmanageable rise in blood pressure, which can lead to life-threatening serious circumstances. The early-stage diagnosis of heart disease is essential to saving several people's life. This paper provides an ML knowledge-based forecast model for detecting heart disease. The Q-learning technique from the RL (Reinforcement Learning) framework was used for the Cleveland heart disease dataset in the prediction method. The framework depicts patients with heart disease utilizing 3 main factors: trestbps, Chol, and age by developing the off-premised RL and instructing the learning agent to determine the best rule for the attributes. The proposed RL method accuracy, recall, precision, AUC, and F-measure values were evaluated with cutting-edge methods like KNN and DT. The proposed RL-based heart disease forecasting outperforms the KNN and DT techniques.