KKKhaja Baseer Kamalapuram

Khaja Baseer Kamalapuram

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Khaja Baseer Kamalapuram has a total of 24 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • AI, IoT, and Cognitive Computing for Mental Health Enhancement and Object Detection

    by K. K. Baseer, Nalavala Ramanjaneya Reddy, T. Satyendra Kumar, Harishchander Anandaram, Alavikunhu Panthakkan

    This chapter explores the potential of AI, IoT, and cognitive computing in improving mental health care and object detection technologies. AI-driven cognitive computing and IoT-enabled devices could enhance personalized, efficient, and real-time mental health solutions. Cognitive computing models will be able to analyze the huge streams of data coming from wearables, for instance, and enable early warnings of mental health issues. Monitoring behavioral patterns will be provided through cognitive computing models, with proactive interventions delivered based on early warning signs. Object detection powered by cognitive computing will offer the capability to identify with precision various environmental factors that may exert effects on one's mental well-being, including crowding, noise, or temperature changes. The integration of these technologies will transform mental health care from a reactive service to a preventive and data-driven approach, thereby enhancing patient outcomes.

  • AI-Driven Threat Detection in Cloud Environments

    by V. Jyothsna, E. Sandhya, Khaja Baseer Kamalapuram, P. Bhasha

    In cloud computing, integrating artificial intelligence (AI) is crucial for enhancing cybersecurity. As organizations move to the cloud, they encounter advanced threats that traditional security measures often miss. AI, through machine learning and deep learning, significantly improves threat detection and response times. This chapter discusses AI-based systems like anomaly detection, predictive analytics, and automated responses, highlighting their effectiveness in real-world scenarios. It also addresses challenges such as data privacy, quality training data, and adversarial attacks. Future trends are explored, emphasizing AI's evolution to counter new threats by adapting to emerging attack vectors and continuously learning from data. This chapter provides valuable insights for researchers, practitioners, and decision-makers to enhance cybersecurity strategies with AI in cloud environments, helping them better prepare for the evolving threat landscape.


  • Machine Learning Applications in Predictive Pest Modeling for Developing Pest-Resistant Crop Varieties

    by K. K. Baseer, M. Jahir Pasha, Gandikota Ramu, Bhasha Pydala, D. William Albert

    This chapter explores the use of machine learning tools in developing models to predict pest attacks and develop resistant crops using large data sets for reliable predictions. Decision trees and neural networks aid in pest prediction by creating resistant crop varieties, reducing chemical usage, and enhancing farming sustainability. The study examines issues in machine learning-driven pest prediction, including data quality, ease of understanding, and expansion, and proposes methods to enhance learning from data and combine multiple methods. This section discusses the use of machine learning tools in developing models to predict pest invasions and develop crops that can resist pests in farming. The study addresses issues like data quality, interpretation ease, and growth potential, suggesting methods to improve data learning and merge learning styles. Future research should refine these models and develop pest-resistant crop varieties.


  • AI-Enabled Industrial Applications

    by Khaja Baseer Kamalapuram, Maria Joseph B. Joseph, Abhishek, Jahir Pasha Jahir

    The project's objective is to provide an explanation of AI-enabled industrial applications and how they can benefit businesses. One of the primary factors that contribute to a movement closer to the fourth industrial revolution is AI. Automation has the potential to enhance economic growth worldwide by streamlining tasks and improving human performance. Additionally, it can aid in decision-making and facilitate interconnected supply chains by providing real-time data from various sources, allowing for total optimization and transparency that might not be possible with the most effective methods currently in use. On a larger scale, AI may completely replace human workers. Artificial intelligence can be used to link the real and virtual worlds in a loop. In this project overview, the authors talk about how AI and human workers can work together to automate a wide range of tasks and the challenges we'll face while developing and investing in these solutions. Request access from your librarian to read this chapter's full text.

  • Open Access

    Investigating Agile Adaptation for Project Development

    by Rajesh H. Kulkarni, P. Padmanabham, Manasi Harshe, K.K. Baseer, Pallavi Patil

    Agile methodologies adaptation in software companies is an accepted norm.Rapid application development and efficient deliverables being the premise. The changing business needs, cost effectiveness and timely delivery are catered to by agile methods. Different software development models are in the literature and also are being used by the industry. Few companies have adopted agile, few are gearing up for and few are in transition. We investigated agile presence in a software company.Project management is an evolving art with innovative methods being added up.The aim of this paper is to tease about project management challenges, agile, agile transition in companies and a comparison of conventional software engineering practices with agile process model.This paper takes stock of the current status of quality in software projects and to add on quality process improvement strategies. The results presented here are after a qualitative interview study with one cross function team using streamline development framework in agile development.


  • FPYM: development and application of a fuzzy-based Poka-Yoke model for the improvement of software performance

    by K.K. Baseer, A. Rama Mohan Reddy, C. Shoba Bindu

    Improving qualities of software like reliability, availability, maintainability, cost, time and energy is key role in software development. These qualities are more dependable on the requirements, design, development, testing and deployment. In order to improve the software qualities on these cycles, avoiding mistakes or making alarm for each activity may be suitable choice. This is effectively studied using Poka-Yoke model which is applied in various production, manufacturing and software industries. Due to advantages of Poka-Yoke model, we have developed fuzzy-based Poka-Yoke model for small-scale software companies. This work aims to study the workflow and activities of two small scale companies involved in software development. In the case study, software performance attributes are defined and performance is analysed using four metrics called, UGAM, IOI, SM and SSM. The collected data is then extensively analysed to identify: the individual characteristics of companies, correlation behaviour of companies which they implemented the proposed model, improvement analysis over the period of time with the proposed model and forecasting the software performance for next products.

  • Quantitative Validation of Poka-Yoke Approach for HQLS Using Regression Coefficient and Analysis of Variance

    by K.K. Baseer, A. Rama Mohan Reddy, C. Shoba Bindu

    As the requirement of the user increases, complexity in the development of software is also increases. It is a great challenge in software engineering to understand, measure, manage, control, and even to low the software complexity and also increases quality. To improve performance of software, web sites and services is a holy grail of software industry. A new approach for implementation of Poka-Yoke method in software performance engineering is proposed. Poka-Yoke is a mistake proofing technique used in product design. In previous work, proposed a new framework for High Quality in Large Scale (HQLS) software development. Now, in this paper, quantitatively validating the Poka-Yoke approach for a product called Personal Secretary (PS). The quantitative of PS was evaluated using Regression Coefficients and Analysis of Variance (ANOVA). Regression analysis showed that Poka-Yoke has a greater impact on software quality that uses the current state of the art software development models. Improved UGAM scores also showed linearity and justified Poka-Yoke implementation. Our findings recommend usage of techniques for mistake proofing for overall software performance. The aim is to reduce errors in the software development process.


  • Open Access

    A Naive Based Approach for Mapping Two ADL Models

    by K. K. Baseer

    In software engineering, we have identified and described the model correspondence problem. To Describe system architecture and artifacts uses models and diagrams. Models contains series of versions. To understand how versions correspondence are difficult. So, we designed a framework based on Search and Ammolite algorithms, which can cardinally finds the correspondence software models. Models are represented as graphs whose nodes have attributes (name, edge, label, connections). For a given diagram pair, it performs different individual matches such as pair-wise match, Split-Merge Match and Drop match and then combine all matches together to design a ADL model. Every ADL Model has its correspondence score for rating quality candidates. To find best Correspondence among the given ADL models uses Search and Ammolite Algorithms.