Ajay Bandi

Dr. Ajay Bandi

School of Computer Science and Information Systems, Northwest Missouri State University, Maryville, Illinois, USA
orcid
Professor of Computer Science

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 July 2023 in Future Internet
Verified
Journal Article
Open access
PDF file
Ajay BandiAjay Bandi
Ajay Bandi
PAPYDI VENKATA SATYA RAMESH ADAPA
PYDI VENKATA SATYA RAMESH ADAPA
YKYudu Eswar Vinay Pratap Kumar Kuchi
Yudu Eswar Vinay Pratap Kumar Kuchi
Generative artificial intelligence (AI) has emerged as a powerful technology with numerous applications in various domains. There is a need to identify the requirements and evaluation metrics for generative AI models designed for specific tasks. The purpose of the research aims to investigate the fundamental aspects of generative AI systems, including their requirements, models, input–output formats, and evaluation metrics. The study addresses key research questions and presents comprehensive insights to guide researchers, developers, and practitioners in the field. Firstly, the requirements necessary for implementing generative AI systems are examined and categorized into three distinct categories: hardware, software, and user experience. Furthermore, the study explores the different types of generative AI models described in the literature by presenting a taxonomy based on architectural characteristics, such as variational autoencoders (VAEs), generative adversarial networks (GANs), diffusion models, transformers, language models, normalizing flow models, and hybrid models. A comprehensive classification of input and output formats used in generative AI systems is also provided. Moreover, the research proposes a classification system based on output types and discusses commonly used evaluation metrics in generative AI. The findings contribute to advancements in the field, enabling researchers, developers, and practitioners to effectively implement and evaluate generative AI models for various applications. The significance of the research lies in understanding that generative AI system requirements are crucial for effective planning, design, and optimal performance. A taxonomy of models aids in selecting suitable options and driving advancements. Classifying input–output formats enables leveraging diverse formats for customized systems, while evaluation metrics establish standardized methods to assess model quality and performance.

4 September 2025 in Future Internet
Verified
Journal Article
Open access
PDF file
Ajay BandiAjay Bandi
Ajay Bandi
BKBhavani Kongari
Bhavani Kongari
RNRoshini Naguru
Roshini Naguru
SPSahitya Pasnoor
Sahitya Pasnoor
SVSri Vidya Vilipala
Sri Vidya Vilipala
Agentic AI systems are a recently emerged and important approach that goes beyond traditional AI, generative AI, and autonomous systems by focusing on autonomy, adaptability, and goal-driven reasoning. This study provides a clear review of agentic AI systems by bringing together their definitions, frameworks, and architectures, and by comparing them with related areas like generative AI, autonomic computing, and multi-agent systems. To do this, we reviewed 143 primary studies on current LLM-based and non-LLM-driven agentic systems and examined how they support planning, memory, reflection, and goal pursuit. Furthermore, we classified architectural models, input–output mechanisms, and applications based on their task domains where agentic AI is applied, supported using tabular summaries that highlight real-world case studies. Evaluation metrics were classified as qualitative and quantitative measures, along with available testing methods of agentic AI systems to check the system’s performance and reliability. This study also highlights the main challenges and limitations of agentic AI, covering technical, architectural, coordination, ethical, and security issues. We organized the conceptual foundations, available tools, architectures, and evaluation metrics in this research, which defines a structured foundation for understanding and advancing agentic AI. These findings aim to help researchers and developers build better, clearer, and more adaptable systems that support responsible deployment in different domains.

28 September 2019 in EPiC Series in Computing
Verified
Conference Paper
Open access
PDF file
Ajay BandiAjay Bandi
Ajay Bandi
AFAziz Fellah
Aziz Fellah
The usage of social media is rapidly increasing day by day. The impact of societal changes is bending towards the peoples’ opinions shared on social media. Twitter has re- ceived much attention because of its real-time nature. We investigate recent social changes in MeToo movement by developing Socio-Analyzer. We used our four-phase approach to implement Socio-Analyzer. A total of 393,869 static and stream data is collected from the data world website and analyzed using a classifier. The classifier identify and categorize the data into three categories (positive, neutral, and negative). Our results showed that the maximum peoples’ opinion is neutral. The next higher number of peoples’ opinion is contrary and compared the results with TextBlob. We validate the 765 tweets of weather data and generalize the results to MeToo data. The precision values of Socio-Analyzer and TextBlob are 70.74% and 72.92%, respectively, when considered neutral tweets as positive.

16 October 2023 in Education and Information Technologies
Verified
Journal Article
Open access
PDF file
WYWilson Libardo Pantoja Yépez
Wilson Libardo Pantoja Yépez
JHJulio Ariel Hurtado
Julio Ariel Hurtado
Ajay BandiAjay Bandi
Ajay Bandi
AKArvind W. Kiwelekar
Arvind W. Kiwelekar
The ability to define, evaluate, and implement software architectures is a fundamental skill for software engineers. However, teaching software architecture can be challenging as it requires students to be involved in real-context projects with high degrees of complexity. This involves making trade-off decisions among several quality attributes. Furthermore, the academic perception of software architecture differs from the industrial viewpoint. To address this issue, a study was conducted to identify and analyze the strategies, challenges, and course experiences used for teaching software architectures. The study analyzed 56 articles reporting on teaching experiences focused specifically on software architectures or focused on software engineering in general but discussing software architecture. The main contributions of this work include identifying strategies used in educating software architecture students aligned with the needs of the software industry. These strategies include short design projects, large development projects, and projects with actual clients. Additionally, the study compared curriculum contents in software development and architecture courses and identified recurring topics such as architecture patterns, quality attributes, and architectural views. This study also recognizes the set of skills that students of software architecture should develop during training, such as leadership and negotiation. The challenges in software architecture training were discussed, such as instructors’ lack of experience in actual projects, the abstract and fuzzy nature of software architectures, and the difficulty of involving clients and industry experts. Evaluation methods commonly used in training software architects, such as surveys, pre-test/post-test, and quality metrics on architectural artifacts, were identified and described. Overall, this study guides researchers and educators in improving their software architecture courses by incorporating strategies reported by the literature review. These strategies can bring architecture courses closer to the needs and conditions of the software industry.

19 October 2024
Verified
Book Chapter
Closed access
PDF file
Ajay BandiAjay Bandi
Ajay Bandi
JBJameer Babu
Jameer Babu
RZRuida Zeng
Ruida Zeng
SMSai Ram Muthyala
Sai Ram Muthyala

22 December 2024
Verified
Book Chapter
Closed access
PDF file
Ajay BandiAjay Bandi
Ajay Bandi
RZRuida Zeng
Ruida Zeng