Contact centers face persistent challenges in work- force management including unpredictable demand fluctuations, suboptimal agent utilization, and high employee attrition. This paper presents a Cognitive Workforce Orchestration (CWO) framework that integrates reinforcement learning (RL), be- havioral analytics, and real-time demand shaping to address these systemic inefficiencies. The proposed framework employs Proximal Policy Optimization (PPO) to dynamically allocate agents, incorporates multi-dimensional behavioral profiling to personalize assignments, and uses ensemble forecasting mod- els to anticipate demand patterns with 15-minute granularity. Production validation across 500 agents and 10,000+ daily in- teractions demonstrates 34% reduction in customer wait times, 28% improvement in agent utilization, 31% decrease in employee attrition, and 89% forecast accuracy. The framework includes SHAP-based interpretability mechanisms to ensure transparency in automated decision-making, addressing critical concerns in human-centric AI deployment. DOI: https://doi.org/10.17762/ijisae.v13i2s.8038

Diabetic Retinopathy is a leading cause of vision impairment and blindness among diabetic patients worldwide. Early detection and accurate classification of DR severity levels are essential for timely intervention and treatment. This study presents a deep learning-based framework for automated detection and classification of DR using high-resolution fundus images. The proposed approach leverages MobileNetV2 for lightweight feature extraction and employs three ResNet variants such as ResNet-18, ResNet-50, and ResNet-152 for classification of DR into five stages: No DR, Mild, Moderate, Severe, and Proliferative.The fundus images from the publicly available Kaggle DR dataset were pre-processed and segmented using Canny Edge Detection, enabling the model to focus on critical retinal structures such as blood vessels and lesions. Experimental results demonstrate that ResNet-152 achieves the best performance, with a validation accuracy of 90.15%, F1-score of 90.01%, and ROC-AUC of 0.94, outperforming baseline models including InceptionV3 (82.00%) and GoogleNet (87.23%).This work demonstrates the effectiveness of combining edge-based segmentation with transfer learning for DR detection, offering a robust and scalable solution for clinical decision support systems, especially in resource-constrained healthcare settings. DOI: https://doi.org/10.17762/ijisae.v12i23s.7771

Research in the area of project strategy has been limited in project management research. In this paper we present the perspectives of project strategy available in literature. Then we present an approach towards an integrated view of project strategy from the viewpoint of stakeholder theory. Most work in this field has been theoretical or conceptual. Furthermore, as large scale projects bring in complexity, it’s important to have a dynamic view of project strategy. We therefore use system dynamics to move towards an integrated definition of project strategy. After developing the system dynamics model we validate the definition and analyze the results. This is part of a phd research being undertaken at ICFAI University Jharkhand.

Turbomachinery plays a crucial role in various industrial applications, including power generation, aviation, and manufacturing. Understanding and optimizing fluid dynamics within these machines is essential for enhancing performance, efficiency, and reliability. This study focuses on the fluid dynamics of turbomachinery, exploring advanced optimization techniques and conducting comprehensive performance analysis. By integrating computational fluid dynamics (CFD) simulations, genetic algorithms, and machine learning, this research aims to develop innovative solutions for improving turbomachinery efficiency. The findings are expected to provide valuable insights for engineers and designers, contributing to advancements in turbomachinery technology and applications. The research encompasses a detailed examination of different types of turbomachinery, including axial, radial, and mixed flow machines. It also addresses the challenges associated with turbulence modeling, mesh generation, and solver validation. Through a combination of theoretical analysis, computational methods, and experimental validation, this study seeks to identify optimal design parameters and performance indicators. The ultimate goal is to enhance the operational efficiency and lifespan of turbomachinery, thereby reducing energy consumption and operational costs in various industries.

This research explores the influence of Generative Artificial Intelligence (AI) on the workforce by analyzing job roles, skill requirements, and employment trends. A mixed-method approach is utilized, combining Insights collected through interview sessions with industry professionals and quantitative findings obtained through surveys conducted among employees in the IT, manufacturing, and healthcare industries. Secondary data is gathered from academic literature, industry reports, and case studies provide additional insights. The findings indicate that, although AI has the potential to replace jobs involving routine tasks, it also generates new opportunities in areas such as AI management and ethical governance A significant skills gap exists, highlighting the need for reskilling and upskilling initiatives. The research emphasizes the importance of adapting to these changes through proactive strategies to mitigate job displacement and address skills shortages. This paper contributes to understanding the transformative effects of Generative AI on the workforce, offering recommendations for building a resilient, future-ready labor market. DOI: https://doi.org/10.17762/ijisae.v12i23s.8102

Hospital buildings are no longer just buildings with fixed structures but have transformed into smart entities capable of interacting with the demands of the internal and external environment and responding quickly to all changes. This is thanks to the accelerated use of advanced technologies in smart materials and smart systems. However, we find another challenge, which is the lack of a clear scientific methodology in the process of selecting the criteria for smart materials and smart systems in hospital buildings. This leads to the adoption of unsuitable engineering solutions and increased costs without achieving a safe, comfortable, and healthy environment for patients and staff. This study aims to propose a methodology for selecting the criteria for smart materials and smart systems in hospital buildings. It employs a descriptive-analytical approach to establish the theoretical framework, a comparative approach to analyze case studies of leading hospitals, and a deductive approach to formulate the proposed methodology. The study arrives at a five-stage methodology: (1) Assessment and Diagnosis, (2) Criteria Specification, (3) Selection and Evaluation, (4) Application and Integration, and (5) Evaluation and Feedback. The results also revealed that implementing this methodology contributes to creating a healthy and safe indoor environment for patients, effectively improving energy efficiency and reducing long-term operating costs, while also increasing patient satisfaction and recovery rates. This study recommends that this approach be adopted as a basis for developing national hospital design codes. DOI: https://doi.org/10.17762/ijisae.v12i14s.8087

The system uses image and video segmentation to improve accuracy and loss metrics. The semantic gap between CBIR content and visual qualities is addressed in the study. Hybrid feature extraction strategies may help content-based retrieval systems close this gap. This study presents a hybrid feature extraction approach to Content-Based Image and Video Retrieval (CBIVR). The study examines video segmentation as well as retrieval to improve video searches and give meaningful abstractions. The study uses keyframes to automatically extract important frames from video diaries. An effective segmentation technique removes the backdrop from input data from the HMDB along with CIFAR-10 datasets. Feature selection-based optimization reduces input variables, improving model performance and computing effort. Using rank-listed numerical properties of phenomena, a hybrid feature vector conditions and machine learning model create informed estimates. For better training data analysis, the study uses error-learning ResNets, an artificial neural network having hundreds of layers that have feed-forward connections. Phase retrieval utilizing diffracted intensity distribution recreates the sample's object plane phase shift. The loss function evaluates the author's machine learning system. Retraining the system with updated authority with pre-trained models in post-processing optimizes video retrieval. The finding opens the door to more sophisticated multimedia material retrieval applications in numerous sectors. The system obtains higher accuracy and loss metrics by utilizing image and video segmentation. Impressive performance is shown by the picture segmentation model in training, with a loss of 0.1466 and an accuracy of 94%, while competitive results are maintained on the test set, with a loss of 0.67 and an accuracy of 82.46%. The model achieves a video loss of 0.39 and a video accuracy of 90% while being trained for video segmentation. These encouraging findings demonstrate the promise of the hybrid approach in improving content-based retrieval systems, opening the door for further investigation into cutting-edge segmentation algorithms, novel training datasets, and cutting-edge deep learning architectures to revolutionize multimedia content retrieval in a wide range of contexts. DOI: https://doi.org/10.17762/ijisae.v12i4.6832

Speech Emotion Recognition (SER) has emerged as a critical area in human-computer interaction, aiming to enable systems to recognize and respond to human emotions expressed through speech. This research focuses on utilizing deep learning techniques to advance the performance of SER systems, particularly in noisy and variable conditions. We present a comprehensive approach, starting with the preparation of audio datasets, followed by the application of various augmentation techniques such as Gaussian noise, pitch shifting, time stretching, and time shifting, aimed at simulating real-world distortions. These augmentations, implemented using the audiomentations library, enhance the robustness of machine learning models by diversifying the training data. We further explore the efficacy of deep learning models, particularly convolutional neural networks (CNNs) and recurrent neural networks (RNNs), in recognizing emotional states across different speech patterns. Initial results demonstrate significant improvements in model generalization, particularly in handling diverse audio conditions. This study contributes to the growing body of work on SER by improving model robustness through data augmentation, with promising results that lay the groundwork for more adaptive and emotion-aware systems. DOI: https://doi.org/10.17762/ijisae.v12i23s.7219

This paper introduces a new Speech and Speaker Recognition System that utilises a Deep Feature Extraction method with a Heuristic Adopted Transformer Bidirectional Long Short Term Memory (LSTM) and Attention Mechanism. The aim of our approach is to address the difficulties associated with effectively recognising speech and identifying speakers in complex audio data. Our system utilises deep learning methods like bidirectional LSTM and attention mechanism in a Transformer framework to extract temporal and long-range relationships in voice input, improving identification accuracy. We compare the proposed model with existing methods like the flow detection algorithm and reptile search algorithm. The experimental findings reveal that our system surpasses existing algorithms in accuracy, precision, recall, and F1-score, demonstrating its value in Speech and speaker recognition tasks. Our research enhances the area of deep learning-based audio analysis and provides a reliable solution for real-world applications that need precise voice and speaker recognition. DOI: https://doi.org/10.17762/ijisae.v12i21s.6121

The various changes in cyber threats have made the old security systems to be more ineffective in reducing advanced attacks. Since the adversaries adapt, evade, and employ artificial intelligence (AI) and machine learning (ML) to establish adaptive and evasive methods, intelligent self-achieving defense is urgent. This article discusses the incorporation of AI adaptation frameworks into cybersecurity systems to battle the future-generation threats. Exploiting a comprehensive overview of existing ML research and practical deployments, the paper points to the superiority of reinforcement learning, adversarial ML, federated learning, and deep neural networks in building resilience against zero-day attacks, malware, phishing, and advanced persistent threats. An adaptation of this conceptual framework to the domain of adaptive AI defenses is advanced, with modeling of how continual model learning may enable the defender to close the gap between static defensive strategies and changing threats. In evidence-based case performance comparisons, adaptive AI-based systems can do better job in detecting with high accuracies, low false positives and scalability compared to conventional technologies. Concerns about adversarial manipulation, ethical issues, and computational requirements, as well as the provision of future paths, which consist of explainable AI, Policies, and quantum-computing based AI integration are other issues that are discussed in the discussion. This paper can therefore confidently draw adaptive AI defenses as one of the fundamental capabilities of safeguarding online infrastructures in view of the ever-evolving cybersecurity environment. DOI: https://doi.org/10.17762/ijisae.v12i23s.7826