International Journal of Systematic Innovation

Innovative solutions for CNN performance: A TRIZ-based reverse engineering approach

2025-01-02T10:56:18+08:00

Convolutional Neural Networks (CNNs) are widely used in computer vision for tasks like image classification and detection. These models work well when the number of image classes is small, but as the number of classes increases, accuracy tends to drop due to overfitting. There are several methods to address this issue, such as data augmentation, preprocessing, class weighting, transfer learning, and adjusting technical parameters. This study introduces a novel approach by utilizing the TRIZ methodology to systematically analyze and enhance these existing methods. Using reverse engineering, we deconstructed current solutions and aligned them with TRIZ principles to propose more innovative and effective approaches for improving CNN performance. The results show that TRIZ provides a structured and creative framework for solving accuracy decline issues in CNN models, offering potential for broader applications in other machine learning architectures.

Keywords: Image classification, CNN, Reverse engineering, TRIZ

A Maya Calendar-Inspired Cyclical TRIZ Approach: Enhancing Systematic Innovation and Long-Term Problem Solving

2025-02-04T08:43:08+08:00

This paper introduces the Maya Calendar-Inspired Cyclical TRIZ Model, a new approach to systematic innovation that integrated the seven TRIZ pillars into short-term (Tzolk’in), mid-term (Haab), and long-term (Long Count) cycles. Unlike traditional linear models, this cyclical model enables continuous adaptation and sustainable innovation. The short-term cycle achieves rapid improvements, the mid-term cycle resolves deeper contradictions, and the long term-cycle drives strategic evolution. Tested through a coffee machine design, the model demonstrates a self-sustaining loop, where each cycle builds on the previous one for ongoing refinement. This model addresses limitations of existing approaches by combining rapid problem-solving with long-term adaptability, making it a versatile tool for industries aiming for both short-term success and long-term resilience.

Hybrid Intelligence Model for Traffic Management in Intelli-gent Transportation System

2024-02-27T02:22:50+08:00

A typical traffic environment in Intelligent Transportation System (ITS) involves various infrastructural units that generates a vast amount of sophisticated traffic data. Such form of complex data is quite challenging to analyzed and hence poses a potential issue towards designing an effective and responsive traffic management system. Therefore, this paper develops an analytical modelling approach where the potential of Artificial Intelligence (AI) and Computational Intelligence (CI) has been harnessed. The scheme presents a simplified predictive approach that is meant for mitigating the current issues towards intelligent traffic management. The simulated outcome of study showcase that proposed scheme offers significant advantage in its predictive performance in ITS.

New Product Development (NPD) Process: Conceptual Framework for Automobile Industries

2025-04-07T13:41:34+08:00

India is emerging as a key destination for global automobile makers, prompting businesses to improve their abilities in product design and development to grow within the technology-focused automobile sector. Managing new product development (NPD) poses significant challenges within the dynamics to remain competitive. A well-defined and proven NPD process in automobile results in high-quality, cost-effective, and timely product delivery to the market. Various frameworks has been proposed in the literature and limitations highlight the need for more flexible, integrated, and adaptive NPD model. Utilizing Cooper's highly efficient Stage-Gate framework, this research paper proposes new NPD process framework to enhance the performance of automobile industries. Based on the limitations of existing stages and gates used and survey among the NPD professionals, detailed activites of the stages and associated gates has been presented.

Handwriting match and AI content Detection (HMAC)

2025-02-25T14:20:43+08:00

Machine-generated text presents a potential threat not only to the public sphere, but also to education, where the authenticity of genuine students is compromised by the presence of convincing, synthetic text. There are also concerns about the spread of academic misconduct, particularly direct replication among students. In response to these challenges, this paper introduces the Handwriting Match and AI Content Detection System (HMAC). HMAC utilizes Optical Character Recognition (OCR) mechanisms to convert handwritten and typed content from a single page pdf into machine-readable text, thus enabling further analysis. Drawing on recent advances in natural language understanding, HMAC aims to preserve the educational value of assignments by effectively detecting AI generated content. Additionally, HMAC has a strong plagiarism detection system that uses a comparative analysis of student submissions in a particular academic field. This paper describes HMAC's architecture, methodology, and results, emphasizing its key contributions: improved handwritten content extraction with OCR and improved identification of AI-generated content. The study addresses the research question of how HMAC improves the identification of AI-generated content and academic integrity when compared to other methodologies.

Enhancing Healthcare Efficiency with AI: Benefits, Challenges, and the Future of Clinical Practice

2025-02-24T14:16:43+08:00

This study explores the integration of Artificial Intelligence (AI) tools in healthcare, focusing on their impact on cognitive workload, decision-making, and professional development. The findings indicate that AI tools significantly reduce cognitive load, enabling healthcare professionals to focus on higher-order tasks such as critical thinking and complex problem-solving. A majority of participants reported that AI positively influences their professional development, enhancing cognitive functions and empowering them in clinical decision-making. However, concerns were raised about AI’s potential negative effects on hands-on clinical skills, particularly in areas like physical examinations and surgeries, which require manual expertise. These concerns align with the theory of "skill degradation," where over-reliance on AI may hinder the development of essential practical skills. Additionally, the study revealed that healthcare workers feared AI could reduce their autonomy in decision-making, emphasizing the need for maintaining human oversight in AI-driven processes. The findings suggest that a balanced approach to AI adoption is essential, where AI complements human expertise rather than replacing it. Training programs should be developed to ensure that healthcare professionals retain core competencies while utilizing AI effectively. Overall, while AI has the potential to improve healthcare delivery by enhancing efficiency and supporting decision-making, its integration must be managed carefully to preserve the essential role of healthcare professionals in providing high-quality care.

Ensemble Transfer Learning for Enhanced Brain Tumor Diagnosis: A new Approach for early detection

2025-03-28T15:17:30+08:00

Brain tumors represent one of the most extreme and complex types of most cancers, requiring unique analysis for powerful remedy and management. Accurate and early identification of brain tumors can greatly enhance patient consequences and decrease mortality. Nowadays deep learning aids the medical field a lot by diagnosing Magnetic Resonance Imaging (MRI) images in Brain tumors. The potential of deep transfer learning architectures to improve brain tumor diagnosis accuracy is explored in this work. This study evaluated three different Convolutional Neural Network (CNN) architectures: AlexNet, VGG16, and ResNet18 as an ensemble model. The gathered dataset was used to train and test the models. In order to increase the dataset's balance and the models' performance, data was collected from: Rizgary Hospital (Erbil), and Hiwa Hospital (slemani). These image enhancement techniques were applied to two categories: normal and abnormal brain tumors. Several brain tumor datasets are available online for the development of Computer Aided Diagnosis systems (CADs), but not KRI Hospital cases, which pose challenges in their classification through deep learning models. This study was implemented by python programming language. Out of the three models used, ResNet had the highest accuracy of 98.66%, VGG16 had an accuracy of 97.8% and AlexNet had an accuracy rate of 97.666%. I also used ensemble between the three models, ensemble predictions of all the models together, majority voting was (98.33%) and the weighting voting was (98.33%).

Sentiment of Largest State, First Mover, And Largest Private Banks Digital Performance In Indonesia : Strategic Perspective

2025-03-28T15:12:47+08:00

Digitalization plays an essential role in improving company performance, including banking. Understanding consumer sensitivity in digital banking applications is essential for strategic decisions. This research aims to analyze the user's sensitivity of the Largest State, First Mover, and Largest Private Bank digital application in Indonesia, using the Naïve Bayes technique through Python. The data was taken from the Google Playstore, a software provider application for computer/laptop and mobile users, with a time range of 3 months from April 2023 until July 2023. The applications as the subject were XAA because it is owned by the largest state-owned bank, namely Bank XA, XBB because it belongs to the first mover for digital banks, and XCC which is an application from the largest privately owned bank, namely Bank XC. The results reveal that most digital bank application users in Indonesia perceive that existing digital bank applications in Indonesia have yet to be able to meet their expectations. This is explained by the higher average negative value of their feedback answers than the existing positive value. Furthermore, this conclusion was revealed from the finding that XAA and XCC, which still had a positive score, had a higher negative score. Meanwhile, the XBB application, which is a first mover, was found to have a positive value higher than a negative one. We clearly compare the three applications divided into positive and negative categories and discuss the existing negative comments using a Digital Business Capabilities (DBC) perspective.