Transactions on Engineering and Computing Sciences

AttentionLipi: A Hybrid CNN–BiLSTM (CRNN) Framework with CTC for Kannada Palm Leaf Manuscript Recognition

2026-01-07T10:44:58+00:00

Character recognition in historical Kannada palm leaf manuscripts presents significant challenges due to degraded document quality, non-uniform character spacing, and the absence of publicly available annotated datasets. In this paper, we present AttentionLipi, an end-to-end Convolutional Recurrent Neural Network (CRNN) architecture combined with Connectionist Temporal Classification (CTC) loss for recognizing Kannada characters from palm leaf manuscripts without explicit character segmentation. The CRNN architecture consists of seven convolutional layers (64–512 channels) with batch normalization and ReLU activation for hierarchical feature extraction, followed by two bidirectional LSTM layers with 256 hidden units each for temporal sequence modeling, and CTC decoding for transcription. Trained on a custom dataset of 3,500 Kannada character samples including vowels, consonants, and compound characters manually extracted from 25 historical palm leaf manuscripts through a 280-hour annotation process, the model achieves 72.6% character recognition accuracy despite severe data constraints and document degradation. The results demonstrate the feasibility of applying deep learning to low-resource manuscript digitization tasks and provide a baseline for scalable OCR systems for Kannada heritage archiving.

Enhancing Engineering Audit Practices in Higher Education

2025-12-30T06:55:06+00:00

Engineering auditing in colleges and universities serves as a core supervisory mechanism for standardizing campus construction processes and enhancing the utilization efficiency of fiscal funds. It plays a pivotal role in optimizing the allocation of higher education resources. Using the annual operational practices of the engineering auditing department at a specific university as a case study, this paper systematically examines the implementation framework and practical outcomes of engineering auditing in higher education institutions. It conducts an in-depth analysis of the core challenges and their underlying causes within audit operations and proposes improvement pathways, such as deepening collaborative mechanisms and strengthening technological empowerment. The aim is to provide practical references for the standardized and scientific development of engineering auditing in colleges and universities.

Comparative Review of Machine Learning Models for Sunspot Number Prediction

2026-01-19T17:43:09+00:00

Accurate prediction of sunspot numbers is essential for understanding solar activity and mitigating the adverse effects of space weather on technological infrastructure. With the limitations of traditional statistical methods, recent years have witnessed a surge in the application of machine learning (ML) models, particularly deep learning architectures, to sunspot time series forecasting. This review presents a comprehensive comparative analysis of major ML models utilised in the prediction of sunspot numbers, focusing on recurrent neural networks (RNN), long short-term memory (LSTM) networks, gated recurrent unit (GRU) models, and hybrid neural network approaches. The article synthesises findings from state-of-the-art literature, summarising the methodological advances, dataset preparation strategies, and evaluation metrics commonly employed in this field. A critical assessment of model performance, based on accuracy, robustness, and operational feasibility, highlights the superior capabilities of LSTM and GRU architectures for long-term and multi-step forecasting tasks. By systematically evaluating methodological advancements and benchmarking results from recent studies, this article highlights the strengths, limitations, and emerging trends in solar forecasting approaches, aiming to guide future research toward robust, interpretable, and operationally feasible sunspot prediction.

Quantum Foundations and Technological Futures: A Critical Analysis of Interpretative Frameworks and Socio-Economic Projections

2026-01-13T19:12:47+00:00

The proliferating discourse surrounding quantum mechanics (QM) increasingly bridges foundational physics, technological speculation, and spiritual or philosophical narratives. Yet, the rhetorical strategies and epistemic warrants used to construct these bridges remain critically unexamined. This study performs a critical discourse analysis to identify and evaluate the narrative frameworks used to connect standard interpretations of QM with extra-scientific domains of meaning, particularly spiritual creation narratives. We employ a structured qualitative content analysis of three corpora: (1) popular science texts explicating QM (e.g., Rovelli, Greene), (2) contemporary quantum technology market reports and roadmaps (2018-2025), and (3) exemplary spiritual creation texts. Using a codebook developed from science communication and sociology of expectation frameworks, we analyze rhetorical devices, appeals to authority, and argumentative structures. Our analysis reveals three dominant rhetorical bridging strategies: (1) the "miraculous analogy," leveraging quantum weirdness to legitimize spiritual wonder; (2) the "teleological projection," wherein quantum computing's potential is presented as an inevitable, purpose-driven evolution; and (3) the "selective complementarity," which isolates specific QM concepts (e.g., observer effect) while ignoring their technical context to create false parallels with philosophical idealism. While interdisciplinary dialogue is valuable, our findings demonstrate that current popular discourse often relies on epistemically problematic analogies that risk misunderstanding both science and spirituality. We propose criteria for more rigorous, conceptually sound transdisciplinary engagement.

Mӧssbauer Spectroscopy and X-ray Powder Diffraction Study on the Milled Gallium Oxide-hematite Nanoparticles

2026-01-07T23:42:11+00:00

Samples in the milled gallium oxide-hematite nanoparticles system were synthesized by mechanochemical activation using ball milling times of 0, 2, 4, 8, and 12 hours. The specimens were characterized using Mӧssbauer spectroscopy and X-ray powder diffraction (XRPD). The Mӧssbauer spectra were deconvoluted by least squares fitting using 2 sextets and a doublet. Lorentzian lineshapes were used in the assumption of thin absorbers approximation. The sextets were assigned to hematite and gallium-doped hematite. The relative area of doublet that represented gallium iron perovskite (gallium orthoferrite), increased with the milling time. The hyperfine magnetic fields decreased as a function of the substitution level according to the model of local atomic environment. The particle size was determined using the Scherrer method for XRPD. The crystallite dimensions were found to be in the tens of nanometers range. These structural and magnetic properties of the milled gallium oxide-hematite nanoparticles system depend on the ball milling times and molar concentrations.

Analytical Modeling of the Dynamics of Random Processes During Combat Use of a Military Tetrasystem

2025-12-31T13:56:27+00:00

A military system consisting of four autonomous subsystems (a tetrasystem) is considered: air, land, sea, and drone. During combat, each subsystem is subject to a stream of random events involving losses and restorations. The dynamics of random processes is studied using a continuous-time Markov chain with sixteen asymmetric possible states. The corresponding mathematical model of the random processes is constructed in the form of sixteenth-order Kolmogorov differential equations. Formulas are found for the sixteen roots of the characteristic Kolmogorov equation, expressed in terms of the intensities of the tetrasystem's loss and restoration flows. The analytical solution to the Kolmogorov differential equations for the tetrasystem is represented in the form of ordered matrices and sixteenth-order determinants, which allows for a compact description of a large volume of initial data, overcomes limitations associated with the problem's dimensionality, and ensures adaptability to computer technologies, including the problem of verification.

Securing the AI Supply Chain: A Framework for AI Software Bills of Materials and Model Provenance Assurance

2026-01-13T19:16:28+00:00

The proliferation of artificial intelligence (AI) systems has exposed critical vulnerabilities in their supply chains, encompassing models, datasets, training pipelines, and dependencies, which introduce risks such as data poisoning, model theft, and adversarial attacks. These threats extend beyond traditional software supply chain concerns, necessitating specialized security measures to ensure trustworthiness in AI deployments across critical sectors. Despite advancements in software bills of materials (SBOMs) driven by initiatives like U.S. Executive Order 14028, existing frameworks inadequately address AI-specific artifacts and provenance requirements, leaving a significant gap in comprehensive risk management. This paper aims to propose a robust framework for operationalizing secure AI supply chains. The key contribution lies in extending SBOM standards to AI components, integrating provenance verification into MLOps pipelines, aligning with governance frameworks such as NIST SSDF and AI RMF, and applying zero-trust principles to AI artifacts. Findings demonstrate that these measures enable proactive vulnerability mitigation, enhanced transparency, and regulatory compliance, thereby advancing resilient and accountable AI systems. These contributions strengthen the field by providing actionable strategies that balance innovation with security, fostering greater trust in AI technologies.

Tail Design for Improved Stability and Control of a Short Take Off and Landing Aircraft at High Angles of Attack

2026-01-08T05:17:10+00:00

Short takeoff and landing (STOL) aircraft are an important part of life in Alaska. These aircraft allow pilots to land in places that would otherwise be considered too small for a standard aircraft. Part of being a STOL capable aircraft requires slow speed flight at high angles of attack. Many of the true STOL aircraft in Alaska are modified commercially available aircraft that were never designed for these high angles of attack. This paper will propose and analyze a set of modifications to an already modified Piper Cub to improve the tail authority at these higher angles of attack. These modifications include changing the cross-sectional geometry of the horizontal stabilizer, increasing the area of the tail, and increasing the length of the wing leading edge slats to improve flow quality. CFD was performed on both the original and modified designs in a variety of flight configurations to evaluate the stability and control of the aircraft system at a free stream velocity of 30mph. Analysis of the CFD found that the elevator authority increases by 12.3% and the maximum achievable angle of attack increases by approximately 5.5 degrees.