
Forensic handwriting identification plays a pivotal role in criminal investigations and legal proceedings, requiring accurate and reliable techniques for analyzing handwriting samples. Convolutional Neural Networks (CNNs) are effective at feature extraction and classification for handwriting analysis, but their performance is highly sensitive to the choice of architectural hyperparameters, and manually tuned CNNs are prone to overfitting on forensic handwriting data. This study integrates the Chicken Swarm Optimization (CSO) algorithm with a CNN classifier (CSO-CNN) to automatically search the number of convolutional layers, the number and size of filters, and the batch size that minimize overfitting and maximize recognition accuracy. Handwritten samples were collected from staff and students of Ajayi Crowther University, Oyo, Nigeria, and organized into three variants (Original, Disguised, and Forged) with each variant split into training and test sets (72% and 28%, respectively) using a random-sampling hold-out procedure. CSO searched 30 candidate CNN configurations over the number of convolutional layers (1–3), the number of filters, the filter size, and the batch size, using recognition rate as the fitness function; the best-performing configuration used a single convolutional layer with 128 filters of size 3×3 and a batch size of 256. The resulting CSO-CNN model was compared against a standard, non-optimized CNN using accuracy, sensitivity, specificity, precision, false positive rate, and recognition time. CSO-CNN outperformed the standard CNN on every dataset variant: on the original dataset, accuracy improved from 82.14% to 86.43%; on the Disguised dataset, from 85.00% to 87.86%; and on the Forged dataset, from 83.57% to 89.29%, while recognition time was also reduced in all three cases. These results indicate that CSO-based hyperparameter search can meaningfully improve CNN-based forensic handwriting identification without requiring architectural redesign. As the evaluation reported here is based on a single hold-out split, repeated cross-validation and testing on independently collected datasets are recommended as a next step to confirm the statistical robustness and generalizability of these gains.
In secure devices like Java Cards, several attacks have been developed to dump memory and reverse its contents, thereby gaining access to sensitive stored assets. Many manufacturers have proposed various countermeasures to protect this data from malicious code. Obfuscation is one of these techniques; it consists of converting part or all of the code into another form that is much harder to understand in order to make the reverse engineering of memory dumps more difficult. This conversion occurs instantly during downloading. In this paper, we propose an automatic approach to reverse engineer obfuscated intermediate bytecode based on a backtracking search algorithm. We then introduce heuristics to optimize the search process and accelerate convergence toward realistic solutions. We implement this approach in a prototype, and, to improve it, we integrate it into the Java Card Disassembler and Analyzer (JCDA) tool. We also explain the new tricks used by our tool to recover some secure assets. Our tool successfully reversed 92% of illegal opcodes and all secure assets.
Blockchain has been widely recognized as a promising technology for inter-organizational collaboration in construction and transportation. However, many blockchain initiatives fail to progress beyond pilot projects. Existing blockchain adoption frameworks primarily identify adoption determinants or technol- ogy acceptance factors but provide limited support for structured, evidence-based feasibility assessment in domain-specific contexts. This paper presents a Design Science Research (DSR) approach to develop a blockchain feasibility assessment framework for public construction and transportation projects. The research was conducted through three iterative Design Science cycles. The Relevance Cycle identifies and validates blockchain-specific feasibility dimensions and assessment factors. The Design Cycle synthesizes these findings into a structured decision-support framework comprising a five-stage assessment process, seven feasibility dimensions, and 58 assessment factors supported by evidence-based scoring and imple- mentation guidance. The Rigor Cycle operationalizes the framework as a web-based decision-support system and evaluates its usability and practical applicability through expert assessment involving three construction and blockchain specialists. The evaluation produced an overall usability score of 4.73/5, in- dicating strong perceived usefulness, completeness, and practical applicability of the proposed artifact. By integrating technical, organizational, governance, legal, economic, and implementation perspectives within a transparent and repeatable assessment process, the framework extends existing blockchain adop- tion research from descriptive assessment factors toward actionable decision support.
Sequential evaluation of large language models (LLMs) needs an auditable way to analyse when intervention first occurs. The architecture presented here uses cumulative scenarios and reconstructs first-ACT/censoring and at-risk datasets from a master record for discrete-time event-history analysis. Its methodological contribution is the integration of established first-event reconstruction with a frozen instrument, independent current-state calls and serving provenance, while retaining later responses for audit. In a thirteen-model demonstration, 26,000 stage-level records yielded 25,999 decision-valid responses, 3,120 scenario-runs and 10,088 at-risk rows. The derived endpoint files and all 2,000 prompt coordinates were regenerated exactly from deposited records. Complete conditional hazards were stage-dependent but non-monotone; within-group linear trend estimates were OR 12.591 (95% CI 8.481–18.694) in Group A, 10.346 (9.292–11.518) in Group B and 4.377 (3.815– 5.022) in Group C, and a quadratic sensitivity confirmed nonlinearity. Later WAIT responses occurred in 21.05% of ACT-containing runs. The reconstruction checks establish analytical reproducibility of one realised first-intervention path under recorded serving conditions; they do not establish a stable latent threshold, normative safety validity or exact recreation of historical provider responses.
The fusion of big data analytics and Cybersecurity has transformed the healthcare industry through technology-enabled methods to detect diseases early and achieve clinical improvement. The exponential growth of electronic health records (EHRs), wearable sensors, and Internet of Things (IoT)-based medical devices has created vast amounts of patient data available for analytics. This data can be used to identify early symptoms of a disease and inform evidence-based clinical decisions. However, increased dependence on digital technologies creates new challenges including data privacy risk; cyberattacks; and unpermitted access to data. This article looks at secure methods for healthcare data analytics leveraging big data technologies in conjunction with advanced cybersecurity methods, including encryption, blockchain, federated learning, and artificial intelligence (AI) models which help ensure patient data remain protected while providing predictive information. The findings outline the vital importance of ensuring innovation with protection of privacy and presents a broadly applicable framework for secure, scalable, and ethical analytics for healthcare.