Case study
Conversational AI over Enterprise Data
A high-fidelity information retrieval system for complex regulatory and operational data—grounded citations, domain-tuned chunking, and evaluation loops that stand up to compliance scrutiny.
Evidence & exploration
Abstracted highlights from solution and platform architecture, conversational enterprise AI, operational analytics, certification programs, research synthesis and surveys, and large-scale academic IT—paired with peer-reviewed publication output.
Case study
A high-fidelity information retrieval system for complex regulatory and operational data—grounded citations, domain-tuned chunking, and evaluation loops that stand up to compliance scrutiny.
Case study
Forecasting and multi-agent analytics for asset-heavy and regulated operations: historical and real-time signals, maintenance records, environmental factors, and asset condition combined into demand or continuity estimates, risk scoring, alerting, and prioritized actions for capacity planning and reliability programs.
Case study
Lead implementation of an ISO 42001 Artificial Intelligence Management System for a large utility—gap analysis, policies, AI-specific risk treatment, audit evidence, and continuous improvement to sustain certification in a safety-critical sector.
Case study · Academia
As CTO and digital-learning leadership for a multi-campus university: cloud migration to Microsoft Azure with observability (Application Insights / Azure Monitor), a modern .NET-based academic software stack, SAP S/4 HANA rollout across campuses, and LMS plus virtual learning platforms to sustain instruction, accreditation-aligned operations, and continuity under pressure.
Case study · Architecture
End-to-end ownership from requirements and reference architecture through integration patterns and delivery: multi-tier enterprise systems (Java and .NET ecosystems), high-volume transactional domains, API and data contracts, performance tuning, security and coding standards, vendor coordination, and modernization roadmaps—spanning capital-markets-grade platforms, product engineering, and complex stakeholder landscapes over two decades.
Case study · Research
Evidence-led studies for teams that need defensible answers before roadmaps or investment: systematic and mapping literature reviews, scoping of emerging domains (e.g., AI/ML and software engineering), bibliometric or text-mining views of publication corpora, and survey-style assessments of tools and practices. Grounded in a long publication record, grant-funded research, and graduate supervision—this pattern is what ni7labs references when clients need research-backed diligence before roadmaps or funding decisions.
Works listed on Google Scholar (sorted by publication date, newest first). Metrics and citations update on Scholar.
Selected papers below are a curated subset of higher-impact work from that profile—not the complete bibliography. For every title, use the Scholar link above.
Selected publications
Enhancing software quality with AI: A transformer-based approach for code smell detection
Applied Sciences 15 (8), 4559
Decoding the user's movements preparation from EEG signals using vision transformer architecture
IEEE Access 10, 109446-109459
Towards automatic license plate detection
Sensors 22 (3), 1245
Content-aware SLIC super-pixels for semi-dark images (SLIC++)
Sensors 22 (3), 906
Development of enhanced stimulus content to improve the treatment efficacy of EEG-based frontal alpha asymmetry neurofeedback for stress mitigation
IEEE Access 9, 130638-130648
Bimodal data fusion of simultaneous measurements of EEG and fNIRS during lower limb movements
Brain Sciences 11 (6), 713
Block compressive sensing single-view video reconstruction using joint decoding framework for low power real time applications
Applied Sciences 10 (22), 7963
Real-time stress assessment using sliding window based convolutional neural network
Sensors 20 (16), 4400
Deep Network for the Iterative Estimations of Students' Cognitive Skills.
IEEE Access 8
Investigating neurofeedback protocols for stress mitigation: a comparative analysis of different stimulus contents
IEEE Access 7, 141021-141035
Block compressive sensing (BCS) based low complexity, energy efficient visual sensor platform with joint multi-phase decoder (JMD)
Sensors 19 (10), 2309
Explicit content detection system: An approach towards a safe and ethical environment
Applied Computational Intelligence and Soft Computing 2018 (1), 1463546
Smart wearable EEG sensor
Procedia Computer Science 105, 138-143
Stock market prediction using machine learning techniques
2016 3rd international conference on computer and information sciences…
Wind Farm Layout Design Using Cuckoo Search Algorithms
2016 5th International Conference on Smart Cities and Green ICT Systems…
Comparative analysis of data mining techniques for financial data using parallel processing
Proceedings of the 7th international conference on frontiers of information technology
Implementation of association rule mining using CUDA
2009 International Conference on Emerging Technologies, 332-336