All projects.
The work index.

AccountsNepal is a production web application for accounting, billing and inventory management, designed for businesses working across companies, branches and fiscal years in Nepal.

My contribution

I contributed across the Angular frontend and Spring Boot backend, and personally handled and obtained IRD verification for the production system.

Core workflows

• Accounting: double-entry bookkeeping, chart of accounts, journal entries, opening balances, customer receivables and supplier payables.
• Billing and POS: sales invoices, purchase bills, quotations, orders, credit and debit notes, receipts and payment vouchers.
• Inventory and delivery: products, batches, stock movements, stock valuation, split and merge operations, delivery chalans and branch transfers.
• Cash and banking: bank and wallet transactions, fund transfers, cheque tracking and reconciliation workflows.
• HR and payroll: employee records, attendance, leave, salary processing and payroll posting.
• Reporting: general ledger, trial balance, profit and loss, balance sheet, cash flow, stock reports and VAT sales and purchase registers.
• Nepal-specific workflows: Bikram Sambat and Gregorian date support, fiscal-year management, VAT handling and IRD/CBMS synchronization for sales bills and credit notes.
• Administration and exports: company and branch access, role-based permissions, audit logs, data migration, invoice printing and PDF/Excel exports.

🥔 Precision Foliar Pathology & Deep Learning Architecture Suite

Multi-Architecture Neural Ensemble · Explainable AI (Grad-CAM) · Soft-Voting + Temperature Scaling T=0.7

End-to-end foliar pathology suite for clinical diagnosis of potato leaf diseases (Alternaria solani — Early Blight, Phytophthora infestans — Late Blight, and Healthy). Moves beyond single-model prototypes with a Tri-Model Soft-Voting Ensemble (DenseNet-121 w0.45, ConvNeXt-Tiny w0.35, EfficientNetV2-S w0.20, 256×256) and Grad-CAM for transparent, field-ready decisions.

Research Benchmark & Ensemble

• DenseNet-121 / ConvNeXt-Tiny / EfficientNetV2-S — ImageNet-pretrained, fine-tuned, soft-voting + temperature scaling
• Kaggle GPU training, TFLite Float16 (21 MB) & Dynamic INT8 exports for edge/mobile
• ITT: TTA, label smoothing, class-weighted, EarlyStopping

Explainable AI

Grad-CAM saliency maps highlight lesion regions driving each prediction — essential for agronomist trust.

Results

Ensemble outperforms single backbones on 405-image held-out test via soft-voting + calibration. Prior B3 baseline: Test Acc 95.80% / Macro-F1 95.86. See Kaggle notebook for full ablation.

NeuroVision is a real-time face recognition system with live enrollment and instant multi-face identification. Users enroll by capturing guided multi-angle samples from their camera — no offline training, no static dataset required. The system learns new faces on the fly via face embeddings and identifies every person in the live camera feed simultaneously.

• Public Page ui design as well as backend apis.
• In distributor module, referral note, ticket, direct sales, promotional sales , month sales, area sales etc reports.
• In Admin module, distributor reports, sales center reports.
• Inventory management, User management features.

Detects cyberbullying in Formspring Q&A posts using NLP and machine learning. Text is preprocessed (stopword removal, stemming) and vectorized with TF-IDF, then classified using multiple models with hyperparameter tuning via GridSearchCV.

Dataset

Formspring.csv -- 13,147 Q&A text entries from the Formspring social platform, labeled for cyberbullying presence.

Classifies SMS messages as spam or ham (not spam) using NLP preprocessing and machine learning. Text is cleaned by removing stopwords and applying stemming, then vectorized with TF-IDF. Multiple classifiers are trained and evaluated, including classical ML, neural networks with Word2Vec embeddings, and a fine-tuned DistilBERT transformer.

• Perks with reports
• Tips with reports
• Payments with reports
• Referrals
• Support & Ticket.
• Settings

• Complete student, teacher, and staff management system with role-based access.
• Class routine and academic scheduling modules.
• Events and academic calendar management.
• Automated invoice generation and fee management.
• Marksheet and academic report generation system.
• Bulk student and teacher upload using Excel files.
• REST API architecture for mobile app system integration.

• Chart of Accounts, Sub Account.
• Sales, Purchase voucher creation with its payment.
• contra voucher.
• Ledger, Trial Balance, Profit & Loss reports etc.
• Payroll with salary generation and posting with its reports

• Hierarchical point distribution system.
• Multi-level role structure (Regional Manager, Area Sales Manager, Distributor, Retailer, Technician).
• Sales-based automated point allocation.
• Top-to-bottom hierarchy point flow logic.
• Point redemption and cash conversion system.
• Redemption payment processing.
• Payment approval workflow.
• Payment reporting system.
• Sales performance reward calculation.

• Valentine’s Week Calendar: Interactive calendar with a real-time Valentine’s Day countdown and automatic active-day highlighting.
• Personalized Love Links: Create unique, shareable links with custom messages and day-specific themes.
• Dynamic Receiver Experience: Private UUID-based links featuring romantic animations, love quotes, and date ideas.
• Real-time Interaction: Receivers can like, accept, or reject, while senders track opens, reactions, and timestamps live.
• Privacy-Focused: IP-based tracking ensures only the link creator can view analytics, with no login required.

🤖 RajuGPT is a context-aware RAG chatbot built with Laravel and OpenRouter, supporting models like Grok-4.1 Fast, GPT-4o, and Gemini 1.5 Pro. It uses hybrid search (MySQL Full-Text + vector embeddings with cosine similarity) for accurate retrieval, maintains conversation memory with Laravel Sessions and localStorage, and automatically ingests knowledge from websites (Firecrawl), PDFs, and GitHub repositories.