Jianjin D.

Key Skills

Software

Don't disclose

Top Subject Matter

Water-leakage detection using fibre-optic pipeline monitoring data

Top Data Types

Computer Code Programming

Image

Text

Top Task Types

Classification

Freelancer Overview

Software R&D Intern — water-leakage detection (labeled supervised dataset for classification). Brings 2+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Don't disclose. Education includes Bachelor of Science, Taylor’s University (2027). AI-training focus includes data types such as Computer Code, Programming, and Medical DICOM and labeling workflows including Classification.

Labeling Experience

Software R&D Intern - Shandong Pusai Communication Technology Co., Ltd.

Classification

You served as a Software R&D Intern supporting a water-leakage detection project using pipeline fibre-optic monitoring data. You cleaned and processed large datasets, engineered features, and prepared labeled samples for supervised model training. You trained and evaluated classification approaches to enable accurate identification and prediction of leakage-related abnormal conditions. • Processed and analyzed 100,000+ fibre-optic monitoring records using Python • Engineered and compared features across pipeline sections and created supervised labels • Trained a classification model to reach 95% prediction accuracy • Developed screening logic for abnormal heating behaviors and supported project analysis

2026 - 2026

Software R&D Intern — water-leakage detection (labeled supervised dataset for classification)

Don't discloseClassification

Processed and analyzed monitoring data from fibre-optic pipeline equipment, producing labeled states for supervised training. Used Python to clean 100,000+ records, extract and compare features across pipeline sections, and assign labels for “leakage” versus “normal.” Trained a classification model using the labeled dataset to identify and predict new fibre-optic inputs. • Supervised label creation for “leakage” and “normal” states • Feature extraction/comparison across pipeline sections • Model training for classification using the labeled data • Built supporting abnormal heating-data screening based on observed behaviours

2026 - 2026

Core Team Member (Machine Learning Project) - Bank Marketing Data Mining and Machine Learning Multi-Model Classification Project

Classification

You participated as a Core Team Member on a bank marketing multi-model classification project using machine learning. You imported raw CSV data and performed exploratory data analysis to understand distributions and data quality. You built and compared several classification models and selected the best performer using standard metrics. • Used Pandas and NumPy for data import, parsing, and exploratory data analysis • Applied scaling and encoding techniques such as StandardScaler, MinMaxScaler, and LabelEncoder • Trained and compared Logistic Regression, KNN, SVC, Random Forest, and Gradient Boosting models • Evaluated models with Accuracy, Precision, Recall, F1-score, Confusion Matrix, and ROC-AUC to choose the best model

2025 - 2025

Education

Work History