Dinan Jayasinghe — Portfolio

Projekte

Zertifiziert

Selbstgesteuertes Projekt

Machine Learning for Automotive

KI / ML · August 2026

92/ 100

Eine ProoV-Fallstudie · Lernprojekt, kein Arbeitsverhältnis

Built an end-to-end used-car pricing analysis for VW and Audi listings in the UK market. Combined the datasets, engineered predictive features such as car age and mileage-per-year, trained and compared Linear Regression and Random Forest models, and used R²/MAE/RMSE to show the Random Forest as the stronger pricing model. Also produced a business summary that identified the main pricing drivers and recommended deployment for CPO valuation workflows.

Bewertet nach

Exploratory Data Analysis20%
Feature Engineering25%
Model Building & Evaluation35%
Business Communication20%

Bestanden · Bestehensgrenze 60/100

Was herausstach6

Combined VW and Audi listings into a single analysis frame with a brand indicator for cross-brand comparison.
Engineered the key predictive features required by the brief, including car age and mileage-per-year, and applied data cleaning for implausible rows.
Compared Linear Regression against Random Forest using R², MAE, and RMSE, then translated the results into a clear CPO pricing recommendation.
Leakage-Free Feature Engineering
Comparative Model Evaluation
Business Translation of ML Results

Meine eingereichte Arbeit10 Aufgaben

5 Aufgaben · 6 Zeilen · 5 Textantworten · 163 Wörter

VW Sprint1 Complete56 Zeichen
VW Sprint2 Complete61 Zeichen
VW Sprint3 Complete59 Zeichen
VW Business Insights1.4k Zeichen
Jupyterlite Code2 Zeilen
VW Sprint1 Complete1 Wort
VW Sprint2 Complete1 Wort
VW Sprint3 Complete1 Wort
VW Business Insights159 Wörter
Jupyterlite Code1 Wort

Bewusst zusammengefasst — der eingereichte Code und die Texte bleiben privat, damit diese Seite nicht als Lösungsvorlage dient. Die vollständige Einreichung steht hinter dem verifizierten Zertifikat.

Verifiziertes ZertifikatFälschungssicher · ausgestellt von ProoV

Zertifiziert

Selbstgesteuertes Projekt

Machine Learning for Automotive Safety

Perception Validation Engineer (ADAS Safety Sign-off) · KI / ML · Juli 2026

92/ 100

Eine ProoV-Fallstudie · Lernprojekt, kein Arbeitsverhältnis

Built a perception validation dossier end to end for a synthetic Aurora-7 detector: defined detection correctly with an IoU >= 0.5 match rule, computed precision/recall and the VRU false-negative rate, and then sliced recall by lighting, visibility, and class to expose the dangerous night and occluded VRU failures. The final safety case framed these as ISO 21448 functional insufficiencies and closed with an evidence-based GO-WITH-CONDITIONS recommendation tied to the dossier’s own numbers.

Bewertet nach

Detection metrics correctness (precision, recall, VRU false-negative rate)30%
Failure-mode analysis & per-condition rigour25%
SOTIF safety case quality (ISO 21448 reasoning)25%
Ship verdict — evidence-based & internally consistent20%

Bestanden · Bestehensgrenze 60/100

Was herausstach6

Computed and carried forward the correct IoU threshold rule: a match only counts at IoU >= 0.5, with unmatched real objects treated as false negatives.
Used VRU recall and VRU false-negative rate as the safety metric, explicitly showing why aggregate accuracy is misleading.
Identified the worst slice as night + occluded with recall 0.27 and kept catastrophic VRU misses in the red band.
Wrote concrete mitigations such as daylight-only restriction, sensor-fusion fallback, targeted night/rare-class data, and driver-attention requirements.
Leakage-Free Detection Definition
Safety-Critical Metric Selection

Meine eingereichte Arbeit20 Aufgaben

12 Aufgaben · 17.0k Zeichen · Python · 8 Textantworten · 845 Wörter

Sensor Match553 Zeichen
Example Iou Demo1.5k Zeichen
Task Definition Code1.1k Zeichen
Task Definition377 Zeichen
Example Metrics DemoPython · 2.2k Zeichen
Scored Metrics RunPython · 2.3k Zeichen
Scored Metrics351 Zeichen
Ttcs Example SlicePython · 1.3k Zeichen
Failure Triage1.8k Zeichen
Ttcs Triage SlicePython · 1.6k Zeichen
Sotif Case2.5k Zeichen
Ship Verdict1.5k Zeichen
Sensor Match27 Wörter
Example Iou Demo169 Wörter
Task Definition Code149 Wörter
Task Definition42 Wörter
Example Metrics Demo154 Wörter
Scored Metrics Run143 Wörter
Scored Metrics18 Wörter
Ttcs Example Slice143 Wörter

Verifiziertes ZertifikatFälschungssicher · ausgestellt von ProoV

Zertifiziert

Selbstgesteuertes Projekt

Predictive Maintenance: Industrial ML for Fault Detection

Condition-Monitoring Engineer · KI / ML · Juli 2026

92/ 100

Eine ProoV-Fallstudie · Lernprojekt, kein Arbeitsverhältnis

Built an end-to-end rolling-bearing fault detector from vibration data: engineered RMS, kurtosis, crest factor, and envelope-spectrum defect-band energy; localized the fault to the outer race via BPFO; trained a depth-capped decision tree on training bearings only; and evaluated it on held-out bearings with reported catch-rate and false-alarm rate. Also justified an alarm threshold using the candidate’s own cost numbers in a maintenance memo.

Bewertet nach

Feature engineering (signal to honest numbers)25%
Held-out evaluation (honest measurement)25%
Cost-based threshold decision + memo25%
Compact model + embedded-budget justification15%
Plain-language explanation10%

Bestanden · Bestehensgrenze 60/100

Was herausstach6

Computed time-domain features that clearly separate healthy and faulty signals, with kurtosis and crest factor jumping sharply on the impulsive fault.
Used the provided envelope-spectrum helper and correctly found BPFO as the dominant band, mapping it to the outer race.
Kept the classifier compact and interpretable, stating a depth-1 tree with 3 nodes and confirming training-only fitting.
Defended the 0.41 threshold with concrete catch-rate, false-alarm, and euro-cost figures in a maintenance-facing memo.
Leakage-Free Feature Engineering
Honest Model Evaluation

Meine eingereichte Arbeit20 Aufgaben

12 Aufgaben · 13 Zeilen · Python · 8 Textantworten · 501 Wörter

Initial Prediction62 Zeichen
Load Plot Signal CodePython · 1.8k Zeichen
Load Plot Signal205 Zeichen
Example Rms WorkedPython · 697 Zeichen
Time FeaturesPython · 1.9k Zeichen
Fault Location239 Zeichen
Train Classifier363 Zeichen
Evaluation Heldout288 Zeichen
Threshold Decision335 Zeichen
Decision Memo878 Zeichen
Freq FeaturesPython · 1.0k Zeichen
Jupyterlite Code2 Zeilen
Initial Prediction9 Wörter
Load Plot Signal Code163 Wörter
Load Plot Signal15 Wörter
Example Rms Worked72 Wörter
Time Features173 Wörter
Fault Location14 Wörter
Train Classifier31 Wörter
Evaluation Heldout24 Wörter

Verifiziertes ZertifikatFälschungssicher · ausgestellt von ProoV