UNLOCKING DIGITAL
AI-DRIVEN
SOLUTIONS
FOR OCCUPATIONAL, SAFETY & HEALTH (OSH) MANAGEMENT
PRESENTATION TO: Chief Executive Officer (CEO)
ORGANIZATION: Serikandi Oilfield Services Sdn. Bhd.
“Exploring Strategic Collaboration in Digital AI & Intelligent OSH Solutions”
Presented by
Ir. Ts. Michael Anggie
Director, Sumira Engineering
AI
SYSTEM.CORE
About Sumira Engineering
Established in 2021, Sumira is a Bumiputera-owned Sarawakian engineering and technology company founded by one of the younger brothers and led by a team of siblings with complementary engineering and industry expertise.
Our multidisciplinary foundation brings together engineering knowledge, industry experience and practical project capabilities, enabling us to support end users, contractors and strategic industry partners through engineering design, project execution, technology integration and operational support.
Our Multidisciplinary Capabilities
OUR NEXT CHAPTER
DIGITAL AI, IoT & SMART TECHNOLOGY
Engineering Expertise // Intelligent Solutions
Objective
To demonstrate how Digital AI, computer vision, IoT and integrated data analytics can enhance OSH management by moving from manual and reactive monitoring toward proactive, predictive and data-driven safety management.
1 Detection
Normal cameras, AI-powered cameras, sensors and wearables continuously monitor workplace activities 24/7.
2 Analysis
AI analyzes data patterns to identify potential hazards and provide actionable insights for preventive measures.
3 Decisions
Dashboards and automated alerts enable timely and informed management decisions, including event statistics.
4 Improvement
Data-driven feedback loops continuously improve safety policies, training and workflows.
Concepts Framework
Surveillance &
Security
COMPUTER VISION
24/7 visual analysis for PPE compliance, intrusion, and unsafe acts.
Integrated
System
AI PROCESSING HUB
- ▸ Real-time Data Aggregation
- ▸ Predictive Risk Modeling
- ▸ Automated Alert Routing
Mobile
App
RESPONSE
Instant push notifications for supervisors.
Fatigue
Management
BIOMETRIC TELEMETRY
Continuous monitoring of HRV and physiology.
Key OSH Safety Concerns
Operational safety in oil and gas facilities involves critical challenges where continuous visibility is hard to maintain manually.
Unsafe Acts (UAUC)
Real-time detection of non-compliant behaviors and PPE violations.
Fatigue Management
Worker fatigue significantly increases accident risk during extended operations.
Phone Compliance
Unauthorized mobile phone use creates distraction risks and potential ignition sources.
Unsafe Acts & Conditions (UAUC)
Manual observation is subjective. We leverage AI-powered Computer Vision connected to CCTV infrastructure to provide 24/7, objective hazard detection.
PPE Compliance Detection
Real-time identification of missing hard hats, safety glasses, face masks, etc.
Fatigue Management: Predictive Safety
Smart Wearables
Capture physiological indicators including HRV, movement patterns and rest quality.
AI Pattern Analysis
AI identification of fatigue-related indicators based on collected physiological data.
CCTV Integration
Computer vision monitors behavioural indicators associated with fatigue.
Mobile Phone Usage Compliance
Mobile phone usage in non-manufacturing areas presents distraction-related safety risks and potential ignition sources.
Digital AI Surveillance Analytics
MLNG Complex, Bintulu - Contractor Yard (CY)_1
POC Overview
Conducted to demonstrate practical capability of Digital AI to analyze CCTV feeds, identify predefined safety/security events, and generate alerts at MLNG Complex.
Key Finding
Face detection observed at ~99%. Behavioral functions at ~75-80%. Successfully provides an additional layer of intelligent monitoring.
Face Detection
~99% Accuracy observed.
Safety Helmet
Missing helmet detection.
Face Mask
Missing mask detection.
Mobile Phone
Usage/operation detection.
Intrusion
Restricted area movement.
Unauthorized Person
Access monitoring.
Perimeter
Boundary movement.
Smoking
Non-designated areas.
Transforming Existing Infrastructure into Integrated Digital Intelligence
Integrated System
Surveillance & Security System
1 Detection
Normal cameras, AI-powered cameras, sensors and wearables continuously monitor workplace activities 24/7, enabling real-time surveillance.
2 Analysis
AI analyses data patterns to identify potential hazards and provide actionable insights for preventive measures.
3 Decisions
Dashboards and automated alerts enable timely and informed management decisions, including event statistics and trends.
4 Improvement
Data-driven feedback loops continuously improve safety policies, training and workflows for operational enhancement.
Bintulu Port's Digital Transformation
Towards a Smarter, More Connected Port
Operational safety in oil and gas facilities involves critical challenges such as non-compliance to HSE at work place especially in industrial area. Even with established HSE systems and procedures, large-scale operations, routine activities, turnarounds and shutdowns can create challenges in maintaining continuous visibility across all work areas.
Existing Digital Ecosystem
- ▸CCTV & video surveillance
- ▸Port operational systems
- ▸Security systems
- ▸Network infrastructure
- ▸Digital platforms
DIGITAL AI OPPORTUNITY
Detection • Alerts • Analytics • Dashboard
Note: Digital AI complements existing systems; it does not require unnecessary replacement of existing infrastructure subject to technical specification and client's requirement.
SUMIRA'S CORE PROPOSITION
RIDE ON THE EXISTING. ADD INTELLIGENCE.
SUMIRA proposes to leverage Bintulu Port's existing infrastructure and enhance its capability through AI-powered video intelligence. The objective is not to replace what Bintulu Port already has but to make it smarter.
EXISTING INFRASTRUCTURE
- - CCTV
- - VMS / Network
- - Security Systems
- - Port Systems
AI INTELLIGENCE LAYER
- - AI Video Analytics
- - Event Detection
- - Alarm Management
SYSTEM INTEGRATION
- - Data / API Integration
- - Event Management
INTEGRATED DASHBOARD
- - One Platform
- - One View
- - Actionable Intelligence
From CCTV to Digital Intelligence
CCTV SEES. AI UNDERSTANDS.
Our Digital AI Integrated System leverages AI, CCTV and computer vision to deliver continuous intelligent monitoring across selected operational areas.
Personal Detection & Identification (FD/FR)
Access control and personnel tracking for authorized zone compliance.
Vehicles / Motion Tracking
Vehicle and worker movement monitoring for hazardous proximity alerts. Route planning and transportation safety.
PPE Compliance
Automated detection of missing or improper personal protective equipment (Helmets, Eye wear, Vests, Boots, etc).
Thermal Detection & Leak Monitoring
Heat signature analysis for fire risks, equipment overheating, and disruptions in processing plants.
Digital AI for Smart Port Operation
AI-POWERED PORT INTELLIGENCE.
SAFETY
- ▸PPE compliance
- ▸Restricted-area detection
- ▸Person/vehicle proximity
- ▸Fall detection
- ▸Unsafe activity
- ▸Fatigue Management
- ▸Mobile Compliance
SECURITY
- ▸Intrusion detection
- ▸Unauthorised access
- ▸Perimeter monitoring
- ▸Abnormal activity
INCIDENT
- ▸Smoke / fire detection
- ▸Crowd detection
- ▸Abnormal events
- ▸Incident verification
OPERATIONS
- ▸Vehicle movement
- ▸Traffic monitoring
- ▸Congestion monitoring
- ▸Operational-zone monitoring
- ▸Activity monitoring
AI applications can be configured according to Bintulu Port's operational priorities and requirements.
INTEGRATED DASHBOARD
FROM DATA to SAFETY INTELLIGENCE
The Integrated Dashboard serves as your centralized safety intelligence platform, transforming raw data from multiple sources into actionable insights. This unified system visualizes all data—providing real-time monitoring, automated alerts, comprehensive analytics, and reporting across personnel, contractors, and vendors.
LIVE MONITORING
- - Camera status
- - Selected live feeds
- - Operational locations
AI EVENTS
- - PPE violation
- - Restricted area
- - Vehicle / pedestrian proximity
- - Intrusion & Smoke/fire
EVENT INFORMATION
Location | Date | Time | Camera | Event Type | Evidence
PREVENTIVE ANALYTICS
Machine learning identifies emerging risks and trends. Statistical summary of performance (daily, weekly, monthly).
ONE DASHBOARD. ONE VIEW. ACTIONABLE INFORMATION.
Management does not need to continuously monitor every camera. The system highlights events that require attention.
BUSINESS BENEFITS TO BINTULU PORT
Enhanced Safety
Earlier identification and notification of potentially unsafe conditions.
Enhanced Security
Improved real-time situational awareness across selected operational areas (24/7 Safety Visibility).
Operational Visibility
Greater visibility of activities across multiple locations simultaneously.
Data-Driven Management
Convert visual events into measurable information, trends and KPIs.
AI-Assisted Monitoring
Enable personnel to focus on higher-value operational and decision-making activities.
Maximise Investment
Enhance existing CCTV infrastructure through AI without unnecessary hardware replacement.
Improved Response
Provide timely alerts to responsible personnel when configured events occur.
Smart Port Transformation
Create an AI-enabled foundation that can progressively support Bintulu Port's digital journey.
DIGITAL AI ROADMAP FOR BINTULU PORT
SUMIRA's intention is to work with Bintulu Port progressively to enhance, integrate and expand the Digital AI capability according to actual operational requirements.
INTEGRATE
Existing CCTV & Infrastructure
INTELLIGENCE
AI Detection & Analytics
INTEGRATION
Systems + Dashboard
OPTIMISE
Additional Algorithms / Locations / Apps
CONTINUOUS IMPROVEMENT
Data → Insights → Improvement
Commitment: SUMIRA is committed to continuously improve and enhance the Digital AI solution in line with Bintulu Port's operational requirements and Smart Port development.
THE BEGINNING OF A LONGER TECHNOLOGY PARTNERSHIP
Our intention is not to treat Digital AI as a one-off system implementation. We see this as a platform that can continuously improve together with Bintulu Port.
Once the initial system is established, additional algorithms, locations and integrations can be introduced based on actual operational requirements and priorities.
SUMIRA would like to be Bintulu Port's local engineering and integration partner in that continuous improvement journey.
Objective
To enable PUSAKA to improve the accuracy, traceability and accountability of physical assets and inventory through AI-enabled monitoring and automation.
Initial Application:
LPG Cylinder Inventory & Asset Tracking
Key Objectives
- ✓Reduce dependence on manual inventory monitoring
- ✓Improve visibility of asset movement
- ✓Minimise inventory discrepancies
- ✓Strengthen asset accountability and traceability
- ✓Provide real-time operational visibility
Identified Operational Challenge
LPG CYLINDER INVENTORY & TRACKING
LPG cylinder inventory can become difficult to manage when physical movement and manual records are not fully synchronised.
Physical stock may not tally with recorded inventory
Manual recording can result in gaps or inconsistencies
Difficult to determine the current location of cylinders
Movement between locations can be difficult to track
Stock reconciliation requires significant manual effort
Limited real-time visibility for management
Key Question:
"Can we know, at any point in time, what assets we have, where they are, and whether the physical inventory matches the recorded inventory?"
Proposed Digital AI Solution
From Manual Tracking to Intelligent Asset Visibility
Physical Asset
Identification
QR/Barcode/RFID/Visual
AI Monitoring
Camera + AI Analytics
Movement Capture
IN / OUT / TRANSFER
Inventory Database
Reconciliation & Exceptions
Management Dashboard
Resulting In
Inventory & Asset Dashboard
One View of Physical Inventory and Asset Movement. From periodic manual checking to continuous operational visibility.
INVENTORY
- ▸ Total stock
- ▸ Available stock
- ▸ Issued stock
- ▸ Returned & In-transit
ASSET STATUS
- ▸ Current location
- ▸ Movement history
- ▸ Last recorded activity
- ▸ Asset ageing
CONTROL
- ▸ Inventory variance
- ▸ Unrecorded movement
- ▸ Missing assets
- ▸ Abnormal activity
EXPECTED BENEFITS TO PUSAKA
1. Inventory Accuracy
Improve reconciliation between physical and recorded stock.
2. Operational Efficiency
Reduce repetitive manual checking and reconciliation.
3. Asset Traceability
Know exactly where an asset is and how it moved.
4. Accountability
Improve visibility of asset issuance, transfer and return.
5. Exception Management
Identify discrepancies and unusual movements faster.
6. Management Visibility
Provide reliable information for operational decision-making.
Beyond Inventory Management
Additional AI capabilities for safety, security and operation.
SAFETY
- ▸ PPE detection
- ▸ Smoking detection
- ▸ Fire & smoke detection
- ▸ Unsafe-zone monitoring
SECURITY
- ▸ Intrusion detection
- ▸ Restricted-area monitoring
- ▸ Unauthorised access
- ▸ Abnormal activity
OPERATIONS
- ▸ Vehicle & pedestrian monitoring
- ▸ Loading / unloading activity
- ▸ Warehouse activity monitoring
- ▸ Operational event detection
Digital AI becomes more than CCTV...
it becomes an intelligent operational monitoring layer.
How Digital AI Complements PUSAKA
Connecting the Physical World with Digital Management
Existing Digital Systems
Records
Data
Transactions
Reports
Digital systems tell PUSAKA what is recorded.
Digital AI
Physical observation
Asset movement
Visual intelligence
Real-time events
Digital AI helps PUSAKA understand what is physically happening.
INTEGRATED OPERATIONAL INTELLIGENCE
SUMIRA'S PROPOSED APPROACH
1. UNDERSTAND
Understand PUSAKA's existing operational processes, systems and requirements.
2. INTEGRATE
Complement existing infrastructure and digital systems with AI-enabled capabilities.
3. ENHANCE
Improve asset visibility, inventory control, traceability and operational intelligence.
4. SCALE
Extend proven capabilities across other assets, warehouses and operational environments.
THE WAY FORWARD
From a Specific Operational Challenge to a Scalable Digital Platform
Digital AI Proof of Concept
The Digital AI-Powered Surveillance Analytics Proof of Concept (POC) was conducted at the Malaysia LNG Sdn. Bhd. (MLNG) Complex, Bintulu, specifically within the Contractor Yard (CY)_1 area, including the designated smoking area, to demonstrate the application of Digital AI technology in supporting Occupational Safety and Health (OSH), safety compliance, and security surveillance.
POC Execution Details
- Location:MLNG Complex, Bintulu (Contractor Yard CY_1 Area & Smoking Area)
- Client:Malaysia LNG Sdn. Bhd. (MLNG)
- Execution Date:13th August 2026
- Technology:MEGVII AI Solution
POC Objectives
To demonstrate and verify the practical applicability of the currently available Digital AI capabilities for supporting OSH, safety compliance, and security surveillance.
Demonstrate AI capability to analyze surveillance camera feeds and identify predefined events in real time.
Verify face detection and face recognition capabilities within the designated surveillance area.
Verify basic PPE compliance detection (missing safety helmets and face masks).
Verify mobile phone usage detection (operating a phone or engaging in a call).
Verify intrusion and access-related detection (movement into restricted areas, unauthorized persons).
Verify perimeter monitoring via AI-based detection across defined perimeter boundaries.
Verify smoking detection capability outside the designated smoking areas.
Demonstrate generation of AI events and alerts following successful detections.
POC Scope & Testing Boundaries
Functional Areas Assessed
Capability Demonstration
This POC was limited to AI detection capabilities available within the system configuration at the time of testing. It serves as a practical capability demonstration and does not constitute a full-scale operational deployment or final performance acceptance.
AI Parameter Evaluation Matrix
Demonstrated Parameters
Face Detection Performance
Behavioral Est. Accuracy
Face Detection
Evaluation of detection and recognition capability.
Safety Helmet
Detection of personnel missing safety helmets.
Face Mask
Detection of personnel missing face masks.
Mobile Phone
Detection of personnel operating a mobile phone.
Intrusion
Movement into defined restricted areas.
Unauthorized Person
Persons without required authorization.
Perimeter
Movement across defined boundaries.
Smoking Detection
Detection within non-designated areas.
Observations & Conclusion
Key Observations
- ▸Digital AI system successfully demonstrated all 8 identified AI detection parameters.
- ▸System automatically detected predefined safety/security events and generated corresponding alerts.
- ▸Observed face detection performance was approximately 99%.
- ▸Selected behavioral detection functions demonstrated an observed performance of ~75-80%.
Conclusion
The POC successfully demonstrated the currently available AI detection capabilities identified for the MLNG Complex CY_1 area.
It demonstrates the potential of Digital AI-Powered Surveillance Analytics to provide an additional intelligent monitoring capability in support of existing OSH, safety compliance, and security surveillance practices.
SUCCESSFULLY DEMONSTRATED
Added Value to Client
Transforming existing surveillance infrastructure into a proactive, intelligent, and highly efficient OSH management asset.
Capital Efficiency
The system leverages existing IP CCTV infrastructure (e.g., standard Hikvision cameras) and adds an AI intelligence layer without requiring unnecessary hardware replacement.
Continuous Safety Visibility
Shifts Occupational Safety and Health (OSH) management from subjective, periodic manual audits to 24/7 autonomous monitoring with real-time alert generation.
Data-Driven Accountability
Converts visual events into measurable KPIs, providing centralized tracking of contractor safety records, compliance rates, and incident history.
Operational Resource Optimization
Automates routine surveillance tasks, allowing safety personnel to focus on high-value incident response and critical decision-making rather than continuous screen monitoring.
Network System Design Architecture
System Topology
Field Tier (Edge Capture)
Standard Hikvision IP cameras and specialized AI CCTV units connect via CAT-6 to field-hardened PoE switches; high-draw cameras receive up to 30W/60W IEEE 802.3at/bt power.
Transmission Tier (Backbone)
Field PoE links to the central server room through armored Single-Mode FO cables via SFP transceivers, isolating field traffic from EMI.
Central Ingestion & Analytics
Fiber runs terminate at the Layer 3 Core Router. Traffic splits: raw streams route to NVR (storage) & HCP (VMS), while secondary RTSP streams route to MEGVII AIoT engine.
Automation & Control Tier
Violations trigger hardware relays via an Ethernet-based DI/DO module, delivering dry-contact signals directly into the plant DCS and local operator HMIs.
End-to-End Process Flow
Optical Acquisition
Standard and thermal cameras capture high-definition RTSP streams and route them over CAT-6 to the nearest field PoE switch.
Backbone Transport & Ingestion
Video data aggregates across the fiber-optic ring through the core router, directing primary recording streams to the NVR and management to HCP.
Real-Time AI Inference
The MEGVII AIoT Engine pulls video channels directly, running deep learning models locally for PPE compliance, phone usage, and boundary violations.
DCS Interlock & HMI Annunciation
Upon detection, MEGVII broadcasts JSON webhooks and triggers the DI/DO module to close physical dry-contact circuits wired to DCS I/O cards.
Communication Matrix
CAT-6 Copper
Camera-to-PoE switch runs (<100m) and rack equipment interconnects.
Fiber Optic (FO)
Long-distance field cabinet-to-control room backbone carrying 10 Gbps uplinks.
RTSP / ONVIF
Video transmission between cameras, HCP, NVR, and the MEGVII AIoT engine.
HTTP REST / WebSocket
MEGVII Open API integration broadcasting alert payloads to web dashboards.
Modbus TCP / Dry Contact
16-Channel DI/DO output to DCS digital input terminal blocks for physical fail-safe triggers.
Project Limitations
Operating parameters and inherent considerations to acknowledge when scaling Digital AI surveillance platforms.
Environmental Dependencies
AI detection performance is inherently subject to external variables, including camera positioning, line-of-sight occlusions, lighting quality, and adverse weather conditions.
Behavioral Accuracy Ceilings
While facial detection achieves ~99% accuracy, complex behavioral anomalies (such as mobile phone usage) currently yield 75-80% precision and require ongoing optimization.
Validation for Complex Variables
Specific parameters, such as smoking detection in non-designated areas, are highly susceptible to environmental interference and require further field validation during active operations (e.g., Shutdown MOD 6).
Decision Support Nature
The Digital AI is an intelligence and alerting layer; it does not physically prevent incidents and still requires human intervention for enforcement and emergency response.
Future Recommendations
Algorithm Customization
Train and deploy site-specific AI models tailored to emerging operational risks, such as chemical spill detection, specific heavy machinery proximity, or advanced ergonomic strain analysis.
Progressive Scalability
Expand the proven AI ecosystem from the initial pilot zones (e.g., Contractor Yard 1) to encompass critical manufacturing areas, storage terminals, and offloading perimeters.
Enterprise Integration
Synchronize the AI Command Dashboard with the client's existing Human Resources databases, contractor permit systems, and automated access control gates for seamless identity management.
Biometric Telemetry
Enhance predictive safety capabilities by outfitting high-risk personnel with IoT wearables to continuously track Heart Rate Variability (HRV) and physiological data for proactive fatigue intervention.
SAFETY INSIGHTS
PLANT DIGITAL TWIN // LIVE TELEMETRY
FIELD OPERATION OVERVIEW
NON-COMPLIANCE TOPS
IOT STATISTICS
ALARM CENTER
REAL-TIME NOTIFICATION
THE END
DIGITAL AI, IoT & SMART TECHNOLOGY
Engineering Expertise. Intelligent Solutions.
Expanding our multidisciplinary engineering capabilities into intelligent, connected and technology-driven solutions.
Sumira Engineering Sdn. Bhd.
Exploring Strategic Collaboration
