Computer Vision Engineer
Jul 2024 – Present(Deep Learning) Hyvision Systems
- Industrial AOI and defect detection pipelines for production.
- Real-time optimization and deployment-ready model engineering.
Deep Learning Engineer (Computer Vision)
Dr. DM. Saqib Bhatti.
Deep Learning Engineer | Computer Vision | 15+ Years Experience
A Deep Learning & Computer Vision expert with 15+ years of experience specializing in Automated Optical Inspection (AOI), Defect Detection, Industrial AI, and Infrastructure Monitoring Systems — focused on real-time, high-accuracy models using customized object detection, segmentation, classification, anomaly detection, and pose estimation.
Core Expertise
🤖 Deep Learning
👁️ Computer Vision
🔍 Object Detection
🧠 Segmentation
🎯 Defect Detection
🏭 Industrial AI / AOI
⚙️ PyTorch / TensorFlow
🚀 TensorRT Optimization
Experience
Industry + research roles across Computer Vision, Industrial AI, and inspection systems.
Computer Vision & AI Researcher
Jan 2024 – Jul 2024Soongsil University, Seoul, South Korea
- Computer vision and AI research.
Computer Vision & AI Researcher
Jun 2021 – Dec 2023Hanyang University, South Korea
- Research and development in AI/vision systems.
Head of Department
Nov 2020 – May 2021Dawood University of Engineering & Technology, Pakistan
- Academic leadership and departmental management.
Assistant Professor
Jan 2017 – May 2021Dawood University of Engineering & Technology, Pakistan
- Teaching, supervision, and research.
Research Assistant PhD
Sep 2012 – Feb 2017Hanyang University, South Korea
- MS–PhD track, research and publications.
BSS Engineer
Jan 2011 – Aug 2012Huawei Technologies, Pakistan
- BSS engineering experience.
Academic Qualifications:
MS–PhD (South Korea): Hanyang University, Seoul (Sep 2012 – Feb 2017)
BE (Pakistan): Mehran University of Engineering & Technology (Jan 2007 – Dec 2010)
Industrial Projects
AOI System for Apple iPhone Front Glass Surface Inspection — Apple
14 defect classes · YOLOv11 + SegNExt · TensorRT
View
AOI system for iPhone front glass surface inspection (scratches, particles, contamination, pinholes, etc.).
Role / Tasks
- Hybrid inspection: object detection + segmentation for multi-class defect recognition.
- Integrated YOLOv11 with customized SegNExt segmentation network.
- Applied TensorRT optimization for real-time deployment.
Development
Language: Python & C#
Libraries: PyTorch, YOLOv11, TensorRT, OpenCV, SegNExt
End Result
- Fast and highly accurate multi-class inspection (14 defect types).
- Production-grade speed and robustness for high-throughput manufacturing.
Automated Optical Inspection for iPhone User Side Glass Logo — Apple
Segmentation · Logo region defects
View
Inspection for user-side glass logo area with precision segmentation to detect subtle defects.
Role / Tasks
- Designed segmentation-based inspection for reflective/low-contrast logo regions.
- Improved defect localization and classification robustness.
- Production-ready optimization and validation.
Development
Language: Python
Libraries: PyTorch, OpenCV
End Result
- Reliable detection of logo-region defects with stable performance.
Gesture Recognition System for Laser Machine Safety Control — Apple
ToF · Detection + Time-series
View
Two-stage system for safety: human detection + 3D time-series gesture classification (6 gestures).
Role / Tasks
- Built human detection stage and gesture pipeline with ToF data.
- Designed time-series classifier for 6 gesture classes.
- Latency reduction for real-time safety control.
Development
Language: Python
Libraries: PyTorch, OpenCV
End Result
- Real-time safety gesture recognition system for laser machines.
AOI System for iPhone Camera-Hole Inspection — Apple
Hybrid segmentation · Small/large defects
View
Camera-hole sidewall defect inspection using hybrid segmentation to handle diverse defect scales.
Role / Tasks
- Developed hybrid segmentation pipeline for small and large defects.
- Optimized model inference under production constraints.
- Improved generalization across variations and reflections.
Development
Language: Python
Libraries: PyTorch, OpenCV
End Result
- High-accuracy inspection suitable for real-time line deployment.
End-to-End System for iPhone Backside Panel Inspection — Apple
Severity grading (A–D) · Measurement
View
Pipeline that detects defects, measures size, and grades severity (A–D).
Role / Tasks
- Designed multi-stage inspection with detection + measurement.
- Implemented severity classification based on size/criteria.
- Improved robustness for varying surface appearance.
Development
Language: Python
Libraries: OpenCV, PyTorch
End Result
- Accurate defect grading and automated decision support.
Automated Ampule Inspection System with Deep Learning — Apple
Detection/segmentation · Quality assurance
View
Deep learning-based ampule inspection system for defect detection and quality control.
Role / Tasks
- Designed inspection pipeline for ampule defects.
- Validated model performance under production constraints.
- Improved reliability via data augmentation and tuning.
Development
Language: Python
Libraries: PyTorch, OpenCV
End Result
- Automated, production-ready ampule inspection pipeline.
Display Chip Inspection System — Samsung SDI
High precision inspection
View
Inspection system for display chips with strong accuracy and robustness requirements.
Role / Tasks
- Designed vision pipeline for chip inspection and defect localization.
- Optimized model inference and stability across conditions.
Development
Language: Python
Libraries: OpenCV, PyTorch
End Result
- Reliable inspection workflow suitable for industrial QA.
AOI System for iPhone MIC Hole Inspection — Apple
Small defect detection
View
Inspection pipeline targeting mic-hole region defects with tight tolerance.
Role / Tasks
- Built AOI pipeline for mic-hole defect detection and validation.
- Improved robustness for small features and reflections.
Development
Language: Python
Libraries: OpenCV, PyTorch
End Result
- High-precision mic-hole inspection ready for deployment.
PCB Board Defects with Anomaly Detection — Company A
Heatmap anomaly detection
View
Anomaly detection for PCB boards (short circuits, irregular patterns) with reduced labeling needs.
Role / Tasks
- Designed anomaly pipeline producing heatmap-based defect localization.
- Handled limited labels using anomaly learning strategy.
- Optimized post-processing for robust decisions.
Development
Language: Python
Libraries: PyTorch, OpenCV, NumPy
End Result
- Reliable PCB anomaly detection with strong localization quality.
Sebang EV Battery Inspection System with AI — Company B
U-Net segmentation · Weld measurement
View
EV battery welding inspection: pinhole/spatter detection and weld size measurement.
Role / Tasks
- Developed U-Net based segmentation for welding defect detection.
- Implemented measurement for weld size and defect severity.
- Optimized for consistent industrial performance.
Development
Language: Python
Libraries: PyTorch, U-Net, OpenCV
End Result
- Accurate welding defect detection with automated measurement output.
Camera Module & Power Button Gap Inspection — Company C
Geometric inspection · Measurement
View
Vision-based inspection system for gap measurement/verification in assembled components.
Role / Tasks
- Designed measurement pipeline for camera module and power button gap.
- Improved precision and robustness across variations.
Development
Language: Python
Libraries: OpenCV, PyTorch
End Result
- Stable, accurate gap inspection suitable for production QA.
Road Sign Detection for Automated Vehicles — Company D
Detection · Real-time
View
Real-time traffic/road sign detection for automated vehicle use-cases.
Role / Tasks
- Designed object detection pipeline for road sign recognition.
- Improved performance in diverse lighting/environment conditions.
Development
Language: Python
Libraries: PyTorch, YOLO, OpenCV
End Result
- Reliable road sign detection with real-time inference capability.
Power Line Galloping Detection System — Company E
Video monitoring · Alerts
View
Video-based monitoring of abnormal oscillations to prevent power line failures.
Role / Tasks
- Built detection using motion/time-series analysis.
- Integrated alert mechanisms for real-time monitoring.
Development
Language: Python
Libraries: OpenCV, PyTorch, NumPy
End Result
- Reliable real-time detection of galloping events.
- Improved grid stability via proactive maintenance decisions.
Transmission Tower Equipment Defect Detection — Company E
Detection + segmentation · Field robustness
View
Inspection system for tower defects (cracks, corrosion, loose components, surface damage).
Role / Tasks
- Computer vision pipeline to detect and classify defects from images.
- Deep learning models (object detection + segmentation) for localization.
- Data augmentation for lighting/weather robustness.
Development
Language: Python
Libraries: PyTorch, YOLO, OpenCV
End Result
- High-accuracy real-time defect detection across multiple failure modes.
- Improved maintenance scheduling and safety through early detection.
Skills
Tooling and frameworks used across industrial CV and deep learning systems.
Programming
Languages:
Python
MATLAB
C
C++
C#
Libraries
Keras
OpenCV
TensorFlow
PyTorch
Frameworks / Models
🎯
Detection: YOLO, Fast R-CNN, Detectron2
🔬
Segmentation: U-Net, SegNExt
🧠
Neural Networks: CNN, DNN, RNN, GAN
📱
Architectures: MobileNet, NFNet, VGG, BERT
Hardware
NVIDIA GPU
Raspberry Pi
Jetson TX2
Software
VS Code
Docker
Jupyter
MATLAB
Anaconda
PyCharm
Specialties
👁️ AOI
🎯 Defect Detection
✂️ Segmentation
🚨 Anomaly Detection
⚡ Real-time Optimization
🏭 Industrial Deployment
Publications
Peer-reviewed journals, conferences, and book chapters (grouped).
Recent Journal Highlights
- 2025 — Energies: Explainable clustered federated learning for solar energy forecasting
- 2025 — Sensors: Shapley-based adaptive weighting for collaborative learning
- 2024 — Sensors: IoT healthcare with federated learning + VAE
- 2023 — IEEE TNSM: FedCLS aggregation method
- 2021 — Applied Sciences: Small traffic sign detection (YOLOv3 improvements)
Full lists below.
Conference & Book
- ICUFN 2023 — Robust aggregation for heterogeneous federated learning
- ICAIIC 2023 — Performance efficient global training in federated learning
- ICTC 2022 — Communication efficient global training approach
- Book Chapter (2021) — Impact of AI in cardiovascular disease
Journal Publications View Full List
2026
- D. M. S. Bhatti, S. Dongho, Y. Shi and H. Nam, “Channel-Aware Clustering for Robust Wireless Federated Learning under Non-IID Data”, IEEE Op. J. Comm. Soc. (Minor Revision).
View Summary
This deep learning learning framework that improves model accuracy in wireless networks by grouping clients based on their channel-state features. This approach overcomes challenges like unreliable connections and non-uniform data, boosting validation accuracy by 22% over standard methods.
2025
- S. S. Ali, M. Ali, D.M.S. Bhatti, and B. J. Choi, “Explainable Clustered Federated Learning for Solar Energy Forecasting”, Energies, 2025.
View Summary
A deep learning approach that combines Clustered Learning with Explainable AI (XAI) to quantify feature contributions. Those XAI insights are used to weight clustering and model aggregation, making updates more transparent and improving training performance.
- D.M.S. Bhatti, M. Ali, J. Yoon and B. J. Choi, “Efficient Collaborative Learning in the Industrial IoT Using Federated Learning and Adaptive Weighting Based on Shapley Values”, Sensors, 2025.
View Summary
This work introduces a Shapley value-based adaptive weighting mechanism for deep learning in Industrial settings. By quantifying each local learning model's contribution to the global model, the method enhances learning efficiency and robustness against data heterogeneity and unreliable local deep learning models.
- S. S. Ali, M. Ali, D.M.S. Bhatti, and B. J. Choi, “dy-TACFL: Dynamic Temporal Adaptive Clustered Federated Learning for Heterogeneous Clients”, Electronics, 2025.
View Summary
This paper presents a dynamic temporal adaptive clustered deep learning framework designed to handle local learning model's heterogeneity. By dynamically adjusting clustering and aggregation based on temporal data patterns, the proposed method improves model performance and convergence speed in diverse environments.
- D. M. S. Bhatti, H. Kim, Y. Shi and H. Nam, “Layered Aggregation Approach for Communication-Efficient Federated Learning”, IEEE Tran. on Artif. Intell.
View Summary
This work introduces a layered aggregation method for deep learning that enhances communication efficiency and robustness. By structuring model updates in layers, the approach reduces overhead while maintaining high model performance under heterogeneous environment.
- D. M. S. Bhatti, Y. Shi, and H. Nam, “AirWeight-FL: Radio-Aware Aggregation for Wireless Federated Learning”, IEEE Op. J. Sig. Proc.
View Summary
This paper explores the integration of wireless environmental factors into deep learning to improve model performance. By adapting learning strategies based on channel conditions, the approach enhances convergence speed and accuracy in wireless networks.
- D. M. S. Bhatti, M. Haris, and H. Nam, “Tackling Privacy Concerns in imperfect communication-driven Federated Learning”, IEEE O. J. Comp. Soc.
View Summary
This study addresses privacy challenges in distributed deep learning over imperfect communication channels. The proposed framework incorporates privacy-preserving techniques to safeguard end user's data while ensuring effective model training despite communication constraints.
2024
- D.M.S. Bhatti and B. J. Choi, "Enhancing IoT Healthcare with Federated Learning and Variational Autoencoder", Sensors, 2024.
View Summary
This study integrates Variational Autoencoders (VAEs) with Deep Learning to enhance IoT systems. The approach addresses data privacy concerns while improving model robustness and accuracy in health monitoring applications.
- M. Haris, D. M. S. Bhatti and H. Nam, “A Fast-Convergent Hyperbolic Tangent PSO Algorithm for UAVs Path Planning”, IEEE Open Journal of Vehicular Technology, 2024.
View Summary
This paper introduces a hyperbolic tangent-based Particle Swarm Optimization algorithm tailored for robot path planning. The proposed method enhances convergence speed and path efficiency, making it suitable for dynamic environments.
- D. Kumar et al., “Performance Evaluation of ARM-based versus x86-based Processors in High Performance Computing Clusters”, Journal of Independent Studies and Research Computing.
View Summary
This study compares the performance of ARM-based and x86-based processors in high-performance computing clusters. The evaluation focuses on metrics such as computational speed, energy efficiency, and scalability to determine the suitability of each architecture for various applications.
2023
- D. M. S. Bhatti and H. Nam, “FedCLS: An Unbiased Aggregation Method for Federated Learning in a Heterogeneous Environment”, IEEE TNSM, 2023.
View Summary
This paper presentsa novel distributed deep learning aggregation method that addresses local learning model heterogeneity. By incorporating model similarity into the aggregation process, FedCLS improves model accuracy and convergence speed in diverse environments.
- M. Ali et al., “Optimization of Spectrum Utilization Efficiency in Cognitive Radio Networks”, IEEE Wireless Communications Letters, 2023.
View Summary
This study proposes an optimization framework to enhance spectrum utilization efficiency in cognitive radio networks. By leveraging advanced algorithms, the approach improves dynamic spectrum access and reduces interference among users.
2022
- D. M. S. Bhatti et al., “Detection and Spatial Correlation Analysis of Infectious Diseases Using WBAN Under Imperfect Wireless Channel”, Big Data, 2022.
View Summary
This paper explores the use of Body Area Networks for detecting infectious diseases, focusing on spatial correlation analysis under imperfect wireless channel conditions. The study highlights the challenges and solutions for reliable health monitoring in such environments.
2021
- Y. Rehman et al., “Detection of Small Size Traffic Signs Using Regressive Anchor Box Selection and DBL Layer Tweaking in YOLOv3”, Applied Sciences, 2021.
View Summary
This study enhances the YOLOv3 object detection framework to improve the detection of small-sized traffic signs. By implementing architectural modifications and training strategies, the approach achieves higher accuracy and reliability in real-world traffic scenarios.
- D. M. S. Bhatti et al., “Machine learning based Cluster Formation in Vehicular Communication”, Telecommunication Systems, 2021.
View Summary
This paper presents a machine learning-based approach for cluster formation in robotic networks. The proposed method enhances network efficiency and reliability by optimizing cluster structures based on robot mobility patterns and communication requirements.
2020
- D.M.S. Bhatti et al., “Clustering Formation in Cognitive Radio Networks Using Machine Learning”, AEU - International Journal of Electronics and Communications, 2020.
View Summary
This study introduces a machine learning-based clustering formation technique for cognitive networks. The approach enhances spectrum utilization and network performance by dynamically grouping users based on their communication patterns and channel conditions.
2019
- S. Ahmed, D.M.S. Bhatti and S. Kim, “Complexity Reduced Soft MIMO Detection Using Single Tree Search”, IJSAEM, 2019.
View Summary
This paper proposes a complexity-reduced soft MIMO detection algorithm utilizing a single tree search approach. The method aims to enhance detection performance while minimizing computational overhead, making it suitable for real-time learning systems.
- Z. U. Bhutto et al., “Efficient Method for SBI Estimation in Iterative Coded MIMO Systems”, IJCSNS, 2019.
View Summary
This study presents an efficient method for Soft Bit Information estimation in iterative coded MIMO systems. The proposed technique improves decoding accuracy and reduces computational complexity, enhancing overall system performance.
2018
- S. Ahmed, N. A. Kaimkhani, D.M.S. Bhatti, M. Sahar and K. Ali, “Virtual General Physician System using Artificial Intelligence”,Broad Research in Artificial Intelligence and Neuroscience (BRAIN) 2018.
View Summary
This paper presents a Virtual General Physician System that leverages artificial intelligence to provide preliminary medical diagnoses and health advice. The system utilizes machine learning algorithms to analyze patient symptoms and medical history, aiming to enhance accessibility to healthcare services.
- S. Ahmed, N. A. Kaimkhani, D.M.S. Bhatti, M. Zubair, H. B. Liaquat and A. Khan, “Surface Detection in Automobile using Sensors”,IJCSNS 2018.
View Summary
This study explores the use of sensors for surface detection in automobiles, aiming to enhance vehicle safety and performance. The proposed system utilizes various sensor technologies to monitor road conditions and vehicle dynamics, providing real-time feedback for improved driving experiences.
- S. B. H. Zaidi, D.M.S. Bhatti and Ihsan-Ullah, “Combinatorial Auctions for Energy Storage Sharing Amongst the Households”, Journal of Energy Storage 2018.
View Summary
This paper investigates the application of combinatorial auctions for energy storage sharing among households. The proposed auction mechanism aims to optimize the allocation of energy storage resources, promoting efficient energy usage and cost savings for participating households.
- N. Saeed, H. Nam, M. I. U. Haq and D.M.S. Bhatti, “A survey on Multidimensional Scaling”, ACM Computing Surveys 2018.
View Summary
This survey paper provides a comprehensive overview of Multidimensional Scaling (MDS) techniques, exploring their applications, methodologies, and challenges. The study highlights the significance of MDS in various fields, including data visualization, machine learning, and network analysis.
- U. U. Rajput, F. Abbas, A. Hussain, D.M.S. Bhatti and A. M. Rajpar, “Privacy Preserving Authentication Approaches in VANET: Existing Challenges and Future Directions”, IJCSNS 2018.
View Summary
This paper reviews privacy-preserving authentication approaches in Vehicular Ad Hoc Networks, discussing existing challenges and proposing future research directions. The study emphasizes the importance of secure communication protocols to protect user privacy in vehicular networks.
- N. A. Kaim Khani, S. Ahmed, D.M.S. Bhatti, M. Z. Tunio and S. Kim, “Study of MIMO Detection schemes for Emerging Wireless Communications”, IJCSNS 2018.
View Summary
This study examines various MIMO detection schemes for emerging wireless communication systems. The paper evaluates the performance of different algorithms, highlighting their strengths and weaknesses in terms of complexity, accuracy, and suitability for future wireless technologies.
- D.M.S. Bhatti, Saleem Ahmed, N. Saeed and B. Shaikh, “Efficient Error Detection in Soft Data Fusion for Cooperative Spectrum Sensing”, AEU International Journal of Electronics and Communication 2018.
View Summary
This paper proposes an efficient error detection method for soft data fusion in cooperative spectrum sensing. The approach enhances the reliability of spectrum sensing by identifying and mitigating errors in the fusion process, leading to improved detection performance in cognitive radio networks.
2017
- D.M.S. Bhatti and H. Nam, “Spatial Correlation based Analysis of Soft Combination and User Selection Algorithm for Cooperative Spectrum Sensing”, IET Communications 2017.
View Summary
This paper presents a spatial correlation-based analysis of soft combination techniques and user selection algorithms for cooperative spectrum sensing. The study aims to enhance detection performance by leveraging spatial correlation among users in cognitive radio networks.
-
F. C. K. Ngayahala, S. Ahmed, D. M. S. Bhatti, N. Saeed, M. Rashid and N. A. Kaimkhani, “Low-Complexity SIC-MMSE for Joint Multiple-input Multiple-output Detection”, Springer Journal of Communications Technology and Electronics 2017.
View Summary
This study introduces a low-complexity Successive Interference Cancellation Minimum Mean Square Error (SIC-MMSE) algorithm for joint MIMO detection. The proposed method aims to improve detection accuracy while reducing computational complexity, making it suitable for real-time wireless communication systems.
- D.M.S. Bhatti, N. Saeed and H. Nam, “Fuzzy C-means Clustering and Energy Efficient Cluster Head Selection for Cooperative Sensor Network”, Sensors 2016.
View Summary
This paper proposes a fuzzy C-means clustering approach combined with an energy-efficient cluster head selection algorithm for cooperative sensor networks. The method aims to enhance network longevity and data transmission efficiency by optimizing cluster formation and head selection processes.
2016
- N. Saeed. M. I. U Haq and D. M. S. Bhatti, “Efficient Localization Algorithm for Wireless Sensor Networks Using Levenberg-Marquardt Refinement”, Ad hoc & Sensor Wireless Networks 2016.
View Summary
This paper presents an efficient localization algorithm for wireless sensor networks that utilizes Levenberg-Marquardt refinement. The proposed method aims to improve localization accuracy while minimizing computational overhead, making it suitable for resource-constrained sensor networks.
Conference Proceedings View Full List
2023
- D.M.S. Bhatti and H. Nam, “A Robust Aggregation Approach for Heterogeneous Federated Learning”, ICUFN 2023, Paris, France.
- D.M.S. Bhatti and H. Nam, “A performance Efficient Approach of Global Training in Federated Learning”, ICAIIC 2023, Bali, Indonesia.
2022
- D.M.S. Bhatti, M. Haris and H. Nam, “A Communication Efficient Approach of Global Training in Federated Learning,” ICTC 2022, Jeju, Korea.
- M. Haris, D.M.S. Bhatti and H. Nam, “Improved PSO algorithm …”, ICTC 2022, Jeju, Korea.
2018 / 2017 / 2014
- D.M.S. Bhatti, S. Ahmed and S. Kim, “Design of Cooperative Spectrum Sensing using MIMO …”, ISITC 2018, Jeonju, Korea.
- D.M.S. Bhatti et al., “Channel Error Detection …”, ICTC 2018, Jeju, Korea.
- W. Ahmad et al., “Localization Of VANETs …”, iComet 2018, Sukkur, Pakistan.
- D.M.S. Bhatti et al., “Fuzzy C-means …”, ICTC 2017, Jeju, Korea.
- D.M.S. Bhatti and H. Nam, “Correlation Based Soft Combining …”, IEEE VTC Spring 2014, Seoul.
Book Chapter View Full List
- M. Khan, S. Ahmed, P. Kumar and D.M.S. Bhatti, “Impact of Artificial Intelligence in Cardiovascular Disease,” Scrivener Publishing, 2021.
Recognition
Professional memberships, reviewing activity, funded academic projects, and awards.
Professional Memberships
- Senior Member — IEEE
- Professional Engineer — Pakistan Engineering Council (PEC)
- Global Member — KICS (Korean Institute of Communications and Information Sciences)
Awards & Honors
- Award for organizing MTSET-2017 (Pakistan).
- HEC (GoP) Scholarship for MS–PhD study in South Korea.
Reviewer of Journals View Full list
- IEEE Transactions on Cybernetics
- IEEE TETCI
- IEEE TNSM
- IEEE TASE
- IET Signal Processing
- Electronics Letters
- Telecommunication Systems
- IET Communications
- IEEE Access
- IET Radar, Sonar & Navigation
- EURASIP JWCN
- Wireless Personal Communications
- Transactions on Emerging Telecommunications Technologies
- Wireless Communication and Mobile Computing
- Sensors
- Mathematics
- IEEE Systems Journal
- IEEE Open Journal of the Communications Society
Academic Projects View Full list
- Deep Learning based Integrated MEC-HCRAN Model for 6G — funded by NRF (Brain Pool), South Korea.
- Detection and Decoding in Coded MIMO System for 5G — funded by HEC, GoP.
- Whole body fatigue evaluation using EMG and heart rate — funded by HEC, GoP.
- Channel switching method in 5G for cognitive radio — funded by HEC, GoP.
- Ultra-lightweight wearable devices via virtualization cloud computing — funded by NRF, South Korea.
- Efficient coexistence of devices in ISM band — funded by Ministry of Science, Education and Technology, South Korea.
Contact
Let’s connect.
Email
GitHub
LinkedIn
📞 Call (US)
📞 Call (KR)
More contact
Emails:
saqibbhatti128@gmail.com
saqib@hyvision.co.kr
saqib@hanyang.ac.kr
Phones:
+82-10-4997-1260
+1-323-723-3653