VIKI

Artificial Intelligence - Computer Vision

AI Traffic Monitoring Application with Object Detection and Counting

This project uses CNN-based object detection to count vehicles crossing a traffic signal and display the number of vehicles detected, categorized by type, in a tabular format. The application uses a pretrained YOLO (You Only Look Once) model for object detection.

GitHub More Info

Explainable Artificial Intelligence : XAI

Medical AI Diagnosis Evaluation Application

An interactive web-based interface for collecting human feedback on medical diagnoses made by AI models. The specific use case focuses on a fictional condition called Osteocuboid Degeneration (OCDegen) in imaginary creatures known as Blockies. The goal is to explore and evaluate human-AI collaboration in high-stakes decision-making scenarios, using explainability and trust as key design components.

GitHub

Artificial Intelligence - Computer Vision

Handwritten Digit Recognition App Using CNN

An application that recognizes handwritten digits using a Convolutional Neural Network (CNN). The model is trained on the MNIST dataset and integrated into a user-friendly GUI built with Python.

GitHub More Info

Handwritten Digit Recognition Application using CNN

A simple and intuitive application that recognizes handwritten digits using a Convolutional Neural Network (CNN). The model is trained on the MNIST dataset and deployed with a user-friendly PyTkinter GUI.

Getting Started

To get started with the Handwritten Digit Recognition App, follow these steps:

Clone the repository
Navigate to the project directory
Install the required dependencies
Run the application

Clone the Repository


git clone https://github.com/neoviki/ai.vision.handwritten.digit.recognizer.cnn.mnist.git
cd ai.vision.handwritten.digit.recognizer.cnn.mnist

Install Dependencies


chmod +x install.dependencies.sh
./install.dependencies.sh

Run the Application


chmod +x run.app.sh
./run.app.sh

Reference


@article{lecun2010mnist,
  title={MNIST handwritten digit database},
  author={LeCun, Yann and Cortes, Corinna and Burges, CJ},
  journal={ATT Labs [Online]. Available: http://yann.lecun.com/exdb/mnist},
  volume={2},
  year={2010}
}

For more details on this project, visit https://github.com/neoviki/ai.vision.handwritten.digit.recognizer.cnn.mnist

Sensor Module Design

Tactile Trackpad – High-Density Pressure Sensing Module for Laptop and Gaming Input

I developed a Tactile Trackpad, a tactile sensing module designed to explore the use of closely packed barometer-based sensors for high-resolution touch and pressure detection. Its dense sensor arrangement enables precise spatial and force sensitivity, making it suitable for next-generation laptop trackpads and gaming interfaces where accurate, responsive, and pressure-aware input is essential.

More Info

Tactile Trackpad – High-Density Pressure Sensing Module for Laptop and Gaming Input

This tactile trackpad module features a high-density array of 36 MEMS barometric pressure sensors within a compact 50 × 65 mm form factor, enabling high-resolution tactile sensing. Although primarily designed as a tactile trackpad, the platform has potential applications in robotics, advanced human–machine interfaces, haptic research, and other pressure-sensing systems.

The primary objective of this work is to investigate the performance characteristics of dense pressure-sensor arrays, including achievable sampling frequency, spatial resolution, sensitivity, noise behavior, and potential hysteresis effects. The study also explores other factors that may influence measurement accuracy, responsiveness, and overall system performance in high-density tactile sensing configurations.

In addition to the tactile trackpad module, a dedicated controller board has been developed to interface with the sensor array and facilitate data acquisition. The controller is responsible for sensor communication, data collection, and transfer to a host system for further processing and analysis. The complete controller design, including schematics, PCB layout files, firmware, and related documentation, has been open-sourced and is available on GitHub

At present, only the basic functionality of the tactile sensing module has been validated, as development was temporarily paused due to commitments to other projects. Several aspects of the system remain under development, including the communication protocol, firmware enhancements, and the silicone surface molding required for the final tactile trackpad interface.

Figure 1: Shows the populated tactile sensing module with MEMS barometric pressure sensors.

Tactile Sensing Module with 36 Sensors — **Figure 1**

Board Layout Top and Bottom Layer — **Figure 2:** Top (a) and bottom (b) layers of the tactile trackpad module's board layout with 36 pressure sensors.

The schematics, evaluation results, and additional details will be shared once testing and evaluation are complete. I’m documenting the progress so far, but since this is a personal project, I need to prioritize other commitments for the time being.

Possible Applications:

Possible applications of this tactile sensing module include robotics, haptic feedback systems, gaming interfaces, smart input devices, gesture-recognition systems, and other applications that require high-resolution tactile sensing.

Tactile fingertip mounted on InMoov robotic hand

Robotic Sensor Module Design

Artificial Fingertip with Tactile Sensing for Humanoid Robots

I developed a high-density tactile fingertip capable of sensing pressure and vibration in a compact form factor. It was designed for humanoid robotic hands and developed as part of my research in tactile sensing.

More Info

High-Density Tactile Sensing Artificial Fingertip for Humanoids and Prosthetics

Figure 1

This project focuses on the design and development of a high-density tactile fingertip module intended for humanoid robot and prosthetic hand applications. The module is capable of measuring pressure exerted on its surface through 22 individual pressure sensors distributed across the fingertip area. It is developed using Flexible Printed Circuit Board (Flex-PCB) technology.

In this project, an origami technique is employed to fold a flat, paper-like flexible tactile sensing module into a three-dimensional shape that mimics the form of a human fingertip. Sensor data acquisition is handled by an onboard 32-bit, low-power microcontroller, and the module communicates using the SPI protocol.

In this project, an origami technique is employed to fold a flat, paper-like flexible tactile sensing module into a three-dimensional shape that mimics the form of a human fingertip. Sensor data acquisition is handled by an onboard 32-bit, low-power microcontroller, and the module communicates using the SPI protocol.

The development of this module presented a number of challenges, particularly in mechanical design and electronics. Prior to this project, I had limited experience with mechanical Computer-Aided Design (CAD). I had to learn how to design both mechanical structures and electronic schematics, as well as manage the manufacturing and integration processes.

Despite these challenges, a functional prototype of the tactile fingertip was developed. While the current version is not yet optimized for production, it is capable of capturing tactile data. Ongoing work includes further optimization of the design, data collection, and analysis.

The dimensions of the fingertip module closely match those of a typical human fingertip, enabling applications in humanoid robots and prosthetic systems.

CAD Model

Animation: The animated CAD model on the left shows the structural design and assembly concept of the high-density tactile fingertip module. The model was created using Siemens Solid Edge. The sheet metal environment was used to design the foldable flexible-PCB geometry, while the part environment was used to integrate additional components such as pressure sensors and the onboard microcontroller.

Board Layout

The schematics and board layout of the tactile fingertip module were designed using Autodesk Eagle EDA. It was a challenging task, as a large number of vias had to be managed within a very small area. The board layout includes approximately 218 vias on a two-layer flexible PCB, with dimensions around 32 mm × 74 mm.

Figure 2: Board layout of the tactile fingertip module.

Fully Populated Tactile Fingertip Module

The tactile fingertip module is manufactured using 2-layer flexible PCB technology with a thickness of 0.11 mm. After fabrication, surface-mount technology (SMT) is used to populate the electronic components. Figure 3 depicts the fully populated tactile fingertip flexible PCB placed next to a 10-cent coin, highlighting the size difference and the complexity of the design.

Figure 3: Fully fabricated and populated tactile fingertip module in flat form factor.

Origami

A technique called origami, a traditional Japanese art of folding paper to form intricate shapes, is applied here to transform the flat version of the flexible tactile fingertip module into a 3D shape resembling a fingertip. Although origami is a complex art and I don't have much expertise in it, I attempted a simplified version to apply the technique as best as I could. The figure below shows the fingertip after being folded using origami techniques, including both the top (Figure 4a) and bottom (Figure 4b) views. The bottom view represents the fleshy part of the fingertip.

Figure 4: Top (a) and Bottom (b) views of the tactile fingertip module folded into a 3D humanoid fingertip-like shape using origami techniques.

Tactile Fingertip Mounted on an InMoov Robotic Hand

Figure 5: High-density tactile fingertip module mounted on an InMoov humanoid robot hand. This demonstration is for illustrative purposes only. The silicone surface molding and supporting structure are still in progress. At this stage, only the electronics and basic sensor sampling have been tested successfully.

Open Source

Parts of this project have been open-sourced, including the tactile controller module and the initial evaluation version of the flexible tactile sensor module with two sensors. The currently available open-source repositories are listed below:

Tactile Controller Module
Source: https://github.com/neoviki/tactile.controller.module
Flexible Tactile Sensor with Dual Sensors
Source: https://github.com/neoviki/flexible.tactile.sensing.module.dual.sensors

Flexible Tactile Sensor with Dual Sensors:

Figure 7

Figure 7, shows the flexible dual-sensor module developed to evaluate hysteresis behavior in MEMS barometric pressure sensors before continuing the development of the fingertip-shaped tactile sensor. After obtaining satisfactory results with minimum or no significant hysteresis from this evaluation module, the current fingertip sensor with 22 barometric sensors was developed, as shown in Figures 3 and 5.

This flexible dual-sensor module is mounted on a triangular prism-shaped base, with a silicone surface formed above the sensors to mimic the behavior of human skin. More details about the image, CAD model, sensor data, and related documentation will be published soon.

For now, the EDA design files, including the schematics and board layout, have been open-sourced and are available here: https://github.com/neoviki/flexible.tactile.sensing.module.dual.sensors

Future Work

Further development is planned, including data collection, sensor evaluation, and communication firmware optimization. Future updates may include:

1. Detailed experimental results
2. Sensor performance analysis
3. Sampling-frequency and spatial-resolution evaluation
4. Additional schematics, data, and documentation

At the moment, these materials have not been published because the project is currently paused due to my focus on other work. Once development resumes and the results and documentation reach a satisfactory level, I plan to make them available.

Embedded Controller Module

Tactile Controller

A 32-bit embedded controller module developed to efficiently retrieve and process tactile sensor data.

GitHub More Info

Computer Networks - IoT

IoT Data Transmission Suite

An IoT Data Transmission Suite with a server daemon and client library, designed for IoT applications. Traffic is transmitted over the HTTP/HTTPS protocol. It supports homegrown plant monitoring and vehicle status tracking, offering a cost-effective alternative to MQTT for lightweight, low-traffic communication. This suite is ideal for simple IoT ecosystems where frequent or intensive data exchange is not required.

GitHub More Info

TUI - Terminal User Interface

Terminal CSV Editor

A Linux terminal-based CSV editor written in Go. It features a Terminal UI (TUI) for viewing and editing CSV files and is fully keyboard-driven - no mouse required.

GitHub

Other Projects

List of Other Projects I have Worked On

I’ve worked on a variety of projects based on my interests and the challenges I encountered along my journey. These projects span across AI, Computer Networking, Linux, GUI, Terminal tools, as well as Robotics and Electronics. I’ve documented and published them on GitHub. This section includes a list of those projects along with their corresponding GitHub URLs.

GitHub More Info

List of Projects

I've had the opportunity to work on projects across a range of fields, including telecom, vehicle telematics, IoT, computer vision, and robotic sensor design - covering areas such as computer science, electronics, and robotics. These projects were practical solutions to challenges I encountered in both day-to-day computing and industry environments. They include Linux utilities, drivers that optimize and streamline personal and industrial workflows, Artificial Intelligence driven applications and command-line tools using `awk`, `sed`, and regex for data splitting, filtering, manipulation, and interpretation. I've also developed C/Python libraries and packages, as well as custom hardware modules such as tactile sensors for robotic sensing.

Below is a list of selected projects, all of which I've published on GitHub.

Nr	Project Details	Reference
1	ai.vision.realtime.traffic.monitoring	Link
2	flexible.tactile.sensing.module.dual.sensors	Link
3	tactile.controller.module	Link
4	ai.vision.traffic.monitor.app	Link
5	ai.vision.handwritten.digit.recognizer.cnn.mnist	Link
6	ai.vision.image.classifier.cnn.cifar10	Link
7	ai.ml.classification.knn	Link
8	ai.vision.face.detector	Link
9	explainable.ai.evalution.app	Link
10	linux.over.the.air.app.updater	Link
11	linux.tcp.port.tunneler	Link
12	linux.remote.debugger.utility	Link
13	linux.app.installer.utility	Link
14	linux.embed.dir.to.bash.script	Link
15	linux.rpi.samba.file.share	Link
16	linux.rpi.vnc.server	Link
17	linux.rpi.wifi.access.point	Link
18	linux.wifi.monitor	Link
19	linux.detect.usb.flash.drive	Link
20	mesos.distributed.cluster.deployer	Link
21	proxmox.virtualization.cluster.deployer	Link
22	ceph.distributed.storage.cluster.deployer	Link
23	compress	Link
24	versionsnap	Link
25	graphical.interface.grid.eye.sensor.electron	Link
26	graphical.interface.gyroscope.sensor	Link
27	graphical.interface.robotic.gripper	Link
28	graphical.interface.serial.monitor	Link
29	iot.data.exchange.suite	Link
30	eagle.library.pic32mm0256gpm036.uqfn.40pin	Link
31	eagle.library.pic32mm0256gpm028.uqfn.28pin	Link
32	arduino.AMG8833.grid.eye.sensor	Link
33	arduino.Bosch.BMP384.pressure.sensor	Link
34	arduino.VL6180X.time.of.flight.distance.sensor	Link
35	arduino.esc.controller	Link
36	audio.joiner	Link
37	audio.multiplier	Link
38	video.splitter	Link
39	video.to.gif	Link
40	automate.transaction.on.ebay	Link
41	crop.image	Link
42	docker.wrapper.commands	Link
43	gps.coordinates.renderer.osm	Link
44	lib.json	Link
45	lib.xml.parser	Link
46	ipc.filelock	Link
47	ipc.messenger	Link
48	ipc.shared.memory	Link
49	mac.osx.tabrun	Link
50	netcopy	Link
51	rand.file.tagger	Link
52	terminate	Link
53	uscreen	Link
54	website.backup.and.restore.utility	Link
55	html.ui.generator	Link
56	ui.python.tkinter.wrapper	Link

About Me

I am Viki (VN), a consulting software and solutions specialist with experience in building solutions involving artificial intelligence, computing clusters, networked systems, sensors, and robotics. I hold a Master’s degree specializing in Artificial Intelligence and Robotics from Germany, and a Bachelor’s degree in Computer Science Engineering. My GitHub repository [ Ref] and this website document the open-source and partially open-source solutions I have developed over the years.

Selected Solutions I Developed

The solutions I developed include the end-to-end design and development of tactile sensor modules for humanoid robots [Ref: 1, 2]; and a tactile trackpad [Ref: 1, 2]; for gaming applications, Artificial Intelligence applications [Ref: 1, 2, 3, 4]; Linux applications and libraries [Ref: 1, 2, 3, 4]; computing cluster infrastructure deployment and management [Ref: 1, 2, 3]; distributed storage infrastructure deployment and management [Ref: 1, 2, 3]; IoT solutions [Ref: 1, 2]; and containerized Docker applications [Ref: 1, 2]; One of the solutions I developed is currently deployed across around 10,000 connected Linux-based edge devices in Europe. [Ref].

Skills

I have experience in computing and its interdisciplinary areas, including programming; computer networking; Linux-based application development[Ref: 1, 2, 3, 4, 5, 6]; and Linux device-driver development; Linux boot-time optimization; Application containerization with Docker [Ref: 1, 2]; Artificial Intelligence-Enabled Application Development (CNN, XAI) [Ref: 1, 2, 3, 4]. I have developed solutions involving OSI communication protocols, including TCP/IP, MQTT, and SSH [Ref: 1, 2]. Alongside software development, I have hands-on experience designing robotic sensor modules and controllers using KiCAD and Eagle [Ref: 1, 2, 3, 4], and I also work with CAD tools such as Solid Edge and FreeCAD [Ref].

Professional Experience

I have more than 14 years of experience in the software industry, including nearly a decade at a well-known computer networking company based in California. For over five years, I have worked as a consulting software architect and manager, supporting clients across Europe and the UK. I have collaborated with and led engineers from diverse cultural and professional backgrounds, including teams from France, the UK, Russia, and South Asia.

Tools I Use Regularly

For software development, I primarily write in C [Ref: 1, 2, 3, 4], Python [Ref: 1, 2], and Bash [Ref: 1, 2, 3, 4, 5, 6], AWK, PHP [Ref: 1, 2], and JavaScript [Ref: 1, 2, 3, 4]. For sensor module design, I work with Eagle and KiCAD [Ref: 1, 2, 3, 4]. For network protocol debugging, I use Wireshark and logic analyzers, and for Linux application crash analysis, I use GDB. For CAD modeling, I work with Solid Edge and FreeCAD[Ref]. I have good hands-on experience with all of these tools.

Contact Me

You can get in touch with me at hello@viki.design