Recycling Collection Service
+Recycling Collection Service
An AI app powered by an object detection model to detect and request the pick up for those recyclable objects.
Read MoreRecycling C
- Electic Vehicles in Washington State, US
+ Electic Vehicles in Washington State, US
A Tableau story with different dashboards about the EV population growth in Washington.
Read More
@@ -120,8 +120,8 @@ 
- 1st Place Future Mobility Challenge
- Exploring different CNN models to classify traffic sign images. $500 Cash prize
+ 1st Place Future Mobility Challenge
+ Exploring different CNN models to classify traffic sign images. $500 Cash price
Read More
@@ -131,7 +131,7 @@ 
- English Speaking AI-Examiner
+ English Speaking AI-Examiner
An app that allows users to answer questions in English and receive feedback about how well they answered.
Read More
diff --git a/others designs/html5up-read-only/index.html b/others designs/html5up-read-only/index.html
index d64d19b..2ecaac7 100644
--- a/others designs/html5up-read-only/index.html
+++ b/others designs/html5up-read-only/index.html
@@ -99,7 +99,7 @@ Projects
- Recycling Collection Service
+ Recycling Collection Service
An AI app powered by an object detection model to detect and request the pick up for those recyclable objects.
Read More
@@ -109,7 +109,7 @@ Recycling C
- Electic Vehicles in Washington State, US
+ Electic Vehicles in Washington State, US
A Tableau story with different dashboards about the EV population growth in Washington.
Read More
@@ -120,7 +120,7 @@
- 1st Place Future Mobility Challenge
+ 1st Place Future Mobility Challenge
Exploring different CNN models to classify traffic sign images. $500 Cash price
Read More
@@ -131,7 +131,7 @@
- English Speaking AI-Examiner
+ English Speaking AI-Examiner
An app that allows users to answer questions in English and receive feedback about how well they answered.
Read More
diff --git a/project_details_CTS.html b/project_details_CTS.html
index 94c9252..4ce5927 100644
--- a/project_details_CTS.html
+++ b/project_details_CTS.html
@@ -13,23 +13,52 @@
- Classifying Traffic Sign
+ Future Mobility Challenge: Deep Learning and Computer Vision for Autonomous Vehicles (AVs)
+ Challenge Mentor: Ryan Ahmed, Ph.D., MBA Professor, McMaster University
- Exploring different CNN models to classify traffic signs.
-
-
-
-
+
+ Github
+
- Project Details
- Include more detailed information about the project here.
+ Project Details
+ The automotive industry is going through a paradigm shift from conventional, human-driven vehicles into Autonomous,Artificial Intelligence (AI)-powered vehicles. AVs offer a safe, efficient, and cost-effective solution that will dramaticallyredefine the future of human mobility. AVs are expected to save over half a million lives and generate enormous economicopportunities in excess of $1 trillion dollars by 2035. From GM’s Cruise and Google’s autonomous car (Waymo) to Uber’sself-driving car-sharing service, the automotive industry is on a billion-dollar quest to deploy the most technologicallyadvanced vehicles on the road.
+ In this challenge, you are tasked to train and evaluate several deep CNNs to classify traffic sign images.
+ The dataset contains colored 32 x 32 pixels images with 43 different traffic sign classes.
+ Images are divided into 34799 images for training, 12630 for testing and 4410 for validation.
+
+
+
+ 
+
+
+
+ Challenge Deliverables:
+ - Research AlexNet Convolutional Neural Network, draw the network architecture, and indicate the use of each of the layers such as convolution/feature extraction, max pooling, and flattening layers.
+ - Visualize a sample image from each class in the dataset. Display the corresponding label and perform a sanity check.
+ - Train a CNN based on AlexNet to classify traffic signs. Train the model using 15 epochs and plot the network accuracy vs. the number of epochs.
+ - Test the trained CNN and evaluate its performance on the testing (holdout) dataset. Note that the testing dataset has never been seen by the model during training.
+ - Fine-tune the trained model by training it on additional datasets. Feel free to collect data from the internet or using a mobile device.
+ - Explore 3 different ways to improve the network accuracy such as increasing the number of epochs, adding additional convolutional/max-pooling layers, or adding dropout layers. Retrain the network and display the results. Any reasonable answer should be sufficient.
+ - Build 3 different deep convolutional neural networks with various architectures. Feel free to choose the number of layers, number of kernels (feature detectors), number of dense (Fully-connected) layers, number of neurons in the dense layer, activation functions, regularization such as dropout..etc. Retrain the network and plot the results.
+ - Test the trained deep CNNs on brand-new images. This might involve collecting traffic sign data and evaluating the system's performance and make adjustment as necessary.
+
+
+
+
+
+
+
- Additional Content
- You can add more sections or content as needed.
+ Additional Content
+ 1st Place Prize (Value): $500
+
+
+ *I'm the third person from the right to the left.
+
diff --git a/project_details_ESAI.html b/project_details_ESAI.html
index 574ec88..d43b5bf 100644
--- a/project_details_ESAI.html
+++ b/project_details_ESAI.html
@@ -13,9 +13,11 @@
- English Speaking AI-Examiner
+ English Speaking AI-Examiner
+ Github
+
An app that allows users to answer questions in English and receive feedback about how well they answered.
@@ -23,13 +25,26 @@ English Speaking AI-Examiner
- Project Details
- Include more detailed information about the project here.
+ Project Details
+ As a non-native English speaker who migrated to Canada, I've been on a mission to improve my English skills. I was motivated to enhance my English speaking skills, but the high costs of language courses discouraged me. That's when I got the idea to create an app that could help me improve without financial constraints.
+
+ What it does
+ This application aims to provide a comprehensive language learning experience, focusing specifically on improving English speaking skills for test takers, such as those preparing for the IELTS/CELPIP exam.
+ The application utilizes the Whisper model to transcribe the user's spoken responses. To provide a comprehensive evaluation, the application leverages a Language Learning Model (LLM) as well.
+ The LLM takes both the transcribed text and the corresponding question as input. By considering the context of the question and the user's response, the LLM generates an assessment of the given answer.
+ This assessment includes analyzing grammar, vocabulary usage, coherence, and fluency, among other language aspects.
+ How I built it
+ I started developing the project using Google Colab, I integrated the "Whisper" model from OpenAI with a Language Learning Model (LLM) to provide feedback on English language usage.
+ It was an exciting journey as I combined these technologies to create a useful tool for language learners.
+
- Additional Content
- You can add more sections or content as needed.
+ Additional Content
+ Flawless English: Master the Language with Precision and Confidence Using AI.
+
+
+
diff --git a/project_details_EV.html b/project_details_EV.html
index 6555816..89b054a 100644
--- a/project_details_EV.html
+++ b/project_details_EV.html
@@ -16,15 +16,28 @@
Electric Vehicles in Washington State, US
+ Github
+
A Tableau story with different dashboards about the EV population growth in Washington.
+ 
+
- 
- Project Details
+ Project Details
The US Department of Energy made significant effort in battery development which resulted in 50% cost of the battery and within 4 years more affordable EVs were made. Today, consumers now have multitude of choices when buying EVs ranging from Hybrids, plug-in-hybrids, and electric across the world. This project will help to explore the growth rate of EV cars in Washington state while also exploring the performance of electric vehicles among diverse Manufacturers.
@@ -44,11 +57,24 @@ Project Details
Compare the retail prices vs the efficiency.
3. Provides a guide for potential buyers of EVs
+
+ 
+
- Additional Content
+ Additional Content
You can add more sections or content as needed.
diff --git a/project_details_rs.html b/project_details_rs.html
index 5472e09..ac61f69 100644
--- a/project_details_rs.html
+++ b/project_details_rs.html
@@ -17,9 +17,11 @@
Recycling Collection Service
+ Github
+
- Project Description
+ Project Description
Capstone Project for Data Analytics for Business at St. Clair College
@@ -45,7 +47,7 @@ Project Description
- App UI
+ App UI
Request tab
@@ -75,13 +77,13 @@ App UI
- Project technical Details
+ Project technical Details
This section can contain more detailed information about the project, such as the technologies used, challenges faced, and the impact of the project.
- Code Snippets
+ Code Snippets
You can showcase relevant code snippets or any other content related to the project.
// Insert code snippet here
Electic Vehicles in Washington State, US
+Electic Vehicles in Washington State, US
A Tableau story with different dashboards about the EV population growth in Washington.
Read More
- 1st Place Future Mobility Challenge
- Exploring different CNN models to classify traffic sign images. $500 Cash prize
+ 1st Place Future Mobility Challenge
+ Exploring different CNN models to classify traffic sign images. $500 Cash price
Read More
@@ -131,7 +131,7 @@
- English Speaking AI-Examiner
+ English Speaking AI-Examiner
An app that allows users to answer questions in English and receive feedback about how well they answered.
Read More
diff --git a/others designs/html5up-read-only/index.html b/others designs/html5up-read-only/index.html
index d64d19b..2ecaac7 100644
--- a/others designs/html5up-read-only/index.html
+++ b/others designs/html5up-read-only/index.html
@@ -99,7 +99,7 @@ Projects
- Recycling Collection Service
+ Recycling Collection Service
An AI app powered by an object detection model to detect and request the pick up for those recyclable objects.
Read More
@@ -109,7 +109,7 @@ Recycling C
- Electic Vehicles in Washington State, US
+ Electic Vehicles in Washington State, US
A Tableau story with different dashboards about the EV population growth in Washington.
Read More
@@ -120,7 +120,7 @@
- 1st Place Future Mobility Challenge
+ 1st Place Future Mobility Challenge
Exploring different CNN models to classify traffic sign images. $500 Cash price
Read More
@@ -131,7 +131,7 @@
- English Speaking AI-Examiner
+ English Speaking AI-Examiner
An app that allows users to answer questions in English and receive feedback about how well they answered.
Read More
diff --git a/project_details_CTS.html b/project_details_CTS.html
index 94c9252..4ce5927 100644
--- a/project_details_CTS.html
+++ b/project_details_CTS.html
@@ -13,23 +13,52 @@
- Classifying Traffic Sign
+ Future Mobility Challenge: Deep Learning and Computer Vision for Autonomous Vehicles (AVs)
+ Challenge Mentor: Ryan Ahmed, Ph.D., MBA Professor, McMaster University
- Exploring different CNN models to classify traffic signs.
-
-
-
-
+
+ Github
+
- Project Details
- Include more detailed information about the project here.
+ Project Details
+ The automotive industry is going through a paradigm shift from conventional, human-driven vehicles into Autonomous,Artificial Intelligence (AI)-powered vehicles. AVs offer a safe, efficient, and cost-effective solution that will dramaticallyredefine the future of human mobility. AVs are expected to save over half a million lives and generate enormous economicopportunities in excess of $1 trillion dollars by 2035. From GM’s Cruise and Google’s autonomous car (Waymo) to Uber’sself-driving car-sharing service, the automotive industry is on a billion-dollar quest to deploy the most technologicallyadvanced vehicles on the road.
+ In this challenge, you are tasked to train and evaluate several deep CNNs to classify traffic sign images.
+ The dataset contains colored 32 x 32 pixels images with 43 different traffic sign classes.
+ Images are divided into 34799 images for training, 12630 for testing and 4410 for validation.
+
+
+
+
+
+
+
+ Challenge Deliverables:
+ - Research AlexNet Convolutional Neural Network, draw the network architecture, and indicate the use of each of the layers such as convolution/feature extraction, max pooling, and flattening layers.
+ - Visualize a sample image from each class in the dataset. Display the corresponding label and perform a sanity check.
+ - Train a CNN based on AlexNet to classify traffic signs. Train the model using 15 epochs and plot the network accuracy vs. the number of epochs.
+ - Test the trained CNN and evaluate its performance on the testing (holdout) dataset. Note that the testing dataset has never been seen by the model during training.
+ - Fine-tune the trained model by training it on additional datasets. Feel free to collect data from the internet or using a mobile device.
+ - Explore 3 different ways to improve the network accuracy such as increasing the number of epochs, adding additional convolutional/max-pooling layers, or adding dropout layers. Retrain the network and display the results. Any reasonable answer should be sufficient.
+ - Build 3 different deep convolutional neural networks with various architectures. Feel free to choose the number of layers, number of kernels (feature detectors), number of dense (Fully-connected) layers, number of neurons in the dense layer, activation functions, regularization such as dropout..etc. Retrain the network and plot the results.
+ - Test the trained deep CNNs on brand-new images. This might involve collecting traffic sign data and evaluating the system's performance and make adjustment as necessary.
+
+
+
+
+
+
+
- Additional Content
- You can add more sections or content as needed.
+ Additional Content
+ 1st Place Prize (Value): $500
+
+
+ *I'm the third person from the right to the left.
+
diff --git a/project_details_ESAI.html b/project_details_ESAI.html
index 574ec88..d43b5bf 100644
--- a/project_details_ESAI.html
+++ b/project_details_ESAI.html
@@ -13,9 +13,11 @@
- English Speaking AI-Examiner
+ English Speaking AI-Examiner
+ Github
+
An app that allows users to answer questions in English and receive feedback about how well they answered.
@@ -23,13 +25,26 @@ English Speaking AI-Examiner
- Project Details
- Include more detailed information about the project here.
+ Project Details
+ As a non-native English speaker who migrated to Canada, I've been on a mission to improve my English skills. I was motivated to enhance my English speaking skills, but the high costs of language courses discouraged me. That's when I got the idea to create an app that could help me improve without financial constraints.
+
+ What it does
+ This application aims to provide a comprehensive language learning experience, focusing specifically on improving English speaking skills for test takers, such as those preparing for the IELTS/CELPIP exam.
+ The application utilizes the Whisper model to transcribe the user's spoken responses. To provide a comprehensive evaluation, the application leverages a Language Learning Model (LLM) as well.
+ The LLM takes both the transcribed text and the corresponding question as input. By considering the context of the question and the user's response, the LLM generates an assessment of the given answer.
+ This assessment includes analyzing grammar, vocabulary usage, coherence, and fluency, among other language aspects.
+ How I built it
+ I started developing the project using Google Colab, I integrated the "Whisper" model from OpenAI with a Language Learning Model (LLM) to provide feedback on English language usage.
+ It was an exciting journey as I combined these technologies to create a useful tool for language learners.
+
- Additional Content
- You can add more sections or content as needed.
+ Additional Content
+ Flawless English: Master the Language with Precision and Confidence Using AI.
+
+
+
diff --git a/project_details_EV.html b/project_details_EV.html
index 6555816..89b054a 100644
--- a/project_details_EV.html
+++ b/project_details_EV.html
@@ -16,15 +16,28 @@
Electric Vehicles in Washington State, US
+ Github
+
A Tableau story with different dashboards about the EV population growth in Washington.
+
+
-
- Project Details
+ Project Details
The US Department of Energy made significant effort in battery development which resulted in 50% cost of the battery and within 4 years more affordable EVs were made. Today, consumers now have multitude of choices when buying EVs ranging from Hybrids, plug-in-hybrids, and electric across the world. This project will help to explore the growth rate of EV cars in Washington state while also exploring the performance of electric vehicles among diverse Manufacturers.
@@ -44,11 +57,24 @@ Project Details
Compare the retail prices vs the efficiency.
3. Provides a guide for potential buyers of EVs
+
+
+
- Additional Content
+ Additional Content
You can add more sections or content as needed.
diff --git a/project_details_rs.html b/project_details_rs.html
index 5472e09..ac61f69 100644
--- a/project_details_rs.html
+++ b/project_details_rs.html
@@ -17,9 +17,11 @@
Recycling Collection Service
+ Github
+
- Project Description
+ Project Description
Capstone Project for Data Analytics for Business at St. Clair College
@@ -45,7 +47,7 @@ Project Description
- App UI
+ App UI
Request tab
@@ -75,13 +77,13 @@ App UI
- Project technical Details
+ Project technical Details
This section can contain more detailed information about the project, such as the technologies used, challenges faced, and the impact of the project.
- Code Snippets
+ Code Snippets
You can showcase relevant code snippets or any other content related to the project.
// Insert code snippet here
1st Place Future Mobility Challenge
-Exploring different CNN models to classify traffic sign images. $500 Cash prize
+1st Place Future Mobility Challenge
+Exploring different CNN models to classify traffic sign images. $500 Cash price
Read More
English Speaking AI-Examiner
+English Speaking AI-Examiner
An app that allows users to answer questions in English and receive feedback about how well they answered.
Read MoreProjects
Recycling Collection Service
+Recycling Collection Service
An AI app powered by an object detection model to detect and request the pick up for those recyclable objects.
Read MoreRecycling C
- Electic Vehicles in Washington State, US
+ Electic Vehicles in Washington State, US
A Tableau story with different dashboards about the EV population growth in Washington.
Read More
@@ -120,7 +120,7 @@
- 1st Place Future Mobility Challenge
+ 1st Place Future Mobility Challenge
Exploring different CNN models to classify traffic sign images. $500 Cash price
Read More
@@ -131,7 +131,7 @@
- English Speaking AI-Examiner
+ English Speaking AI-Examiner
An app that allows users to answer questions in English and receive feedback about how well they answered.
Read More
diff --git a/project_details_CTS.html b/project_details_CTS.html
index 94c9252..4ce5927 100644
--- a/project_details_CTS.html
+++ b/project_details_CTS.html
@@ -13,23 +13,52 @@
- Classifying Traffic Sign
+ Future Mobility Challenge: Deep Learning and Computer Vision for Autonomous Vehicles (AVs)
+ Challenge Mentor: Ryan Ahmed, Ph.D., MBA Professor, McMaster University
- Exploring different CNN models to classify traffic signs.
-
-
-
-
+
+ Github
+
- Project Details
- Include more detailed information about the project here.
+ Project Details
+ The automotive industry is going through a paradigm shift from conventional, human-driven vehicles into Autonomous,Artificial Intelligence (AI)-powered vehicles. AVs offer a safe, efficient, and cost-effective solution that will dramaticallyredefine the future of human mobility. AVs are expected to save over half a million lives and generate enormous economicopportunities in excess of $1 trillion dollars by 2035. From GM’s Cruise and Google’s autonomous car (Waymo) to Uber’sself-driving car-sharing service, the automotive industry is on a billion-dollar quest to deploy the most technologicallyadvanced vehicles on the road.
+ In this challenge, you are tasked to train and evaluate several deep CNNs to classify traffic sign images.
+ The dataset contains colored 32 x 32 pixels images with 43 different traffic sign classes.
+ Images are divided into 34799 images for training, 12630 for testing and 4410 for validation.
+
+
+
+
+
+
+
+ Challenge Deliverables:
+ - Research AlexNet Convolutional Neural Network, draw the network architecture, and indicate the use of each of the layers such as convolution/feature extraction, max pooling, and flattening layers.
+ - Visualize a sample image from each class in the dataset. Display the corresponding label and perform a sanity check.
+ - Train a CNN based on AlexNet to classify traffic signs. Train the model using 15 epochs and plot the network accuracy vs. the number of epochs.
+ - Test the trained CNN and evaluate its performance on the testing (holdout) dataset. Note that the testing dataset has never been seen by the model during training.
+ - Fine-tune the trained model by training it on additional datasets. Feel free to collect data from the internet or using a mobile device.
+ - Explore 3 different ways to improve the network accuracy such as increasing the number of epochs, adding additional convolutional/max-pooling layers, or adding dropout layers. Retrain the network and display the results. Any reasonable answer should be sufficient.
+ - Build 3 different deep convolutional neural networks with various architectures. Feel free to choose the number of layers, number of kernels (feature detectors), number of dense (Fully-connected) layers, number of neurons in the dense layer, activation functions, regularization such as dropout..etc. Retrain the network and plot the results.
+ - Test the trained deep CNNs on brand-new images. This might involve collecting traffic sign data and evaluating the system's performance and make adjustment as necessary.
+
+
+
+
+
+
+
- Additional Content
- You can add more sections or content as needed.
+ Additional Content
+ 1st Place Prize (Value): $500
+
+
+ *I'm the third person from the right to the left.
+
diff --git a/project_details_ESAI.html b/project_details_ESAI.html
index 574ec88..d43b5bf 100644
--- a/project_details_ESAI.html
+++ b/project_details_ESAI.html
@@ -13,9 +13,11 @@
- English Speaking AI-Examiner
+ English Speaking AI-Examiner
+ Github
+
An app that allows users to answer questions in English and receive feedback about how well they answered.
@@ -23,13 +25,26 @@ English Speaking AI-Examiner
- Project Details
- Include more detailed information about the project here.
+ Project Details
+ As a non-native English speaker who migrated to Canada, I've been on a mission to improve my English skills. I was motivated to enhance my English speaking skills, but the high costs of language courses discouraged me. That's when I got the idea to create an app that could help me improve without financial constraints.
+
+ What it does
+ This application aims to provide a comprehensive language learning experience, focusing specifically on improving English speaking skills for test takers, such as those preparing for the IELTS/CELPIP exam.
+ The application utilizes the Whisper model to transcribe the user's spoken responses. To provide a comprehensive evaluation, the application leverages a Language Learning Model (LLM) as well.
+ The LLM takes both the transcribed text and the corresponding question as input. By considering the context of the question and the user's response, the LLM generates an assessment of the given answer.
+ This assessment includes analyzing grammar, vocabulary usage, coherence, and fluency, among other language aspects.
+ How I built it
+ I started developing the project using Google Colab, I integrated the "Whisper" model from OpenAI with a Language Learning Model (LLM) to provide feedback on English language usage.
+ It was an exciting journey as I combined these technologies to create a useful tool for language learners.
+
- Additional Content
- You can add more sections or content as needed.
+ Additional Content
+ Flawless English: Master the Language with Precision and Confidence Using AI.
+
+
+
diff --git a/project_details_EV.html b/project_details_EV.html
index 6555816..89b054a 100644
--- a/project_details_EV.html
+++ b/project_details_EV.html
@@ -16,15 +16,28 @@
Electric Vehicles in Washington State, US
+ Github
+
A Tableau story with different dashboards about the EV population growth in Washington.
+
+
-
- Project Details
+ Project Details
The US Department of Energy made significant effort in battery development which resulted in 50% cost of the battery and within 4 years more affordable EVs were made. Today, consumers now have multitude of choices when buying EVs ranging from Hybrids, plug-in-hybrids, and electric across the world. This project will help to explore the growth rate of EV cars in Washington state while also exploring the performance of electric vehicles among diverse Manufacturers.
@@ -44,11 +57,24 @@ Project Details
Compare the retail prices vs the efficiency.
3. Provides a guide for potential buyers of EVs
+
+
+
- Additional Content
+ Additional Content
You can add more sections or content as needed.
diff --git a/project_details_rs.html b/project_details_rs.html
index 5472e09..ac61f69 100644
--- a/project_details_rs.html
+++ b/project_details_rs.html
@@ -17,9 +17,11 @@
Recycling Collection Service
+ Github
+
- Project Description
+ Project Description
Capstone Project for Data Analytics for Business at St. Clair College
@@ -45,7 +47,7 @@ Project Description
- App UI
+ App UI
Request tab
@@ -75,13 +77,13 @@ App UI
- Project technical Details
+ Project technical Details
This section can contain more detailed information about the project, such as the technologies used, challenges faced, and the impact of the project.
- Code Snippets
+ Code Snippets
You can showcase relevant code snippets or any other content related to the project.
// Insert code snippet here
Electic Vehicles in Washington State, US
+Electic Vehicles in Washington State, US
A Tableau story with different dashboards about the EV population growth in Washington.
Read More
- 1st Place Future Mobility Challenge
+ 1st Place Future Mobility Challenge
Exploring different CNN models to classify traffic sign images. $500 Cash price
Read More
@@ -131,7 +131,7 @@
- English Speaking AI-Examiner
+ English Speaking AI-Examiner
An app that allows users to answer questions in English and receive feedback about how well they answered.
Read More
diff --git a/project_details_CTS.html b/project_details_CTS.html
index 94c9252..4ce5927 100644
--- a/project_details_CTS.html
+++ b/project_details_CTS.html
@@ -13,23 +13,52 @@
- Classifying Traffic Sign
+ Future Mobility Challenge: Deep Learning and Computer Vision for Autonomous Vehicles (AVs)
+ Challenge Mentor: Ryan Ahmed, Ph.D., MBA Professor, McMaster University
- Exploring different CNN models to classify traffic signs.
-
-
-
-
+
+ Github
+
- Project Details
- Include more detailed information about the project here.
+ Project Details
+ The automotive industry is going through a paradigm shift from conventional, human-driven vehicles into Autonomous,Artificial Intelligence (AI)-powered vehicles. AVs offer a safe, efficient, and cost-effective solution that will dramaticallyredefine the future of human mobility. AVs are expected to save over half a million lives and generate enormous economicopportunities in excess of $1 trillion dollars by 2035. From GM’s Cruise and Google’s autonomous car (Waymo) to Uber’sself-driving car-sharing service, the automotive industry is on a billion-dollar quest to deploy the most technologicallyadvanced vehicles on the road.
+ In this challenge, you are tasked to train and evaluate several deep CNNs to classify traffic sign images.
+ The dataset contains colored 32 x 32 pixels images with 43 different traffic sign classes.
+ Images are divided into 34799 images for training, 12630 for testing and 4410 for validation.
+
+
+
+
+
+
+
+ Challenge Deliverables:
+ - Research AlexNet Convolutional Neural Network, draw the network architecture, and indicate the use of each of the layers such as convolution/feature extraction, max pooling, and flattening layers.
+ - Visualize a sample image from each class in the dataset. Display the corresponding label and perform a sanity check.
+ - Train a CNN based on AlexNet to classify traffic signs. Train the model using 15 epochs and plot the network accuracy vs. the number of epochs.
+ - Test the trained CNN and evaluate its performance on the testing (holdout) dataset. Note that the testing dataset has never been seen by the model during training.
+ - Fine-tune the trained model by training it on additional datasets. Feel free to collect data from the internet or using a mobile device.
+ - Explore 3 different ways to improve the network accuracy such as increasing the number of epochs, adding additional convolutional/max-pooling layers, or adding dropout layers. Retrain the network and display the results. Any reasonable answer should be sufficient.
+ - Build 3 different deep convolutional neural networks with various architectures. Feel free to choose the number of layers, number of kernels (feature detectors), number of dense (Fully-connected) layers, number of neurons in the dense layer, activation functions, regularization such as dropout..etc. Retrain the network and plot the results.
+ - Test the trained deep CNNs on brand-new images. This might involve collecting traffic sign data and evaluating the system's performance and make adjustment as necessary.
+
+
+
+
+
+
+
- Additional Content
- You can add more sections or content as needed.
+ Additional Content
+ 1st Place Prize (Value): $500
+
+
+ *I'm the third person from the right to the left.
+
diff --git a/project_details_ESAI.html b/project_details_ESAI.html
index 574ec88..d43b5bf 100644
--- a/project_details_ESAI.html
+++ b/project_details_ESAI.html
@@ -13,9 +13,11 @@
- English Speaking AI-Examiner
+ English Speaking AI-Examiner
+ Github
+
An app that allows users to answer questions in English and receive feedback about how well they answered.
@@ -23,13 +25,26 @@ English Speaking AI-Examiner
- Project Details
- Include more detailed information about the project here.
+ Project Details
+ As a non-native English speaker who migrated to Canada, I've been on a mission to improve my English skills. I was motivated to enhance my English speaking skills, but the high costs of language courses discouraged me. That's when I got the idea to create an app that could help me improve without financial constraints.
+
+ What it does
+ This application aims to provide a comprehensive language learning experience, focusing specifically on improving English speaking skills for test takers, such as those preparing for the IELTS/CELPIP exam.
+ The application utilizes the Whisper model to transcribe the user's spoken responses. To provide a comprehensive evaluation, the application leverages a Language Learning Model (LLM) as well.
+ The LLM takes both the transcribed text and the corresponding question as input. By considering the context of the question and the user's response, the LLM generates an assessment of the given answer.
+ This assessment includes analyzing grammar, vocabulary usage, coherence, and fluency, among other language aspects.
+ How I built it
+ I started developing the project using Google Colab, I integrated the "Whisper" model from OpenAI with a Language Learning Model (LLM) to provide feedback on English language usage.
+ It was an exciting journey as I combined these technologies to create a useful tool for language learners.
+
- Additional Content
- You can add more sections or content as needed.
+ Additional Content
+ Flawless English: Master the Language with Precision and Confidence Using AI.
+
+
+
diff --git a/project_details_EV.html b/project_details_EV.html
index 6555816..89b054a 100644
--- a/project_details_EV.html
+++ b/project_details_EV.html
@@ -16,15 +16,28 @@
Electric Vehicles in Washington State, US
+ Github
+
A Tableau story with different dashboards about the EV population growth in Washington.
+
+
-
- Project Details
+ Project Details
The US Department of Energy made significant effort in battery development which resulted in 50% cost of the battery and within 4 years more affordable EVs were made. Today, consumers now have multitude of choices when buying EVs ranging from Hybrids, plug-in-hybrids, and electric across the world. This project will help to explore the growth rate of EV cars in Washington state while also exploring the performance of electric vehicles among diverse Manufacturers.
@@ -44,11 +57,24 @@ Project Details
Compare the retail prices vs the efficiency.
3. Provides a guide for potential buyers of EVs
+
+
+
- Additional Content
+ Additional Content
You can add more sections or content as needed.
diff --git a/project_details_rs.html b/project_details_rs.html
index 5472e09..ac61f69 100644
--- a/project_details_rs.html
+++ b/project_details_rs.html
@@ -17,9 +17,11 @@
Recycling Collection Service
+ Github
+
- Project Description
+ Project Description
Capstone Project for Data Analytics for Business at St. Clair College
@@ -45,7 +47,7 @@ Project Description
- App UI
+ App UI
Request tab
@@ -75,13 +77,13 @@ App UI
- Project technical Details
+ Project technical Details
This section can contain more detailed information about the project, such as the technologies used, challenges faced, and the impact of the project.
- Code Snippets
+ Code Snippets
You can showcase relevant code snippets or any other content related to the project.
// Insert code snippet here
1st Place Future Mobility Challenge
+1st Place Future Mobility Challenge
Exploring different CNN models to classify traffic sign images. $500 Cash price
Read More @@ -131,7 +131,7 @@
- English Speaking AI-Examiner
+ English Speaking AI-Examiner
An app that allows users to answer questions in English and receive feedback about how well they answered.
Read More
diff --git a/project_details_CTS.html b/project_details_CTS.html
index 94c9252..4ce5927 100644
--- a/project_details_CTS.html
+++ b/project_details_CTS.html
@@ -13,23 +13,52 @@
- Classifying Traffic Sign
+ Future Mobility Challenge: Deep Learning and Computer Vision for Autonomous Vehicles (AVs)
+ Challenge Mentor: Ryan Ahmed, Ph.D., MBA Professor, McMaster University
- Exploring different CNN models to classify traffic signs.
-
-
-
-
+
+ Github
+
- Project Details
- Include more detailed information about the project here.
+ Project Details
+ The automotive industry is going through a paradigm shift from conventional, human-driven vehicles into Autonomous,Artificial Intelligence (AI)-powered vehicles. AVs offer a safe, efficient, and cost-effective solution that will dramaticallyredefine the future of human mobility. AVs are expected to save over half a million lives and generate enormous economicopportunities in excess of $1 trillion dollars by 2035. From GM’s Cruise and Google’s autonomous car (Waymo) to Uber’sself-driving car-sharing service, the automotive industry is on a billion-dollar quest to deploy the most technologicallyadvanced vehicles on the road.
+ In this challenge, you are tasked to train and evaluate several deep CNNs to classify traffic sign images.
+ The dataset contains colored 32 x 32 pixels images with 43 different traffic sign classes.
+ Images are divided into 34799 images for training, 12630 for testing and 4410 for validation.
+
+
+
+
+
+
+
+ Challenge Deliverables:
+ - Research AlexNet Convolutional Neural Network, draw the network architecture, and indicate the use of each of the layers such as convolution/feature extraction, max pooling, and flattening layers.
+ - Visualize a sample image from each class in the dataset. Display the corresponding label and perform a sanity check.
+ - Train a CNN based on AlexNet to classify traffic signs. Train the model using 15 epochs and plot the network accuracy vs. the number of epochs.
+ - Test the trained CNN and evaluate its performance on the testing (holdout) dataset. Note that the testing dataset has never been seen by the model during training.
+ - Fine-tune the trained model by training it on additional datasets. Feel free to collect data from the internet or using a mobile device.
+ - Explore 3 different ways to improve the network accuracy such as increasing the number of epochs, adding additional convolutional/max-pooling layers, or adding dropout layers. Retrain the network and display the results. Any reasonable answer should be sufficient.
+ - Build 3 different deep convolutional neural networks with various architectures. Feel free to choose the number of layers, number of kernels (feature detectors), number of dense (Fully-connected) layers, number of neurons in the dense layer, activation functions, regularization such as dropout..etc. Retrain the network and plot the results.
+ - Test the trained deep CNNs on brand-new images. This might involve collecting traffic sign data and evaluating the system's performance and make adjustment as necessary.
+
+
+
+
+
+
+
- Additional Content
- You can add more sections or content as needed.
+ Additional Content
+ 1st Place Prize (Value): $500
+
+
+ *I'm the third person from the right to the left.
+
diff --git a/project_details_ESAI.html b/project_details_ESAI.html
index 574ec88..d43b5bf 100644
--- a/project_details_ESAI.html
+++ b/project_details_ESAI.html
@@ -13,9 +13,11 @@
- English Speaking AI-Examiner
+ English Speaking AI-Examiner
+ Github
+
An app that allows users to answer questions in English and receive feedback about how well they answered.
@@ -23,13 +25,26 @@ English Speaking AI-Examiner
- Project Details
- Include more detailed information about the project here.
+ Project Details
+ As a non-native English speaker who migrated to Canada, I've been on a mission to improve my English skills. I was motivated to enhance my English speaking skills, but the high costs of language courses discouraged me. That's when I got the idea to create an app that could help me improve without financial constraints.
+
+ What it does
+ This application aims to provide a comprehensive language learning experience, focusing specifically on improving English speaking skills for test takers, such as those preparing for the IELTS/CELPIP exam.
+ The application utilizes the Whisper model to transcribe the user's spoken responses. To provide a comprehensive evaluation, the application leverages a Language Learning Model (LLM) as well.
+ The LLM takes both the transcribed text and the corresponding question as input. By considering the context of the question and the user's response, the LLM generates an assessment of the given answer.
+ This assessment includes analyzing grammar, vocabulary usage, coherence, and fluency, among other language aspects.
+ How I built it
+ I started developing the project using Google Colab, I integrated the "Whisper" model from OpenAI with a Language Learning Model (LLM) to provide feedback on English language usage.
+ It was an exciting journey as I combined these technologies to create a useful tool for language learners.
+
- Additional Content
- You can add more sections or content as needed.
+ Additional Content
+ Flawless English: Master the Language with Precision and Confidence Using AI.
+
+
+
diff --git a/project_details_EV.html b/project_details_EV.html
index 6555816..89b054a 100644
--- a/project_details_EV.html
+++ b/project_details_EV.html
@@ -16,15 +16,28 @@
Electric Vehicles in Washington State, US
+ Github
+
A Tableau story with different dashboards about the EV population growth in Washington.
+
+
-
- Project Details
+ Project Details
The US Department of Energy made significant effort in battery development which resulted in 50% cost of the battery and within 4 years more affordable EVs were made. Today, consumers now have multitude of choices when buying EVs ranging from Hybrids, plug-in-hybrids, and electric across the world. This project will help to explore the growth rate of EV cars in Washington state while also exploring the performance of electric vehicles among diverse Manufacturers.
@@ -44,11 +57,24 @@ Project Details
Compare the retail prices vs the efficiency.
3. Provides a guide for potential buyers of EVs
+
+
+
- Additional Content
+ Additional Content
You can add more sections or content as needed.
diff --git a/project_details_rs.html b/project_details_rs.html
index 5472e09..ac61f69 100644
--- a/project_details_rs.html
+++ b/project_details_rs.html
@@ -17,9 +17,11 @@
Recycling Collection Service
+ Github
+
- Project Description
+ Project Description
Capstone Project for Data Analytics for Business at St. Clair College
@@ -45,7 +47,7 @@ Project Description
- App UI
+ App UI
Request tab
@@ -75,13 +77,13 @@ App UI
- Project technical Details
+ Project technical Details
This section can contain more detailed information about the project, such as the technologies used, challenges faced, and the impact of the project.
- Code Snippets
+ Code Snippets
You can showcase relevant code snippets or any other content related to the project.
// Insert code snippet here
English Speaking AI-Examiner
+English Speaking AI-Examiner
An app that allows users to answer questions in English and receive feedback about how well they answered.
Read MoreClassifying Traffic Sign
+Future Mobility Challenge: Deep Learning and Computer Vision for Autonomous Vehicles (AVs)
+Exploring different CNN models to classify traffic signs.
- -
- Github
+Project Details
-Include more detailed information about the project here.
+Project Details
+The automotive industry is going through a paradigm shift from conventional, human-driven vehicles into Autonomous,Artificial Intelligence (AI)-powered vehicles. AVs offer a safe, efficient, and cost-effective solution that will dramaticallyredefine the future of human mobility. AVs are expected to save over half a million lives and generate enormous economicopportunities in excess of $1 trillion dollars by 2035. From GM’s Cruise and Google’s autonomous car (Waymo) to Uber’sself-driving car-sharing service, the automotive industry is on a billion-dollar quest to deploy the most technologicallyadvanced vehicles on the road.
+In this challenge, you are tasked to train and evaluate several deep CNNs to classify traffic sign images. + The dataset contains colored 32 x 32 pixels images with 43 different traffic sign classes. + Images are divided into 34799 images for training, 12630 for testing and 4410 for validation. +
+ +
+ -
+
- Research AlexNet Convolutional Neural Network, draw the network architecture, and indicate the use of each of the layers such as convolution/feature extraction, max pooling, and flattening layers. +
- Visualize a sample image from each class in the dataset. Display the corresponding label and perform a sanity check. +
- Train a CNN based on AlexNet to classify traffic signs. Train the model using 15 epochs and plot the network accuracy vs. the number of epochs. +
- Test the trained CNN and evaluate its performance on the testing (holdout) dataset. Note that the testing dataset has never been seen by the model during training. +
- Fine-tune the trained model by training it on additional datasets. Feel free to collect data from the internet or using a mobile device. +
- Explore 3 different ways to improve the network accuracy such as increasing the number of epochs, adding additional convolutional/max-pooling layers, or adding dropout layers. Retrain the network and display the results. Any reasonable answer should be sufficient. +
- Build 3 different deep convolutional neural networks with various architectures. Feel free to choose the number of layers, number of kernels (feature detectors), number of dense (Fully-connected) layers, number of neurons in the dense layer, activation functions, regularization such as dropout..etc. Retrain the network and plot the results. +
- Test the trained deep CNNs on brand-new images. This might involve collecting traffic sign data and evaluating the system's performance and make adjustment as necessary. +
Challenge Deliverables:
+Additional Content
-You can add more sections or content as needed.
+Additional Content
+1st Place Prize (Value): $500
+
+ English Speaking AI-Examiner
+English Speaking AI-Examiner
Github
+An app that allows users to answer questions in English and receive feedback about how well they answered.
English Speaking AI-Examiner
Project Details
-Include more detailed information about the project here.
+Project Details
+As a non-native English speaker who migrated to Canada, I've been on a mission to improve my English skills. I was motivated to enhance my English speaking skills, but the high costs of language courses discouraged me. That's when I got the idea to create an app that could help me improve without financial constraints.
+ +What it does
+This application aims to provide a comprehensive language learning experience, focusing specifically on improving English speaking skills for test takers, such as those preparing for the IELTS/CELPIP exam. + The application utilizes the Whisper model to transcribe the user's spoken responses. To provide a comprehensive evaluation, the application leverages a Language Learning Model (LLM) as well. + The LLM takes both the transcribed text and the corresponding question as input. By considering the context of the question and the user's response, the LLM generates an assessment of the given answer. + This assessment includes analyzing grammar, vocabulary usage, coherence, and fluency, among other language aspects.
+How I built it
+I started developing the project using Google Colab, I integrated the "Whisper" model from OpenAI with a Language Learning Model (LLM) to provide feedback on English language usage. + It was an exciting journey as I combined these technologies to create a useful tool for language learners.
+Additional Content
-You can add more sections or content as needed.
+Additional Content
+Flawless English: Master the Language with Precision and Confidence Using AI.
+ + +Electric Vehicles in Washington State, US
+Github
+A Tableau story with different dashboards about the EV population growth in Washington.
+Project Details
+Project Details
The US Department of Energy made significant effort in battery development which resulted in 50% cost of the battery and within 4 years more affordable EVs were made. Today, consumers now have multitude of choices when buying EVs ranging from Hybrids, plug-in-hybrids, and electric across the world. This project will help to explore the growth rate of EV cars in Washington state while also exploring the performance of electric vehicles among diverse Manufacturers.
@@ -44,11 +57,24 @@Project Details
3. Provides a guide for potential buyers of EVs
+Additional Content
+Additional Content
You can add more sections or content as needed.
Recycling Collection Service
+Github
+Project Description
+Project Description
Capstone Project for Data Analytics for Business at St. Clair College
@@ -45,7 +47,7 @@Project Description
App UI
+App UI
App UI
Project technical Details
+Project technical Details
This section can contain more detailed information about the project, such as the technologies used, challenges faced, and the impact of the project.
Code Snippets
+Code Snippets
You can showcase relevant code snippets or any other content related to the project.
// Insert code snippet here