Tag: technology
-
A Closer Look at the Azure Cloud Portfolio – 3. Azure DevOps Boards
Azure Boards (AB), part of Azure DevOps suite, is a tool for managing software development work that allows planning, tracking, customization, and discussion. The post outlines how to start with AB, set up a project, create and manage work items, customize a project’s boards, and organize work into sprints. AB’s key advantages include its flexibility,…
-
GPT & DeepLake NLP: Amazon Financial Statements
The post outlines the implementation of an AI-powered chatbot using NLP to process and analyze financial data from Amazon’s financial statements. The tool employs LlamaIndex and DeepLake to answer queries, summarize financial information, and analyze trends. This approach enhances the efficiency of data analysis, making it a valuable resource for finance and banking professionals.
-
Effective 2D Image Compression with K-means Clustering
The post explores the application of the K-means clustering algorithm, a popular unsupervised Machine Learning algorithm, for image compression. By segmenting 2D images into different clusters, the algorithm effectively reduces storage space without compromising on image quality or resolution. It also demonstrates the application of this approach through a case study, where optimal results were…
-
A Closer Look at the Azure Cloud Portfolio – 2. From VMs to Web Servers
This guide explains how to create virtual machines (VMs) for deploying web servers from Azure. It covers the process of creating a VM and connecting it to a secured subnet within a virtual network (VNet), using Azure’s Bastion service for secure RDP/SSH connections, and installing a Nextcloud server on the VM. Additional steps include making…
-
Video Game Sales Data Exploration
The post explores the gaming industry’s size and state, highlighting a potential market value of $314bn by 2027. It emphasizes the industry’s three main subsectors: console, PC, and smartphone gaming. Moreover, the post conducts extensive data analysis on video game sales data, using Python to examine aspects such as genre profitability, platform sales prices, and…
-
Deep Reinforcement Learning (DRL) on $MO 8.07% DIV USA Stock Data 2022-23
This study applies the Deep Reinforcement Learning (DRL) algorithm to USA stocks with +4% DIV in 2022-23, focusing on Altria Group, Inc. The study addresses accurate stock price predictions and the challenges in traditional methods. Recent advances in DRL have shown improved accuracy in stock forecasting, making it suitable for turbulent markets and investment decision-making.
-
LSTM Price Predictions of 4 Tech Stocks
The given content explains the process of using Exploratory Data Analysis (EDA) and Long Short-Term Memory (LSTM) Sequential model for comparing the risk/return of four major tech stocks: Apple, Google, Microsoft, and Amazon, considering the tech scenario in 2023. The analysis involves examining stock price patterns, their correlations, risk-return assessment, and predicting stock prices using…
-
Comparative ML/AI Performance Analysis of 13 Handwritten Digit Recognition (HDR) Scikit-Learn Algorithms with PCA+HPO
Featured Photo by Torsten Dettlaff on Pexels The article consists of the following three parts: 3. Unsupervised ML using the Principal Component Analysis (PCA) for the dimensionality reduction within Parts 1 and 2. Our main goal is to build a text and graphics report comparing the main scikit-learn classification metrics: accuracy_score, classification_report (precision, recall, and…
-
Python Technical Analysis for BioTech – Get Buy Alerts on ABBV in 2023
Seeking Alpha urged investors to buy AbbVie (NYSE:ABBV), Vertex Pharma (NASDAQ:VRTX), Genmab (GMAB) and a range of other biotechs in 2022 long before those stocks outperformed − sometimes even as the consensus view on Wall Street suggested otherwise. Let’s examine the ABBV 2022 stock performance using mplfinance, plotly, bokeh, bqplot, and cufflinks libraries in Python. Let’s set the…
-
50 Coronavirus COVID-19 Free APIs
The COVID-19 pandemic has triggered the creation of numerous free, accessible APIs providing real-time data on the virus’s spread. With data in JSON and CSV formats sourced from reputable institutions, developers and researchers can track cases, government policies, and more for informed decision-making and analysis.
-
AI-Based ECG Recognition – EOY ’22 Status
Featured Photo by cottonbro studio on pexels. Electrocardiography (ECG) is the method most often used to diagnose cardiovascular diseases. The recent study demonstrates that an AI is capable of automatically diagnosing the abnormalities indicated by an ECG. In this post we will review and illustrate how AI applies to ECG analysis to outperform traditional ECG analysis.…
-
99% Accurate Breast Cancer Classification using Neural Networks in TensorFlow
Breast cancer is a significant global health concern, affecting 12% of women. Machine Learning and Artificial Intelligence techniques play a crucial role in early diagnosis using image features. The study demonstrates a successful Neural Network model for breast cancer classification, achieving 98% accuracy and 98% F1-score. Multiple metrics confirm the model’s efficiency.
-
Textual Genres Analysis using the Carloto’s NLP Algorithm
Featured Photo by Dominika Roseclay on Pexels. Computational Linguistics (CL) is the scientific study of language. Oftentime, CL is linked to the Python software development based on Natural Language Processing (NLP) libraries. NLP basically consists of combining machine learning (ML) techniques with text, and using math and statistics to get that text in a format…
-
A Comparison of Scikit Learn Algorithms for Breast Cancer Classification – 2. Cross Validation vs Performance
The post is a continuation of a previous breast cancer study comparing Scikit-Learn binary classifiers for cross validation and model performance. The classifiers compared include Logistic Regression, GaussianNB, SVC, KNN, Random Forest, Extra Trees, and Gradient Boosting. Learning curves show the comparison of classifier performance. Results indicate GaussianNB is more efficient than SVC in terms…
-
Hands-On USGS Webscraping of Earthquakes- Worldwide (24 Hours)
A live global earthquake tracker has been developed using the USGS earthquake data feed. This tool, which functions 24/7, distinguishes between underground nuclear explosions and organic or man-made seismic activities such as earthquakes and mining explosions. This tracker is crucial given that a third of the world’s population is exposed to earthquakes.
-
ML/AI Breast Cancer Diagnosis with 98% Confidence
We demonstrate the importance of hyperparameter optimization (HPO) for enhancing ML prediction accuracy. Specifically, we will focus on the Random Forest Classifier (RFC) as an ensemble of decision trees. RFC is a supervised ML algorithm that has been applied successfully to the BC binary classification.