Applications

更多类似内容

Персональне навчальне середовище

由Антощенко Мария

Facets of Learning

由Kim Nguyen

The 4-Hour Workweek by Timothy Ferris

由Anthony Johnson

conferencia internacional de promoción de la salud

由Juana Vega

Applications

Student's Guide Application

The Student Guide Application is designed to support students with language learning and tutoring. It incorporates cognitive computing elements, including chatbots powered by Natural Language Processing (NLP) technology, Q/A models, and APIs.

In this application, chatbots act as the user interface. They receive user queries and relay them to the Q/A model, specifically GPT-3. When a user submits a question or query to the chatbot, the chatbot channels it to the Q/A model for processing. To facilitate this communication between the Q/A model and chatbots, an API serves as the intermediary, using API requests to transmit questions and retrieve answers seamlessly.

Platforms

Microsoft Azure

Azure API management for API integration

Azure Machine Learning for Q/A model deployment

Azure bot services for chatbots

Area of cognitive computing

API

API will serve as communication channel between Q/A model and ChatBot

Natural Language Processing

Chatbots use NLP to generate natural language responses to student's queries. This includes selecting appropriate words, phrases, and grammar rules to create human-like replies

NLP will enable the system to parse student queries and extract meaning from them.

Questions-Answering Technology

GPT-3 will be used as a Q/A model which will serve as chatBot's backend which will be responsible for answering questions posed by students

This application is designed for students seeking learning support. It offers language learning tools and tutoring assistance. Through chatbots, students can engage in conversations with language-learning chatbots to enhance their speaking and comprehension skills. Additionally, the application aids students with their assignments. Students can choose their course from a list and request assignment help. The chatbot will then deliver a step-by-step solution for the specified assignment

Education

Battery prediction of mobile devices application

The battery prediction of mobile device application will use the reasoning and decision-making quality provided by cognitive computing. This application will intelligently suggest when to charge the device based on usage patterns and battery life predictions.

This application will continuously learn from user interactions and feedback to improve its predictions and recommendations over time. This adaptive learning is a fundamental aspect of cognitive computing.

Context-awareness is another cognitive computing aspect used in this application. This application considers the usage pattern of the mobile device and suggests power-saving settings when the battery is low.

Area of cognitive computing : Artificial Intelligence

Platform

Scikit-learn

Scikit-learn is a popular machine learning library in python to build code for regression models

Artificial Intelligence models will be used to do the prediction of battery life of mobile devices. Features like Bluetooth, GPS, Sync and CPU speed will be send as an input to the AI models which will provide the battery consumption rate as an output. The application will also provide ranking of features where features of mobile device will be ranked based on the amount of energy consumed by each feature.

Definition

Mobile device battery life will be estimated by analyzing usage patterns of features like Bluetooth, sync, GPS, and CPU speed. This estimation will inform users about how many hours their phone will last on a single charge.

domain

Telecommunication