Anomaly detection is a common problem that can be solved using machine learning techniques. Simple density based algorithms provide a good baseline for such projects, and can be used to solve a variety of problems from defect detection in manufacturing to network attacks in IT.
Automated text summarization through machine learning can be an extremely valuable tool to increase efficiency in both our everyday life and professional endeavors if the important information in a document can be extracted and accurately summarized.
The use of Twitter and natural language processing opens up a promising new approach to flu surveillance. Such data-driven methods produce encouraging results and provide a faster way to identify flu surges.
Further, these Twitter-based methods can be very easily applied to numerous other domains such as Marketing, for identifying geospatial trends in brand image, as well as in Urban Planning for analyzing public attitudes towards various spaces and landmarks for example.
Both patients and hospitals need to effectively predict wait times, whether for psychological benefits or schedule optimization needs. In this post, we will explore some of the main ways that officials predict hospital wait times and assess how successful they are at doing so.
Responding to the global challenges, agriculture must improve on all aspects: Smarter resource use, increasing yields, increased operational efficiency, and sustainable land usage. Big data is expected to have a large impact on "smart farming" and involves the whole supply chain, from biotechnology and plant development to individual farmers and the companies that support them.
Governments in the US and around the world have introduced a variety of financial penalties to hospitals with excess early readmissions. But how can hospitals predict which patients are likely to be readmitted early, so they can help these patients avoid readmittance? In this post, we explore some machine learning methods for predicting early readmissions.
Recently, there has been great success in time series analyses by applying dynamic time warping (DTW). Indeed, when combined with simple algorithms such as k-Nearest Neighbours, DTW has reproduced accuracies of state-of-the-art algorithms, such as deep neural nets etc.
We will discuss here a supervised classification example of wearable devices and a possible use-case for DTW.
Much of the hype surrounding neural networks is about image-based applications. However, Recurrent Neural Networks (RNNs) have been successfully used in recent years to predict future events in time series as well. RNNs have contributed to breakthroughs in a wide variety of fields centered around predicting sequences of events. In this piece, however, we'll demonstrate how one type of RNN, the Long Short-Term Memory (LSTM) network, can be used to predict even financial time series data—perhaps the most chaotic and difficult of all time series.
This blog focuses on developing an algorithm to understand spoken Arabic digits. Such algorithms are the first step in developing computers that can understand languages with applications ranging from text-to-speech, voice-recognition, and translation, to modern AI assistants that are widely becoming available.
Artificial Intelligence (AI) is on a trajectory to become ubiquitous in every area of our lives. In this post, we explore three current applications of artificial intelligence in the real world and the machine learning techniques that make them work.
Machine vision is one of the pillars of machine learning. Its stature will grow in importance as more accurate algorithms are explored, but has already been used by Amazon for online shopping, Google for image search and Facebook for its facial recognition. Here we give a brief overview of convolutional neural networks, one of the best deep learning algorithms for image recognition.
Customer lifetime value goes a step further than churn rate prediction. It uses retention (i.e. the inverse of churn) and a “discount” factor, which accounts for the decreasing value of future money to predict the expected monetary value that a customer will generate over the entire period of the relationship with your company.
Client churn is the turnover (or attrition) rate over time of your company’s customers. Since keeping clients is often much more cost effective than finding new ones, by understanding who is likely to churn and why, we can create a cost-effective way to increase profits.
Machine Learning is still in its infancy in archaeology, but the approach holds enormous promise. Just as in finance and disaster mitigation, the use of satellite imagery has become a vital resource for archaeology. As more archaeologists around the world automate the process of identifying archaeological sites with satellite images, sites will be found at a faster rate than ever before.
We introduce the concept of Reinforcement Learning and discuss how such an algorithm can be used to solve portfolio optimizations that extract the most value from raw market data. Over time, such algorithms learn the strategies to deploy that will generate the maximum possible value and consequently the maximum possible profit.
Artificial Neural Networks were originally inspired by the human nervous system. The term has entered popular parlance in recent years due to the huge advancements in computational power and data storage abilities. We here give a brief summary of what Neural Nets are and how they work.
Document classification is currently one of the most important branches of Natural Language Processing (NLP). The general idea is to automatically classify documents into categories using machine learning algorithms.
The applications are almost endless, we can classify: patient records, movie reviews, webpages, emails (spam vs not spam), and in fact anything text based.
Relation Extraction is one of the cornerstones of Natural Language Processing and concerns the linking of two entities in unstructured text. In this blog post, we describe two of the simplest methods that are typically used: Supervised Feature Extraction and Semi-Supervised Seeding.
Dynamic Time Warping (DTW) is an intelligent, dynamically adjusted metric that allows more flexibility when used in combination with any distance dependent algorithm. This flexibility allows for better classification results in many different time-series analyses.
DTW allows us to retain the temporal dynamics by directly modeling the time-series. As its names suggests, the usual Euclidean distance in problems is replaced with a dynamically adjusted metric.