CPT+: Decreasing the Time/Space Complexity of the Compact Prediction Tree

Gueniche, Ted; Fournier-Viger, Philippe; Raman, Rajeev; Tseng, Vincent S.

doi:10.1007/978-3-319-18032-8_49

Cited by 60 publications

(59 citation statements)

References 13 publications

(25 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of such non-probabilistic sequence prediction algorithms is the compact prediction tree (CPT) [42] algorithm, which was later improved to the computationally more efficient CPT+ algorithm [43]. The CPT and CPT+ algorithms generate a tree-based data structure that makes a lossless compres-sion from the training data which can be used at prediction time to efficiently search for the most likely next element.…”

Section: Non-probabilistic Sequence Classificationmentioning

confidence: 99%

An interdisciplinary comparison of sequence modeling methods for next-element prediction

2020

View full text Add to dashboard Cite

Data of sequential nature arise in many application domains in forms of, e.g. textual data, DNA sequences, and software execution traces. Different research disciplines have developed methods to learn sequence models from such datasets: (i) in the machine learning field methods such as (hidden) Markov models and recurrent neural networks have been developed and successfully applied to a wide-range of tasks, (ii) in process mining process discovery techniques aim to generate human-interpretable descriptive models, and (iii) in the grammar inference field the focus is on finding descriptive models in the form of formal grammars. Despite their different focuses, these fields share a common goal -learning a model that accurately describes the behavior in the underlying data. Those sequence models are generative, i.e, they can predict what elements are likely to occur after a given unfinished sequence. So far, these fields have developed mainly in isolation from each other and no comparison exists. This paper presents an interdisciplinary experimental evaluation that compares sequence modeling techniques on the task of nextelement prediction on four real-life sequence datasets. The results indicate that machine learning techniques that generally have no aim at interpretability in terms of accuracy outperform techniques from the process mining and grammar inference fields that aim to yield interpretable models.

show abstract

Section: Non-probabilistic Sequence Classificationmentioning

confidence: 99%

An interdisciplinary comparison of sequence modeling methods for next-element prediction

2020

View full text Add to dashboard Cite

show abstract

“…This model is executing the predictions in sequence manner. This type of learning is used in prediction applications such as weather forecasting and stock market [12].…”

Section: Review Of Neural Network Prediction Systemmentioning

confidence: 99%

Prediction of Seismic zone in India using Neural Network Algorithms

Sangeetha*¹,

Mohankumar²

2019

IJITEE

View full text Add to dashboard Cite

In this world, earthquake is a major catastrophe which creates huge amount of loss in living non living things. The prediction of an earthquake is an important task in seismology. Neural network performs a key task in the prediction of earthquake. The neural network architecture are created with different input layer and hidden layers with deep learning optimization algorithms. The input layer was developed with the parameters of historical earthquake data of India taken from India Meteorological Department (IMD). The earthquake event such as date, latitude, longitude, depth, magnitude are mathematically converted into seismic indicators depend on Gutenberg-Richter’s inverse law, are the input layers of this neural network model. The developed network model was trained with set of data items using neural network algorithms such as Backpropagation and sequential learning. The Backpropagation is used to find the magnitude prediction and sequential learning is used to find the prediction model for the cartographic risky areas. The loss and accuracy of the model are analyzed with the help of software tool, Disaster Management System which is developed for this work using Python. The deep neural network optimizers such as Stochastic Gradient Descent (SGD), Adaptive Gradient algorithm (AdaGrad) and Root Mean Square propagation (RMSprop) are used to optimize the prediction model. The optimizer produced earthquake prediction model with high ability and more accuracy. Also give the cartography which shows the seismic zone in India face earthquake in future

show abstract

“…For example, they are utilized for predicting the next symbol of a sequence based on the previously observed symbols. According to [31], a prediction model is trained with a set of training sequences (known as sequence database). There are numerous popular applications relating to sequence predictions such as weather forecasting, web page prefetching, stock market prediction, consumer product recommendation and so on.…”

Section: Sequence Databasementioning

confidence: 99%

“…Moreover, they have also a few limitations as follows: Approaches using Machine Learning build lossy models, which may thus ignore relevant information from training sequences while performing predictions [30]. According to the paper [31], above-mentioned models suffer from some major drawbacks: prediction is not exact due to Markov models. Therefore, these models skipped nearly information contained in training sequences for predicting, and this leads significantly reduce their accuracy.…”

Section: Introductionmentioning

confidence: 99%

“…Nevertheless, increasing the order of Markov models often leads to a very high state complexity, thus making them may be impractical. Currently, in terms of sequence prediction, the CPT+ is up to 98 times more compact and 4.5 times faster than CPT and has the best overall accuracy when compared to six state-of-the-art models from the literature [31]. In the next section, we formally introduce fundamental knowledge relating to sequence database and sequence prediction, in particular, the CPT+.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A novel approach based on sequence prediction for webpage access

Da¹,

Hanh²

2018

IJET

View full text Add to dashboard Cite

Predicting the next item of a sequence over a finite alphabet is highly important in Web Mining. This paper presents a solution to improve the performance of sequence prediction; first and foremost, predicting what is the next Web page that will be visited by that user for prefetching the Web page. The proposed approach is how to decrease the complexity of the prediction space. Experimental results on a few real-life datasets show that the time execution of this novel approach is better than that of traditional approaches.

show abstract

CPT+: Decreasing the Time/Space Complexity of the Compact Prediction Tree

Cited by 60 publications

References 13 publications

An interdisciplinary comparison of sequence modeling methods for next-element prediction

An interdisciplinary comparison of sequence modeling methods for next-element prediction

Prediction of Seismic zone in India using Neural Network Algorithms

A novel approach based on sequence prediction for webpage access

Contact Info

Product

Resources

About