Churn prediction in telecommunication industry using kernel Support Vector Machines.

In this age of fierce competitions, customer retention is one of the most important tasks for many companies. Many previous works proposed models to predict customer churn based on various machine learning techniques. In this study, we proposed an advanced churn prediction model using kernel Support Vector Machines (SVM) algorithm for a telecom company. Baseline SVM models were initially built to find out the most suitable kernel types and will be used to make comparison with other approaches. Dimension reduction strategies such as Sequential Forward Selection (SFS) and Sequential Backward Selection (SBS) were applied to the dataset to find out the most important features. Furthermore, resampling techniques to deal with imbalanced data such as Synthetic Minority Oversampling Technique Tomek Link (SMOTE Tomek) and Synthetic Minority Oversampling Technique ENN (SMOTE ENN) were used on the dataset. Using the above-mentioned techniques, we have obtained better results compared to those obtained from previous works, we achieved an F1-score and accuracy of 99% and 98.9% respectively.

Ultra-high-speed image signal accumulation sensor.

Averaging of accumulated data is a standard technique applied to processing data with low signal-to-noise ratios (SNR), such as image signals captured in ultra-high-speed imaging. The authors propose an architecture layout of an ultra-high-speed image sensor capable of on-chip signal accumulation. The very high frame rate is enabled by employing an image sensor structure with a multi-folded CCD in each pixel, which serves as an in situ image signal storage. The signal accumulation function is achieved by direct connection of the first and the last storage elements of the in situ storage CCD. It has been thought that the multi-folding is achievable only by driving electrodes with complicated and impractical layouts. Simple configurations of the driving electrodes to overcome the difficulty are presented for two-phase and four-phase transfer CCD systems. The in situ storage image sensor with the signal accumulation function is named Image Signal Accumulation Sensor (ISAS).