: This thesis applies neural network feature selection techniques to multivariate time series data to improve prediction of a target time series. Two approaches to feature selection are used. First, a subset enumeration method is used to determine which financial indicators are most useful for aiding in prediction of the S&P 500 futures daily price. The candidate indicators evaluated include RSI, Stochastics and several moving averages. Results indicate that the Stochastics and RSI indicators result in better prediction results than the moving averages. The second approach to feature selection is calculation of individual saliency metrics. A new decision boundary-based individual saliency metric, and a classifier independent saliency metric are developed and tested. Ruck's saliency metric, the decision boundary based saliency metric, and the classifier independent saliency metric are compared for a data set consisting of the RSI and Stochastics indicators as well as delayed closing price values. The decision based metric and the Ruck metric results are similar, but the classifier independent metric agrees with neither of the other metrics. The nine most salient features, determined by the decision boundary based metric, are used to train a neural network and the results are presented and compared to other published results. (AN)

/pdf/nonlinear-time-series-analysis-1j3a35n4y3.pdf

Nonlinear Time Series Analysis.

Newness and distinctiveness is claimed in the features of ornamentation as shown inside the broken line circle in the accompanying representation.

Display screen or portion thereof with graphical user interface

A surgical instrument can comprise a channel configured to support a staple cartridge and, in addition, an anvil pivotable between open and closed positions relative to the channel. The surgical instrument can further comprise a cutting member configured to incise tissue positioned captured between the staple cartridge and the anvil and, in addition, means for stopping the cutting member prior to a distal end datum, wherein the distal end datum can be defined by the distal-most staple cavity in the staple cartridge. In such embodiments, the incision within the tissue may not extend beyond the portion of the tissue that has been stapled.

Surgical stapling instrument with an articulatable end effector

A surgical instrument, such as an endoscopic or laparoscopic instrument. The surgical instrument may comprise an end effector comprising at least one sensor. The surgical instrument may also comprise an electrically conductive shaft having a distal end connected to the end effector wherein the sensor is electrically insulated from the shaft. The surgical instrument may also comprise a handle connected to a proximate end of the shaft. The handle may comprise a control unit electrically coupled to the shaft such that the shaft radiates signals as an antenna from the control unit to the sensor and receives radiated signals from the sensor. Other components electrically coupled to the shaft may also radiate the signals.

Surgical instrument with wireless communication between control unit and remote sensor

A surgical cutting and fastening instrument. The instrument comprises an end effector that has a shaft coupled thereto that is coupled to a robotic system. A tool mounting portion includes an electric, DC motor connected to a drive train in the shaft for powering the drive train. A power pack that comprises at least one charge-accumulating device connected to the DC motor for powering the DC motor is provided.

Robotically-controlled motorized surgical cutting and fastening instrument

This study explains and demonstrates the utilisation of different nonlinear-dynamics-based procedures for the purposes of structural health monitoring as well as for monitoring of robot joints.

Emil Manoach

Papers

Vibration-based methods for structural and machinery fault diagnosis based on nonlinear dynamics tools

Hemodynamics and wall mechanics of a compliance matching stent: in vitro and in vivo analysis.

Coupled, thermoelastic, large amplitude vibrations of Timoshenko beams

A model of stress-induced geometrical remodeling of vessel segments adjacent to stents and artery/graft anastomoses.

Vibration-based damage detection in plates by using time series analysis