Prediction modeling of Coriolis type mass flow: Sensor using neural network

The neural network (NN) technique has been utilized for prediction of performance of omegatube type Coriolis mass flow sensor. The results show that a well trained and well tested NN model has the capability to predict the performance of mass flow sensor for varying design parameters depending on the availability of the data and can be used as an alternative to the physical models in the sense that the results can be produced in a fast and cost effective way. The values of correlation coefficient (R) for the training, testing and whole datasets indicates that the NN results are in good agreement with the experimental results.     

Handwritten signature verification using shallow convolutional neural network

Multimedia Tools and Applications - Handwritten signatures are an undeniable and unique way to prove the identity of persons. Owing to the simplicity and uniqueness, it finds an essential place in...     

Predicting Spam Messages Using Back Propagation Neural Network

Wireless Personal Communications - With the increase in popularity of smartphones, text-based communication has also gained popularity. Availability of messaging services at low cost has resulted...     

Which separation scenarios are advantageous for membranes or distillations?

We systematically analyze power requirements of membrane and distillation processes for binary mixtures where the desired product component is more permeable and also more volatile. We first derive a shortcut method to compare the efficiency of heat pump and steam-driven distillations. Then, power requirements of heat pump distillation and membrane separation are discussed. Distillation generally requires lower power when either high component recoveries are needed (at all tested product purities), or high purity product streams with modest recoveries are needed. For high purity products at modest recoveries, membranes have a potential to provide energy benefits for highly enriched feeds, especially those composed of close boiling components. Additionally, when feed concentration is moderate to high and product recovery and purity are modest, membranes are likely to show efficiency gain. For the advantageous distillation scenarios studied, the power was generally lower than the membranes by a factor of two to seven.     

Artificial intelligence techniques in wireless sensor networks for accurate localization of user in floor,building and indoor area

Multimedia Tools and Applications - An indoor positioning system (IPS) is a network of sensors that may locate persons or objects in situations when GPS and other satellite technologies are...     

Orientation development in solid‐state extrusion and hot forming of polypropylene tubes

The use of high‐strength polymer in automotive structural components is limited by insufficient understanding of microscopic aspects of deformation for accurate numerical predictions of the mechanical behavior during forming processes. One approach to meeting these critical data needs is a careful examination of the structure property relationships that directly influence formability. Different hot forming processes (solid‐state extrusion, axial feed hot oil tube forming, and biaxial ball stretching test) are utilized in this work for investigating the effect of process conditions on the molecular orientation of polypropylene (PP) tubes. White‐Spruiell representation of orientation factors based on the results form X‐ray diffraction (XRD) patterns is utilized to analyze the development of orientation under extrusion and various forming conditions. POLYM. ENG. SCI., 2011. © 2011 Society of Plastics Engineers