Axiomatic Characterizations of a Proportional Influence Measure for Sequential Projects with Imperfect Reliability

We define and axiomatically characterize a new proportional influence measure for sequential projects with imperfect reliability. We consider a model in which a finite set of players aims to complete a project, consisting of a finite number of tasks, which can only be carried out by certain specific players. Moreover, we assume the players to be imperfectly reliable, i.e., players are not guaranteed to carry out a task successfully. To determine which players are most important for the completion of a project, we use a proportional influence measure. This paper provides two characterizations of this influence measure. The most prominent property in the first characterization is task decomposability. This property describes the relationship between the influence measure of a project and the measures of influence one would obtain if one divides the tasks of the project over multiple independent smaller projects. Invariance under replacement is the most prominent property of the second characterization. If, in a certain task group, a specific player is replaced by a new player who was not in the original player set, this property states that this should have no effect on the allocated measure of influence of any other original player.

Real Time CHIS Model for Efficient Sugarcane Plant Growth and Yield Estimation Model using Satellite Images

The research on plant growth estimation of sugarcane plants is a key factor ongoing now days. The problem of plant growth and yield estimation of sugarcane plants is well studied. There are number of solutions recommended by different researchers, still they suffer with poor accuracy. Existing methods measure the plant growth according to the rainfall and temperature which introduces poor performance. To improve the performance, an efficient Climate Hydro Image Soil Model (CHISM) is presented. The model considers various properties namely climate conditions like temperature, humidity and hydrologic features namely rainfall, water poured and soil conditions towards plant growth. The method uses the satellite images in obtaining the soil condition, by applying image processing technique, the soil condition are obtained. Remaining features are obtained through the regional data set provided by agriculture sector. Using all these features, the method estimates various influence measure on different features considered. The method computes rainfall influence measure (RIM), water influence measure (WIM), temperature influence measure (TIM), humidity influence measure (HIM), and soil influence measure (SIM). Using all these measure, the model computes the plant growth rate (PGR) and Yield Rate (YR) in different time window. According to the measures estimated, the model performs water regulation. The method improves the performance of plant growth estimation and crop yield.

Sensitivity Analysis of Deep Neural Networks

Deep neural networks (DNNs) have achieved superior performance in various prediction tasks, but can be very vulnerable to adversarial examples or perturbations. Therefore, it is crucial to measure the sensitivity of DNNs to various forms of perturbations in real applications. We introduce a novel perturbation manifold and its associated influence measure to quantify the effects of various perturbations on DNN classifiers. Such perturbations include various external and internal perturbations to input samples and network parameters. The proposed measure is motivated by information geometry and provides desirable invariance properties. We demonstrate that our influence measure is useful for four model building tasks: detecting potential ‘outliers’, analyzing the sensitivity of model architectures, comparing network sensitivity between training and test sets, and locating vulnerable areas. Experiments show reasonably good performance of the proposed measure for the popular DNN models ResNet50 and DenseNet121 on CIFAR10 and MNIST datasets.