In Wireless Sensor Networks (WSNs), effective transmission with acceptable degradation in the power of sensor nodes is a key challenge. In a large network, holdup is bound to occur in communicating superfluous data. The aforementioned issues namely, energy, delay and data redundancy are interdependent on each other and a tradeoff needs to be worked out to improve the overall performance. The extant methods in the literature employ either centralized or distributed approach to select a cluster head (CH). In this paper, sink originated hybrid and dynamic clustering with routing technique is proposed. The proposed routing algorithm works based on node handling capability of each sensor node in the selection of CH and also helps in identifying the forwarder node. In addition, processing load of a sensor node is also considered for selecting the forwarder. Both space and time correlation is used to collect data from the clusters and then aggregated to provide a proficient communication. The introduced method is evaluated with the performance of the previously available techniques like, Data Routing for In-Network Aggregation (DRINA), Efficient Data Collection Aware of Spatio-Temporal Correlation (EAST), Cluster-Based Data Aggregation (CBDA), Energy-Efficient Data Aggregation and Transfer (EEDAT), and Distributed algorithm for Integrated tree Construction and data Aggregation (DICA). Simulation parameters considered for assess ing the performance of the proposed algorithm are aggregation ratio, routing overhead, packet delivery fraction, throughput, packet delay and consumed energy. The experimental analysis of the introduced algorithm generates paramount outcome of finest aggregation quality with diverse key characteristics and circumstances as required by a sensor network.

No abstract

Thousands of patients around the world affecting their health with various factor as age, body mass index, cholesterol levels, albumin levels and several other factor. Prediction of health outcome due to these factors at a proper time can be served as an early warning. Recent growth in machine learning algorithm inspired us to build a predictive model for better healthcare facilities. In our work we have focused on problem of noisy and imbalanced dataset in which majority class is favored over minority one that leads to false prediction. We have experimented with two publicly available medical imbalanced dataset which varies in its size as MIT’s GOSSIS death and PIMA Indians Diabetes Dataset based on binary class. In this model we have investigated 3 oversampling techniques (Synthetic Minority Oversampler, Random Oversampler and Adaptive Synthetic Sampler) along with two undersampling techniques (Random Undersampler and Near Miss) which were paired with 3 data reduction and cleaning methods namely Tomek Links, One Sided Selection and Edited Nearest Neighbors. At last, we found that combination of Adaptive Synthetic Sampler along with One Sided Selection perform better in case of large size dataset while combination of random oversampler along with Tomek Link showed better performance in case of low size data dataset. We have also analyzed that oversampling technique gives quite promising results in comparison to undersampling methods specifically when applied with machine learning classifiers as these classifiers are data hungry algorithms.

No abstract

In the original version of this article, the given and family names of Stephen Thompson were incorrectly structured. Correct is Thompson StephanThe original article has been corrected.Publisher's Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.