Multi-Path Service Function Chaining for Mobile Surveillance of Animal Husbandry

Animal husbandry is the pillar industry in some ethnic areas of China.However,the communication/networking infrastructure in these areas is often underdeveloped,thus the difficulty in centralized management,and challenges for the effective monitoring.Considering the dynamics of the field monitoring environment,as well as the diversity and mobility of monitoring targets,traditional WSN(Wireless Sensor Networks)or IoT(Internet of Things)is difficult to meet the surveillance needs.Mobile surveillance that features the collaboration of various functions(camera,sensing,image recognition,etc.)deployed on mobile devices is desirable in a volatile wireless environment.This paper proposes the service function chaining for mobile surveillance of animal husbandry,which orchestrates multi-path multifunction(MPMF)chains to help mobile devices to collaborate in complex surveillance tasks,provide backup chains in case the primary service function chain fails due to mobility,signal strength,obstacle,etc.,and make up for the defects of difficult deployment of monitoring facilities in ethnic areas.MPMF algorithmmodels both mobile devices and various functions deployed on them as abstract graph nodes,so that chains that are required to traverse various functions and hosting mobile devices can be orchestrated in a single graphbased query through modified and adapted Dijkstra-like algorithms,with their cost ordered automatically.Experiment results show that the proposed MPMF algorithm finds multiple least-costly chains that traverse demanded functions in a timely fashion on Raspberry Pi-equipped mobile devices.

A Weighted Spatially Constrained Finite Mixture Model for Image Segmentation

Spatially Constrained Mixture Model(SCMM)is an image segmentation model that works over the framework of maximum a-posteriori and Markov Random Field(MAP-MRF).It developed its own maximization step to be used within this framework.This research has proposed an improvement in the SCMM’s maximization step for segmenting simulated brain Magnetic Resonance Images(MRIs).The improved model is named as the Weighted Spatially Constrained Finite Mixture Model(WSCFMM).To compare the performance of SCMM and WSCFMM,simulated T1-Weighted normal MRIs were segmented.A region of interest(ROI)was extracted from segmented images.The similarity level between the extracted ROI and the ground truth(GT)was found by using the Jaccard and Dice similarity measuring method.According to the Jaccard similarity measuring method,WSCFMM showed an overall improvement of 4.72%,whereas the Dice similarity measuring method provided an overall improvement of 2.65%against the SCMM.Besides,WSCFMM signicantly stabilized and reduced the execution time by showing an improvement of 83.71%.The study concludes that WSCFMM is a stable model and performs better as compared to the SCMM in noisy and noise-free environments.