Design of a Lightweight Compressed Video Stream-Based Patient Activity Monitoring System

Inpatient falls from beds in hospitals are a common problem.Such falls may result in severe injuries.This problem can be addressed by continuous monitoring of patients using cameras.Recent advancements in deep learning-based video analytics have made this task of fall detection more effective and efficient.Along with fall detection,monitoring of different activities of the patients is also of significant concern to assess the improvement in their health.High computation-intensive models are required to monitor every action of the patient precisely.This requirement limits the applicability of such networks.Hence,to keep the model lightweight,the already designed fall detection networks can be extended to monitor the general activities of the patients along with the fall detection.Motivated by the same notion,we propose a novel,lightweight,and efficient patient activity monitoring system that broadly classifies the patients’activities into fall,activity,and rest classes based on their poses.The whole network comprises three sub-networks,namely a Convolutional Neural Networks(CNN)based video compression network,a Lightweight Pose Network(LPN)and a Residual Network(ResNet)Mixer block-based activity recognition network.The compression network compresses the video streams using deep learning networks for efficient storage and retrieval;after that,LPN estimates human poses.Finally,the activity recognition network classifies the patients’activities based on their poses.The proposed system shows an overall accuracy of approx.99.7% over a standard dataset with 99.63% fall detection accuracy and efficiently monitors different events,which may help monitor the falls and improve the inpatients’health.

Syntrophic co-culture of Bacillus subtilis and Klebsiella pneumonia for degradation of kraft lignin discharged from rayon grade pulp industry

In order to search the degradability of kraft lignin, the potential bacterial strains Bacillus subtilis（GU193980） and Klebsiella pneumoniae（GU193981） were isolated, screened and applied in axenic and co-culture conditions. Results revealed that mixed culture showed better decolorization efficiency（80%） and reduction of pollution parameters（COD 73% and BOD62%） than axenic culture. This indicated syntrophic growth of these two bacteria rather than any antagonistic effect. The HPLC analysis of degraded samples of kraft lignin has shown the reduction in peak area compared to control, suggesting that decrease in color intensity might be largely attributed to the degradation of lignin by isolated bacteria.Further, the GC-MS analysis showed that most of the compounds detected in control were diminished after bacterial treatment. Further, the seed germination test using Phaseolus aureus has supported the detoxification of bacterial decolorized kraft lignin for environmental safety. All these observations have revealed that the developed bacterial co-culture was capable for the effective degradation and decolorization of lignin containing rayon grade pulp mill wastewater for environmental safety.

Effect of heavy metals and phenol on bacterial decolourisation and COD reduction of sucrose-aspartic acid Maillard product

Melanodins are amino-carbonyl complex, predominantly present in sugarcane molasses based distillery wastewater as major source of colourant. The microbial decolourisafion of melanoidin is a challenge due to its binding property with other co-pollutants of distillery waste. Results revealed that the presence of Zn2＋ （2.00-20.00 mg/L） in melanoidin solution （1200 mg/L） stimulated the bacterial growth and sucrose-aspartic acid Maillard product （SAA） decolourisation as compared to control, while Fe3＋ and Mn2＋ at the same concentration inhibited the process. However, the presence of phenol （100 mg/L） along with Zn2＋, Fe3＋ and Mn2＋ suppressed the bacterial growth, SAA decolourisation and MnP activity. The shrinkage and reduced number of bacterial cell count at higher concentration of heavy metals in presence of phenol was also observed under scanning electron microscope.