Semi-Supervised Learning Based Big Data-Driven Anomaly Detection in Mobile Wireless Networks

With rising capacity demand in mobile networks, the infrastructure is also becoming increasingly denser and complex. This results in collection of larger amount of raw data(big data) that is generated at different levels of network architecture and is typically underutilized. To unleash its full value, innovative machine learning algorithms need to be utilized in order to extract valuable insights which can be used for improving the overall network's performance. Additionally, a major challenge for network operators is to cope up with increasing number of complete(or partial) cell outages and to simultaneously reduce operational expenditure. This paper contributes towards the aforementioned problems by exploiting big data generated from the core network of 4 G LTE-A to detect network's anomalous behavior. We present a semi-supervised statistical-based anomaly detection technique to identify in time: first, unusually low user activity region depicting sleeping cell, which is a special case of cell outage; and second, unusually high user traffic area corresponding to a situation where special action such as additional resource allocation, fault avoidance solution etc. may be needed. Achieved results demonstrate that the proposed method can be used for timely and reliable anomaly detection in current and future cellular networks.

Effect of pollution on DNA damage and essential fatty acid profile in Cirrhinus mrigala from River Chenab

The objective of this study was to evaluate the effect of anthropogenic pollution on DNA damage and the fatty acid profile of the bottom dweller fish （Cirrhinus mr^gala）, collected from the River Chenab, in order to assess the effect of the toxicants on the quality of the fish meat. The levels ofCd, Hg, Cu, Mn, Zn, Pb, Cr and Sn and of phenols from this river were significantly higher than the permissible limits set by the USEPA. Comet assays showed DNA damage in Cirrhinus mr^gala collected from three different sampling sites in the polluted area of the river. Significant differences were observed for DNA damage through comet assay in fish collected from polluted compared to control sites. No significant differences were observed for DNA damage between farmed and fish collected from upstream. The micronucleus assay showed similar trends. Fish from the highly polluted sites showed less number of fatty acids and more saturated fatty acids in their meat compared to fish from less polluted areas. Several fatty acids were missing in fish with higher levels of DNA in comet tail and micronucleus induction. Long-chain polyunsaturated fatty acids, eicosapentaenoic acid （20：5n-3） was found missing in the fish from polluted environment while it was found in considerable amount in farmed fish 7.8±0.4%. Docosahexaenoic acid （22：6n-3） also showed significant differences as 0.1±0.0 and 7.0±0.1% respectively, in wild polluted and fanned fishes.

ESTIMATION OF VOLATILE CONSTITUENTS IN THE FISH FLESH FROM WILD AND FARMED CIRRHINA MRIGALA AND CYPRINUS CARPIO

Analysis of fish meat using gas chromatography is described.Flavor is the sensation arising from the interplay of the signals of sensing smell, taste and irritating stimuli from food stuff.For human, flavor and nutrition are inseparable.In fish, trace amount of volatile organic compounds (VOCs) are the major compounds to affect consumer’s preference, which are produced during storage and spoilage.In the present study, volatile compounds were extracted by Likens-Nickerson concurrent distillation apparatus from wild and farmed Cirrhina mrigala and Cyprinus carpio. The quantitative and qualitative estimation of volatiles was made by gas chromatography.Wild and farmed fish of different fish sizes were compared for these compounds (appearing in the form of peaks), which were identified from their retention time by comparing with the standards.Fifteen major VOCs were found in these species which included hexadecane, 3-octanol, hexanal, decane, 3-hexene-1-ol, 2-undecanone, 2-heptanone, butanal, 2-nonanone, 1-heptanal, furaldehyde, 3-methyl-1-butanal, trans-3-hexene-1-ol, octanal and decanal.These compounds varied qualitatively and quantitatively in both wild and farmed fish of different fish sizes.

Development of Bioinfo-Portal Tool for the Analysis of Genomic and Proteomic Data

The recent explosion of biological data and the concomitant proliferation of distributed databases make it challenging for biologists and bioinformaticians to discover the best data resources for their needs, and the most efficient way to access and use them For the biologist, running bioinformatics analyses involve a time-consuming management of data and tools. Users need support to organize their work, retrieve parameters and reproduce their analyses. They also need to be able to combine their analytic tools using a safe data flow software mechanism. Finally we have designed a system, Bioinfo-Portal, to provide a flexible and usable web environment for defining and running bioinformatics analyses. It embeds simple yet powerful data management features that allow the user to reproduce analyses and to combine tools using an adobe flex tool. Bioinfo-Portal can also act as a front end to provide a unified view of already-existing collections of bioinformatics resources. Users can analyze genomic and proteomic data by using the tools that has been integrated in the portal （tools for alignments, dotplots, motif detection, domain analysis, profile searching and tertiary structure prediction）. The sequences that user obtained from portal＇s nucleotide and protein databases are easily analyzed by the portal tools on the same interface in no time. User can also take benefit from the animations.