{"title":"A comparative study of classifiers used in facial embedding classification","authors":"Sourabh Sarkar, Geeta Sikka","doi":"10.1109/ICSCCC.2018.8703359","DOIUrl":"https://doi.org/10.1109/ICSCCC.2018.8703359","url":null,"abstract":"Face recognition, recently, has been a fast and effective method of authentication with the advent of deep learning and powerful hardware. This paper investigates different classifiers used in classifying facial embeddings and evaluates their performance. The paper also focuses on an easily deployable pipeline for face recognition using Python which can be used to develop a face recognition system on portable low-power hardware devices. The methodology discussed uses pretrained models and frameworks which results in state-of-the-art performance without the need of any powerful hardware. The proposed methodology achieves an F1 score of 0. 9947with an AUC score of 0.9997 on LFW dataset.","PeriodicalId":148491,"journal":{"name":"2018 First International Conference on Secure Cyber Computing and Communication (ICSCCC)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125148708","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Novel Framework for Smart Crop Monitoring Using Internet of Things (IOT)","authors":"K. Ghanshala, Rahul Chauhan, R. Joshi","doi":"10.1109/ICSCCC.2018.8703366","DOIUrl":"https://doi.org/10.1109/ICSCCC.2018.8703366","url":null,"abstract":"Agriculture is one of the area which required urgent attention and advancement for high yield and efficient utilization of resources. In this paper an approach of smart crop monitoring is presented through Internet of things (IOT). A 4 level framework is proposed namely sensing devices, sensor data level, base station level, edge computing and cloud data level for smart crop monitoring. Method proposed here focuses on analysing the soil nutrients (eg. NPK), soil moisture, temperature and humidity through a sensor node designed using arduino. Sensor node also consists of a wireless Zigbee module, metos NPK sensor, motor and water sprinklers. LAN of sensor node is designed using Zigbee and LEACH routing protocol is used for hopping. Collected data at gateway is being uploaded to cloud using an ESP8266 Wi-Fi module. An experimental setup was made in the field. Various data collected, analyzed and necessary information was sent to farmers for appropriate action. The data collected at cloud is analysed using machine learning technique and available to the farmers through soil nutrient index to monitor their soil nutrient requirements and ensure better crop yield.","PeriodicalId":148491,"journal":{"name":"2018 First International Conference on Secure Cyber Computing and Communication (ICSCCC)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125272702","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An efficient Gaussian Noise Reduction Technique For Noisy Images using optimized filter approach","authors":"Sandeep Chand Kumain, Maheep Singh, Navjot Singh, Krishan Kumar","doi":"10.1109/ICSCCC.2018.8703305","DOIUrl":"https://doi.org/10.1109/ICSCCC.2018.8703305","url":null,"abstract":"In the Multimedia era, removal of the Noises from an image becomes a key challenge in the field of Digital Image Processing (DIP) and Computer Vision. Noise may be mixed with an image during capturing time, transmission time or due to dust particle on the screen of capturing device. Therefore, removal of these unwanted signals from the image is urgently required for the better analysis of the image and the de-noised image is more meaningful for Object detection, Edge detection and many more. There are various types of image noise, however, Gaussian Noise and Impulse Noise are commonly found in the image. This work focuses on the outliers and Mean Filter to improve the performance for Gaussian noise reduction from the image. In experimental assessments, artificial noise has been mixed using MATLAB to MSRA (10k images) dataset, this dataset is used to evaluate our proposed technique. The experiment results show that the proposed approach improves the performance in noise reduction over other filter approaches.","PeriodicalId":148491,"journal":{"name":"2018 First International Conference on Secure Cyber Computing and Communication (ICSCCC)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117331224","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Feature Weighting for Improved Classification of Anuran Calls","authors":"Dalwinder Singh, Birmohan Singh","doi":"10.1109/ICSCCC.2018.8703371","DOIUrl":"https://doi.org/10.1109/ICSCCC.2018.8703371","url":null,"abstract":"Automatic bioacoustics monitoring has a great potential to assess the ecosystem health. However, such bioacoustics systems are not highly accurate because the classification of data involves a large number of species. In this paper, we have considered the related problem which involves classification of frog and toad species from their sounds. A publicly available large dataset is used for this purpose where performance is evaluated with leave-one-out cross-validation on the k-NN classifier. The dataset was prepared by extracting Mel-frequency cepstral coefficients (MFCCs)features from the recorded anurans calls, and it comprises the classification of anurans at family, genus and species levels. This paper presents the application of feature weighting to improve the classification of anurans calls. It is a continuous search problem where weights are assigned to features with respect to their contribution in classification. These weights are searched with the Ant Lion optimization along with the best parametric values of the k-NN classifier. The outcomes of experiments show that the proposed approach has successfully enhanced the classification accuracy at family, genus and species levels. The maximum classification accuracies of 95.01%, 88.38%,and 88.08% are achieved at family, genus and species levels respectively which has outperformed the feature selection approach as well as existing works.","PeriodicalId":148491,"journal":{"name":"2018 First International Conference on Secure Cyber Computing and Communication (ICSCCC)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127949632","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"ICSCCC 2018 Author Index","authors":"","doi":"10.1109/icsccc.2018.8703297","DOIUrl":"https://doi.org/10.1109/icsccc.2018.8703297","url":null,"abstract":"","PeriodicalId":148491,"journal":{"name":"2018 First International Conference on Secure Cyber Computing and Communication (ICSCCC)","volume":"132 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131654307","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Fog Classification and Accuracy Measurement Using SVM","authors":"M. Anwar, A. Khosla","doi":"10.1109/ICSCCC.2018.8703365","DOIUrl":"https://doi.org/10.1109/ICSCCC.2018.8703365","url":null,"abstract":"Fog is not always homogeneous in nature. The fog density and distribution are varying in nature while capturing images through a camera or sensor. In contrast to homogeneity the fog may be treated as heterogeneous which depends upon the density variation of its constituents particles i.e water droplets. Classification is important and sometimes helpful to design a fog removal algorithm for vision enhancement while considering type of fog without knowing its density. Classification methods are applicable for both synthetic and camera images. This paper presents Support Vector Machine (SVM) that plays a key role to classify the synthetic data into two classes with accuracy measurement. Confusion matrix and Receiver Operational Characteristic (ROC) curve hold SVM to quantify the accuracy. The proposed method quantifies the type of fog with more than 92 percent accuracy for synthetically generated images containing various objects and environments in foggy situation. This acquaintance will finally help to generate a natural image dataset of homogeneous and heterogeneous foggy images.","PeriodicalId":148491,"journal":{"name":"2018 First International Conference on Secure Cyber Computing and Communication (ICSCCC)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133824946","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Concentric Layered Architecture for Multi-Level Clustering in Large-Scale Wireless Sensor Networks","authors":"Harmanpreet Singh, Damanpreet Singh","doi":"10.1109/ICSCCC.2018.8703282","DOIUrl":"https://doi.org/10.1109/ICSCCC.2018.8703282","url":null,"abstract":"Multi-level clustering offers energy efficient data gathering and much needed scalability in large-scale wireless sensor networks (WSNs). Although, few multi-level frameworks have been designed for static clustering and manually deployed WSNs, but no work has been done for randomly deployed WSN performing dynamic clustering. Moreover, there is a lack of structured framework for evolutionary optimization based multilevel clustering protocols. Design of multi-level clustering depends on two parameters: 1) optimal position of layers and 2) number of sensor nodes at each layer. Based on these parameters, a concentric layered architecture (CLA) is designed in this paper to perform multi-level clustering in randomly deployed WSN. CLA divide the network into layers based on node density and number of sensor nodes at each layer. Further, CLA is evaluated on an evolutionary optimization technique based clustering approach namely PSO-C. Simulation results show that the proposed CLA significantly improves the network lifetime and energy efficiency.","PeriodicalId":148491,"journal":{"name":"2018 First International Conference on Secure Cyber Computing and Communication (ICSCCC)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116664169","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Deep Leaming Approaches for Brain Tumor Segmentation: A Review","authors":"A. Kamboj, Rajneesh Rani, Jiten Chaudhary","doi":"10.1109/ICSCCC.2018.8703202","DOIUrl":"https://doi.org/10.1109/ICSCCC.2018.8703202","url":null,"abstract":"Brain tumor has been a cause of concern for the medical fraternity. The manual segmentation of brain tumor by medical expert is a time-consuming process and this needs to be automated. The Computer-aided diagnosis (CAD) system, help to improve the diagnosis and reduces the overall time required to identify the tumor. Researchers have proposed methods that can diagnose brain tumor based on machine learning and deep learning techniques. But the methods based on deep learning have proven much better than the traditional machine learning methods. In this paper we have discussed the state-of-the-art methods for brain tumor segmentation based on deep learning.","PeriodicalId":148491,"journal":{"name":"2018 First International Conference on Secure Cyber Computing and Communication (ICSCCC)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114536019","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Abnormality detection in ECG using hybrid feature extraction approach","authors":"Ritu Singh, N. Rajpal, R. Mehta","doi":"10.1109/ICSCCC.2018.8703349","DOIUrl":"https://doi.org/10.1109/ICSCCC.2018.8703349","url":null,"abstract":"Biomedical signals like Electrocardiogram (ECG) contains essential information related to the functionality of heart. The pre analysis of ECG disturbances, aided by computer designed algorithms can prove to be efficient support in reducing cardiac emergencies. In this present method, dual tree complex wavelet transform (DTCWT) with linear discriminate analysis (LDA) also known as hybrid feature extraction are employed for denoising and dimensionally reduced non linear feature extraction respectively. The classification and analysis of ECG dataset into normal and abnormal beats is done by independently deploying five classifiers like support vector machine (SVM), decision tree (DT), back propagation neural network (BPNN), feed forward neural network (FNNN) and K nearest neighbour (KNN). The outcomes of proposed work are compared with pre existing methods. The highest percentage accuracy of 99.7% is achieved using BPNN, SVM and KNN. The simulation results show that the shift invariance nature of DTCWT provides a robust technique for non linear and non stationary ECG signals.","PeriodicalId":148491,"journal":{"name":"2018 First International Conference on Secure Cyber Computing and Communication (ICSCCC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122203919","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"LoRaWAN based GPS tracking of city-buses for smart public transport system","authors":"Swapnil Hattarge, Akshay M. Kekre, A. Kothari","doi":"10.1109/ICSCCC.2018.8703356","DOIUrl":"https://doi.org/10.1109/ICSCCC.2018.8703356","url":null,"abstract":"The increasing level of air-pollution due to vehicular emissions is an imminent threat to our environment. In order to tackle this situation, we need to promote and adapt public transport. Making the existing city-bus system smarter by tracking the buses is the step that can be taken immediately for making public vehicles more accessible. The main hurdle in deploying traditional GPS trackers is the maintenance cost which can significantly be reduced by using LoRaWAN instead of GSM/GPRS modules. In this paper, an end-to-end wireless tracking system based on LoRaWAN is proposed. The gateway is set up along with server and data is stored in a cloud database. Android application is built to show the current location of the transmitter to the user. The main contribution of this paper is in building a custom gateway and server which provides more flexibility in designing the network parameters when compared to the commonly used third-party gateway or server applications.","PeriodicalId":148491,"journal":{"name":"2018 First International Conference on Secure Cyber Computing and Communication (ICSCCC)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127501108","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}