Pub Date : 2020-12-11DOI: 10.1109/MPCIT51588.2020.9350495
S. Sheela, S. Sathyanarayana
Cyclic elliptic curves (CEC) and chaotic sequences are used for cryptographic application from many decades. In this paper, authors propose a hybrid model to generate pseudo random key sequences for symmetric ciphers. Hybrid model is developed using CEC points over GF (28) and a one-dimensional cubic map. In the proposed system first, binary chaotic sequence and CEC points are given to AES SBOX to get two random sequences separately. Byte wise parity is computed for both the sequences. Based on the parity the sequences are either left or right circular shifted by a byte and two sequences are combined using the XOR operation to get the random binary sequence. The randomness of the generated sequences is analysed using various randomness test suites like NIST SP 800-22 Rev.1a and Correlation. It has been observed that all the sequences pass the randomness tests. These sequences are used to encrypt an image using additive stream cipher algorithm. The security analysis of the cipher image is conducted. The results obtained for the proposed system indicates that it is secure against cryptographic attacks.
{"title":"Generation of Pseudo Random Sequences based on Chaotic Cubic Map and Cyclic Elliptic Curves over GF (28) for Cryptographic Applications","authors":"S. Sheela, S. Sathyanarayana","doi":"10.1109/MPCIT51588.2020.9350495","DOIUrl":"https://doi.org/10.1109/MPCIT51588.2020.9350495","url":null,"abstract":"Cyclic elliptic curves (CEC) and chaotic sequences are used for cryptographic application from many decades. In this paper, authors propose a hybrid model to generate pseudo random key sequences for symmetric ciphers. Hybrid model is developed using CEC points over GF (28) and a one-dimensional cubic map. In the proposed system first, binary chaotic sequence and CEC points are given to AES SBOX to get two random sequences separately. Byte wise parity is computed for both the sequences. Based on the parity the sequences are either left or right circular shifted by a byte and two sequences are combined using the XOR operation to get the random binary sequence. The randomness of the generated sequences is analysed using various randomness test suites like NIST SP 800-22 Rev.1a and Correlation. It has been observed that all the sequences pass the randomness tests. These sequences are used to encrypt an image using additive stream cipher algorithm. The security analysis of the cipher image is conducted. The results obtained for the proposed system indicates that it is secure against cryptographic attacks.","PeriodicalId":136514,"journal":{"name":"2020 Third International Conference on Multimedia Processing, Communication & Information Technology (MPCIT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116759128","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}
Pub Date : 2020-12-11DOI: 10.1109/MPCIT51588.2020.9350454
R. Naik, S. Sathyanarayana, T. Sowmya
Key management shows an important role in the information transmissions. This paper analyzes the more improved and cost-effective key management scheme with respect to transmission overhead, computation cost. A key management policy is effectually employed for the purpose of generating a distinctive convention key for ample members to promise the security of their prospect communications, and this agreement can be allied in cloud computing for the purpose of assisting protected and skilled data distribution. The Key exchange protocols provides the two or more members to decide on a shared secret key and later be able to used for encrypting a long message. The complexity of Discrete Logarithm Problem (DLP) as basic problem considered in Diffie-Hellman Key Exchange Protocol. The Elliptic curve Diffie-Helman (ECDH) is considered as an expansion to the standard Diffie-Hellman. The ECDH function is ideal for a wide range of cryptographic functions. Key management based on ECDH provides much security on key meanwhile having more amount of storage cost and execution time involving in this. The ECDH Curve 25519 makes much faster in execution and lesser storage cost due its structure which uses much higher prime group of the order 2252.
{"title":"Key Management Using Elliptic Curve Diffie Hellman Curve 25519","authors":"R. Naik, S. Sathyanarayana, T. Sowmya","doi":"10.1109/MPCIT51588.2020.9350454","DOIUrl":"https://doi.org/10.1109/MPCIT51588.2020.9350454","url":null,"abstract":"Key management shows an important role in the information transmissions. This paper analyzes the more improved and cost-effective key management scheme with respect to transmission overhead, computation cost. A key management policy is effectually employed for the purpose of generating a distinctive convention key for ample members to promise the security of their prospect communications, and this agreement can be allied in cloud computing for the purpose of assisting protected and skilled data distribution. The Key exchange protocols provides the two or more members to decide on a shared secret key and later be able to used for encrypting a long message. The complexity of Discrete Logarithm Problem (DLP) as basic problem considered in Diffie-Hellman Key Exchange Protocol. The Elliptic curve Diffie-Helman (ECDH) is considered as an expansion to the standard Diffie-Hellman. The ECDH function is ideal for a wide range of cryptographic functions. Key management based on ECDH provides much security on key meanwhile having more amount of storage cost and execution time involving in this. The ECDH Curve 25519 makes much faster in execution and lesser storage cost due its structure which uses much higher prime group of the order 2252.","PeriodicalId":136514,"journal":{"name":"2020 Third International Conference on Multimedia Processing, Communication & Information Technology (MPCIT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128300546","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}
Pub Date : 2020-12-11DOI: 10.1109/MPCIT51588.2020.9350510
L. B. Shyamasundar, V. A. Kumar, Jhansi Rani Prathuri
An environment is developed with a distributed Apache SPARK, deployed on Hadoop cluster for timely inference and classification of security incidents. Analysis of 85GB of network-packet dataset collected over four months is done (provided by CSIR-4PI, Govt. of India). K-means machine learning algorithm is used to analyze the network traffic based on various fields. By building and evaluating models, optimum number of clusters was determined. Clustering results are evaluated by calculating the clustering score using Within-Set Sum-of-Squared-Errors(WSSSE), entropy, Silhotte, Davies-Bouldin-Index and Dunn-Index. Several plots are visualized to understand the clustering analysis results and understand the nature of incoming malicious connections.
{"title":"Analyzing Big Data Originated from Data Communication Networks using K-Means Algorithm to Understand the Nature of Incoming Malicious Connections","authors":"L. B. Shyamasundar, V. A. Kumar, Jhansi Rani Prathuri","doi":"10.1109/MPCIT51588.2020.9350510","DOIUrl":"https://doi.org/10.1109/MPCIT51588.2020.9350510","url":null,"abstract":"An environment is developed with a distributed Apache SPARK, deployed on Hadoop cluster for timely inference and classification of security incidents. Analysis of 85GB of network-packet dataset collected over four months is done (provided by CSIR-4PI, Govt. of India). K-means machine learning algorithm is used to analyze the network traffic based on various fields. By building and evaluating models, optimum number of clusters was determined. Clustering results are evaluated by calculating the clustering score using Within-Set Sum-of-Squared-Errors(WSSSE), entropy, Silhotte, Davies-Bouldin-Index and Dunn-Index. Several plots are visualized to understand the clustering analysis results and understand the nature of incoming malicious connections.","PeriodicalId":136514,"journal":{"name":"2020 Third International Conference on Multimedia Processing, Communication & Information Technology (MPCIT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128167337","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}
Pub Date : 2020-12-11DOI: 10.1109/MPCIT51588.2020.9350475
Urmila Mathure, R. Ramkrishna
This paper presents a method of control known as maximum efficiency point tracking (MEPT). This method of control is used for wireless power transfer (WPT) systems to provide maximum value of efficiency against load variations and coupling with achieving power demands of the system. In traditional MEPT systems, on both transmitting and receiving sides dc/dc converters are used in order to achieve maximum efficiency and for the regulation of output voltage. But this arrangement increases the complexity of network with increasing power loss. Some implementations lead to new problems like hard switching, large dc voltage ripples and low average efficiency. An implementation of MEPT based on pulse density modulation is explained in this paper which removes all the drawbacks in existing implementation. A PDM circuit is used in both transmitting and receiving side to achieve maximum efficiency. A simulation circuit is built in matlab in this paper to get maximum efficiency. By varying load resistances and pulse densities in the matlab Simulink circuit an efficiency and output voltage is checked By comparing the results of existing MEPT implementation with this simulation circuit of WPT using PDM it achieved efficiency upto 83% for various load resistances and pulse densities.
{"title":"Simulation of Maximum Efficiency Point Tracking in Wireless Power Transfer Systems using Pulse Density Modulation","authors":"Urmila Mathure, R. Ramkrishna","doi":"10.1109/MPCIT51588.2020.9350475","DOIUrl":"https://doi.org/10.1109/MPCIT51588.2020.9350475","url":null,"abstract":"This paper presents a method of control known as maximum efficiency point tracking (MEPT). This method of control is used for wireless power transfer (WPT) systems to provide maximum value of efficiency against load variations and coupling with achieving power demands of the system. In traditional MEPT systems, on both transmitting and receiving sides dc/dc converters are used in order to achieve maximum efficiency and for the regulation of output voltage. But this arrangement increases the complexity of network with increasing power loss. Some implementations lead to new problems like hard switching, large dc voltage ripples and low average efficiency. An implementation of MEPT based on pulse density modulation is explained in this paper which removes all the drawbacks in existing implementation. A PDM circuit is used in both transmitting and receiving side to achieve maximum efficiency. A simulation circuit is built in matlab in this paper to get maximum efficiency. By varying load resistances and pulse densities in the matlab Simulink circuit an efficiency and output voltage is checked By comparing the results of existing MEPT implementation with this simulation circuit of WPT using PDM it achieved efficiency upto 83% for various load resistances and pulse densities.","PeriodicalId":136514,"journal":{"name":"2020 Third International Conference on Multimedia Processing, Communication & Information Technology (MPCIT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124586534","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}
Pub Date : 2020-12-11DOI: 10.1109/MPCIT51588.2020.9350389
Prashanth Kannadaguli
The therapeutic analysis f microscopic blood smear begins with recognizing blood cells f various categories as well as estimating cell count in blood sample. The distinctive blood cell grading and counting furnish priceless knowledge to the pathologist about sundry infections. This exercise can be easily concluded if the shapes f blood cells are pinpointed first and using the shapes, we classify the blood cells. In this research work we build and test an automatic microscopic blood smear red blood cell (RBC) classification by using Principal Component Analysis (PCA) and Support Vector Machine (SVM) based machine learning. We train and test the statistical data models based n probabilistic pattern recognition to classify the blood smear RBC into Normal Cells, Echinocytes, Elliptocytes and Sickle cells. The H-minimum Transform (HmT) and Watershed Transform (WT) are used in pre-processing f images to increase the accuracy if segmentation shape extraction f the blood cells. Then the Bag f Features (BoF) created considering the 500 strongest features f each type f blood cell after K-Means clustering. Training takes place through Image Category Classifier (ICC) whose performance measured by using Mean Average Precision (mAP) justifies that SVM based classifiers provide audacious results.
显微血液涂片的治疗分析首先要识别血液样本中各种类型的血细胞以及估计细胞计数。独特的血细胞分级和计数为病理学家提供了关于各种感染的宝贵知识。如果首先确定血细胞的形状，并使用形状对血细胞进行分类，那么这个练习可以很容易地得出结论。在本研究中，我们基于主成分分析(PCA)和支持向量机(SVM)的机器学习，建立并测试了显微血液涂片红细胞(RBC)的自动分类。我们训练并测试了基于n概率模式识别的统计数据模型，将血涂片红细胞分为正常细胞、棘细胞、椭圆细胞和镰状细胞。采用h -最小变换(HmT)和分水岭变换(WT)对图像进行预处理，提高血细胞分割形状提取的精度。然后在K-Means聚类后，考虑每种血型的500个最强特征，创建Bag f Features (BoF)。通过图像分类器(ICC)进行训练，其性能通过使用平均精度(mAP)来衡量，证明基于SVM的分类器提供了大胆的结果。
{"title":"Microscopic Blood Smear RBC Classification using PCA and SVM based Machine Learning","authors":"Prashanth Kannadaguli","doi":"10.1109/MPCIT51588.2020.9350389","DOIUrl":"https://doi.org/10.1109/MPCIT51588.2020.9350389","url":null,"abstract":"The therapeutic analysis f microscopic blood smear begins with recognizing blood cells f various categories as well as estimating cell count in blood sample. The distinctive blood cell grading and counting furnish priceless knowledge to the pathologist about sundry infections. This exercise can be easily concluded if the shapes f blood cells are pinpointed first and using the shapes, we classify the blood cells. In this research work we build and test an automatic microscopic blood smear red blood cell (RBC) classification by using Principal Component Analysis (PCA) and Support Vector Machine (SVM) based machine learning. We train and test the statistical data models based n probabilistic pattern recognition to classify the blood smear RBC into Normal Cells, Echinocytes, Elliptocytes and Sickle cells. The H-minimum Transform (HmT) and Watershed Transform (WT) are used in pre-processing f images to increase the accuracy if segmentation shape extraction f the blood cells. Then the Bag f Features (BoF) created considering the 500 strongest features f each type f blood cell after K-Means clustering. Training takes place through Image Category Classifier (ICC) whose performance measured by using Mean Average Precision (mAP) justifies that SVM based classifiers provide audacious results.","PeriodicalId":136514,"journal":{"name":"2020 Third International Conference on Multimedia Processing, Communication & Information Technology (MPCIT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124008964","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}
Pub Date : 2020-12-11DOI: 10.1109/MPCIT51588.2020.9350429
Abhijeet Anand, Abhinav Kumar, A. Rao, Anupam Ankesh, Ankur Raj
Due to daily acceleration in the quantity of vehicles out and about, traffic issues will undoubtedly exist. The current transportation framework and vehicle parking space are unable to meet with the quantity of vehicles. Looking for a parking space in central city zones, particularly during top hours, is very strenuous for drivers. To avoid such a situation the project, Smart Parking System (S-Park) is envisioned. In this project, a real time system is developed and implemented, that allows the drivers to successfully locate and restrain the unoccupied parking areas remotely through website and Android App. The system developed, also allows the driver to navigate to their respective parking spot using Google maps. The driver needs to first register himself to avail the facility. The details of driver and vehicle are stored in database. This helps in tracking the in-out time and other details of every individual driver. S-Park provides hassle free operations in and around parking location. It also helps in attenuating the traffic congestion at a very rich scale.
{"title":"Smart Parking System (S-Park) – A Novel Application to Provide Real-Time Parking Solution","authors":"Abhijeet Anand, Abhinav Kumar, A. Rao, Anupam Ankesh, Ankur Raj","doi":"10.1109/MPCIT51588.2020.9350429","DOIUrl":"https://doi.org/10.1109/MPCIT51588.2020.9350429","url":null,"abstract":"Due to daily acceleration in the quantity of vehicles out and about, traffic issues will undoubtedly exist. The current transportation framework and vehicle parking space are unable to meet with the quantity of vehicles. Looking for a parking space in central city zones, particularly during top hours, is very strenuous for drivers. To avoid such a situation the project, Smart Parking System (S-Park) is envisioned. In this project, a real time system is developed and implemented, that allows the drivers to successfully locate and restrain the unoccupied parking areas remotely through website and Android App. The system developed, also allows the driver to navigate to their respective parking spot using Google maps. The driver needs to first register himself to avail the facility. The details of driver and vehicle are stored in database. This helps in tracking the in-out time and other details of every individual driver. S-Park provides hassle free operations in and around parking location. It also helps in attenuating the traffic congestion at a very rich scale.","PeriodicalId":136514,"journal":{"name":"2020 Third International Conference on Multimedia Processing, Communication & Information Technology (MPCIT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114001882","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}
Pub Date : 2020-12-11DOI: 10.1109/MPCIT51588.2020.9350470
S. S. Navalgund
It is a well-known fact that the placements are crucial in the professional life of a graduating student. The need for high quality output from the academia necessitates the students to be equipped with the requisite skill set to be industry-ready. This paper briefs about the training sessions done at SDMCET-Dharwad, for aiding the students in campus placement drives. Also, this paper deliberates a unique approach based on fuzzy logic for measuring the effectiveness of training sessions in terms of various dimensions namely program pacing, quality of content covered and interaction with students. The fuzzy controller is built using Mamdani and Sugeno style of inference engines. The design and simulations have been done using MATLAB and Simulink softwares.
{"title":"A Novel Fuzzy Logic Based Controller for Measuring the Effectiveness of Training for Placement","authors":"S. S. Navalgund","doi":"10.1109/MPCIT51588.2020.9350470","DOIUrl":"https://doi.org/10.1109/MPCIT51588.2020.9350470","url":null,"abstract":"It is a well-known fact that the placements are crucial in the professional life of a graduating student. The need for high quality output from the academia necessitates the students to be equipped with the requisite skill set to be industry-ready. This paper briefs about the training sessions done at SDMCET-Dharwad, for aiding the students in campus placement drives. Also, this paper deliberates a unique approach based on fuzzy logic for measuring the effectiveness of training sessions in terms of various dimensions namely program pacing, quality of content covered and interaction with students. The fuzzy controller is built using Mamdani and Sugeno style of inference engines. The design and simulations have been done using MATLAB and Simulink softwares.","PeriodicalId":136514,"journal":{"name":"2020 Third International Conference on Multimedia Processing, Communication & Information Technology (MPCIT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130329995","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}
Pub Date : 2020-12-11DOI: 10.1109/mpcit51588.2020.9350424
{"title":"MPCIT 2020 Table of Contents","authors":"","doi":"10.1109/mpcit51588.2020.9350424","DOIUrl":"https://doi.org/10.1109/mpcit51588.2020.9350424","url":null,"abstract":"","PeriodicalId":136514,"journal":{"name":"2020 Third International Conference on Multimedia Processing, Communication & Information Technology (MPCIT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125207921","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}
Pub Date : 2020-12-11DOI: 10.1109/MPCIT51588.2020.9350431
B. Yaswanth, R. Darshan, H. Pavan, D. Srinivasa, B. T. V. Murthy
In the global scenario, women’s safety is a crucial problem. The security of women has become a greater challenge to many families in their daily life, hence a system is developed using rapidly growing technologies to address this problem. This paper mainly focuses on an IoT based self-security system that is comfortable, easy to use and wearable, and helps to share the user location when they feel panic and also help to find the nearest safe place. The designed system is user friendly and it can be accessed only by a specific person. The system is controlled through raspberry pi, and it has two different modes namely normal mode and security mode. In normal mode, user can register their fingerprint, and in security mode, the fingerprint sensor acts as a panic button, and when a fingerprint is detected system shares the location and captures the photo of the culprit and stores it in the cloud. The machine learning algorithm gets the user location as input and predicts the nearest safe place location.
{"title":"Smart Safety and Security Solution for Women using kNN Algorithm and IoT","authors":"B. Yaswanth, R. Darshan, H. Pavan, D. Srinivasa, B. T. V. Murthy","doi":"10.1109/MPCIT51588.2020.9350431","DOIUrl":"https://doi.org/10.1109/MPCIT51588.2020.9350431","url":null,"abstract":"In the global scenario, women’s safety is a crucial problem. The security of women has become a greater challenge to many families in their daily life, hence a system is developed using rapidly growing technologies to address this problem. This paper mainly focuses on an IoT based self-security system that is comfortable, easy to use and wearable, and helps to share the user location when they feel panic and also help to find the nearest safe place. The designed system is user friendly and it can be accessed only by a specific person. The system is controlled through raspberry pi, and it has two different modes namely normal mode and security mode. In normal mode, user can register their fingerprint, and in security mode, the fingerprint sensor acts as a panic button, and when a fingerprint is detected system shares the location and captures the photo of the culprit and stores it in the cloud. The machine learning algorithm gets the user location as input and predicts the nearest safe place location.","PeriodicalId":136514,"journal":{"name":"2020 Third International Conference on Multimedia Processing, Communication & Information Technology (MPCIT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126467379","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}
Pub Date : 2020-12-11DOI: 10.1109/MPCIT51588.2020.9350455
Abdul-Gafoor Mohamed, P. Mahanta
The evolution of Data Management Scenarios augmented by scientific discovery and rigor is apparent in the industry, judging by the sheer focus on it by analysts and others over the past couple of years. Machine Learning helps immensely playing its part in simplifying enterprise data landscapes, contributing to many aspects of Data Management. We see value in focusing on the Data Discovery and Data Quality aspects in this context, as enterprises these days have complex landscapes, with the average enterprise using more than 5 Cloud storages in addition to their on-prem data sources.A greater affinity for enterprise grade Machine Learning has created a significant pull for system design. This leads platforms towards capabilities like standard APIs for scaled-database queries and integration scenarios. This paper explores the integration of Machine Learning tools and customized libraries with any Cloud Platform for enhancing the stakeholders’ experience with Analytics. As far as concepts are concerned, we propose a hypothesis for scaling an existent platform to a community-based approach, which helps enable sharing of experimental iterations, ideally translating into industry specific solutions that should stay extremely reusable. The intent is to offer a data model flexible enough to handle diverse data scenarios, evaluating confidence scores for each of these. It should enable reproducible shared experiments with consistent evaluated scores, thereby easing the integration process through automated guidance. This paper will touch upon the good practices and architectural recommendations that need to be considered for general Machine Learning applications.
{"title":"Scientific Discovery and Rigor with ML","authors":"Abdul-Gafoor Mohamed, P. Mahanta","doi":"10.1109/MPCIT51588.2020.9350455","DOIUrl":"https://doi.org/10.1109/MPCIT51588.2020.9350455","url":null,"abstract":"The evolution of Data Management Scenarios augmented by scientific discovery and rigor is apparent in the industry, judging by the sheer focus on it by analysts and others over the past couple of years. Machine Learning helps immensely playing its part in simplifying enterprise data landscapes, contributing to many aspects of Data Management. We see value in focusing on the Data Discovery and Data Quality aspects in this context, as enterprises these days have complex landscapes, with the average enterprise using more than 5 Cloud storages in addition to their on-prem data sources.A greater affinity for enterprise grade Machine Learning has created a significant pull for system design. This leads platforms towards capabilities like standard APIs for scaled-database queries and integration scenarios. This paper explores the integration of Machine Learning tools and customized libraries with any Cloud Platform for enhancing the stakeholders’ experience with Analytics. As far as concepts are concerned, we propose a hypothesis for scaling an existent platform to a community-based approach, which helps enable sharing of experimental iterations, ideally translating into industry specific solutions that should stay extremely reusable. The intent is to offer a data model flexible enough to handle diverse data scenarios, evaluating confidence scores for each of these. It should enable reproducible shared experiments with consistent evaluated scores, thereby easing the integration process through automated guidance. This paper will touch upon the good practices and architectural recommendations that need to be considered for general Machine Learning applications.","PeriodicalId":136514,"journal":{"name":"2020 Third International Conference on Multimedia Processing, Communication & Information Technology (MPCIT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116100424","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：