Computation of Automatic Logistic Handling Using Artificial Intelligence in Data Mart Applications
D. Maria Manuel Vianny1, S. Manikanan2, K.Vaidehi3, Syed Khasim4
1Assistant Professor, Department of Computing Science and Engineering, Chitkara Institute of Engineering and Technology, Chitkara University, Punjab-140 401, India
2Department of Information Technology, E.G.S. Pillay Engineering College, Nagapattinam, Tamil Nadu, India ([email protected])
3Department of Computer Science & Engineering, Stanley College of Engineering and Technology for Women, Hyderabad, India,([email protected])
4Professor, Department of Computer Science & Engineering, Dr.Samuel George Institute of Engineering & Technology, Markapur, Andhra Pradesh, India ([email protected])
ABSTRACT – Today web crawlers are expected key part in social occasion information from wherever and play put. The data analytics is motorized process and convey particular essential administration comes to fruition. The artificial intelligence is the field of settling on decision and significant learning process. The proposed show exhibits that electronic big data analysis process and making diverse features using machine learning wellsprings of information and programming building model. This paper illuminates particular gathering, data check, data logging, constancy, dynamism of various pros at various conditions.
INDEX TERMS: Artificial Intelligence, Data Science, Big Data Analytics, Data Handling
1.INTRODUCTION
Google is one of the famous search engine, which is collected various data and analysis data for making successful decision. Artificial Intelligence is the machine learning technique for search engine to collect information. When Big Data analysis process the number of iteration to be considered and the information exchanged by internet. For example Amazon, IBM, Microsoft and other companies are developed various automated search engine and software architecture for handling natural language input data and extract data from database [1]. The CIA (Computer Information and Architecture) developed “Data Mart Cell” for analysis data automatically and making successful decision support system [2].
Amazon RedShit is the data analysis tool for collecting logs automatically based on number of input queries. The IT and ITeS are showing popularity of the various real time applications. Acting used IT approaches increases the speed, reliability, quality and automated in all the applications. The Industry needs automated data processing and analyzing agent [3]. The solution can be formulated by various characteristics such as input request, selling and delivering information, product details, etc. Data handing the critical process and targeting social data likes logs, access details, affected details by using mathematical approach. An AI based „H‟ approach is statistical model for handle Big Data. It enables us to collect data log values. The proposed AI system is aimed to analyze various kind of data analyzing process such as social infrastructure, logistics services, financial services, reliability and end user product industry.
2.GENERALTERMSANDAPPROACHES
Artificial Intelligence is the study of agent interaction system with intelligent behavior on the demand of various automated applications, internet application, e-commerce solutions, etc and intelligent behavior systems needed for the society. Decision based approaches such as extraction, queries models, statistical model, requires following dependencies
1. Working with Big Data
2. Reliable and Portable forecast processing 3. Working with large spatial problem 4. Production and non-linear problem
5. Machine learning and Software Architecture Approach
Extracting the effectiveness of different task including queries, demand forecasting and special model is required to solve real time systems [5].
AI is one of the demands for approval of credit/debit decision process, medical apps, cyber forensics, supply chain management, optimization, decision support systems, etc. Artificial Intelligence classifies as machine learning techniques, software model, and information operation and decision support systems. Machine learning techniques handling natural inputs from difference input medium, software architecture to a model based approach to handling real time operations.
Inference rule specifies deep learning inputs, data analytics process, parallel and distributed systems.
Deep learning includes machine learning process, natural learning process, knowledge discovery process, data conversion and status modeling [4].
A Modern analysis tool of customer demand and need the various automated software developed.
For example the voice input collected from Google, the statistical machine learning, etc [6].
3.MODEL OF AICOMPUTATION
We propose a computational model for assigning execution time of each state. AI computing system defines following input states
1. Table Formation – Micro and Marco objective function 2. Automated and Aggregated input parameters
3. Extract information from cluster nodes and prediction factor
For example, we collected input from e-commerce database for customer and product delivery process.
Cust_IT Values A001 600 A002 750 B010 1,440 Table 1: Macro Table for customer processing
Cust_IT Prod_IT Values Time Cost A001 P124 600 12.35 $67 A002 P135 750 22.45 $56 B010 P235 1,440 17.31 $25 Table 2: Micro Table for customer processing
S.No Cust_IT Values Method Cost
1 A001 600 Get $67
2 A002 750 Post $56
3 B010 1,440 Post $25
Table 3: Predict Table for customer ordering y=a1x1+a2x2+….+anxn
y – Cart factor productivity
x – Number of input different actions a – Number of inputs co-efficient
The following are the computation algorithm for calculating each stage values Step 1: V={v0,v1,v2….vn} – input values
Step 2: S – finite state belongs to V
Step 3: T is the set of traversal time as T1,T2,..
Step 4: Label – Function to assign each stage input for calculating computational time Step 5: The final execution time
Vi -> S{[Tn]} – n – number of Iterations Example for computation time process
Each stage specifies by values of input parameters, execution time factor, stages and final result.
1.Execution Time:
The execution time calculated by input factors such as memory, cache, pipeline process. In this paper, we verify real time input propagation based on response and invariance factor.
∑ U(invariance) € S{Tn} where n>=0 2. Logistic data handling:
For handling NoSQL database inputs Table 4 extracts log details. Each values of cart information are prescribed and picked the product parameters. The purpose of this analysis to reduce various time taken at each values.
Data Collection
Log Collection
Time
12/12/2017 –
16/12/2017 Function Working
Object Inputs
Level Select Parameters Feature Access ID Table 4: Data Log Table order processing
The proposed was experimented by using working load data inputs. Finally the reduced working time was evaluated by input conditions. AI models various programming language inputs are implemented and analyzed by each characteristics. In this paper, temporal and inference values are measured by using axiom calculations. Axiom parameters are set by input training set up by table.
Axiom of Q <= Time (T) – State U input conditions B1_Time = Label (S1) – Initial Value
B2_Time = Label (S2) – Next Value
Axiom of Q <= Time (T) = Label values state S CONCLUSION
In this paper, the AI based system implemented with machine learning, deep learning, and software architecture inputs. We collected computer based inputs and automated data analysis process handlers. We proposed real time application handlers for generating execution time and reduced work done time based on input modeling. We verified extracted inputs like relationship between learning inputs, log values and social data. The log data is evaluated and analyzed from risk based model and result to be implemented.
REFERENCES
[1] Viktor P. Semenov, Vladimir V. Cheronkulsky and Natalya V. Razomchava, “Reasearch of Artificial Intelligence in the Retail Management Problems” 2017 IEEE II Conference on Controls in Technical Systems, DOI: 978-1-5386-0777-0/17, pp:333-336
[2] Satoshi Yamne, “Deductively Verifying Embedded Software in the Era of Artificial Intelligence
= Machine Learning + Software Sciences, 2017 IEEE 6th Golbal Conference on Consumer Electronics, DOI:978-1-5090-4045-2/17 .
[3] S.Manikandan, Dr.M.Chinnadurai, "Motion Detection Algorithm for Agent Interaction Surveillance Systems", International Journal of Engineering Technology Science and Research (IJETSR), ISSN 2394 – 3386, Volume-4, Issue-11, pp:408-412, November-2017
[4] Fumiya Kudo, Tomoki Akitomi and Norihiko Moriwaki, “An Artificial Intelligence Computer System for Analysis of Social Infrastructure Data”, 2015 IEEE 17th Conference on Business Information, DOI:978-1-4673-7340-1/15, pp: 85-89
[5] Kumari A., Prasad U., Bala P.D. Retail Forecasting using NeuralNetwork and Data Mining Technique: A Review and Reflection /
International Journal of Emerging Trends & Technology in Computer Science (IJETTCS) November – December, 2013. V. 2. I. 6. pp. 266–269.
[6] Manikandan, S & Chinnadurai, M 2019, „Intelligent and Deep Learning Approach OT Measure E-Learning Content in Online Distance Education‟, The Online Journal of Distance Education and e-Learning, vol.7, issue 3, July 2019, ISSN: 2147-6454.
[7] V. Lakshmanan: Data Science on the Google Cloud Platform: Implementing End-to-end Real- time Data Pipelines: from Ingest to Machine Learning
[8] S. Manikandan and K. Manikanda Kumaran, "Identifying Semantic Identifying Semantic Relations Between Disease And Treatment Using Machine Learning Approach", International Journal of Engineering Research & Technology(IJERT), essn:2278-0181,Vol.2,June – 2013 [9] Bastian Schlich : Model checking of software for microcontrollers. ACM Trans. Embedded
Comput. Syst. 9(4), 2010.
[10] R. Konoshita, K. Sakurai, S. Yamane : Model generation by the exhaustive search for embedded assembly programs and application to model checking, IEEE 3th GCCE, pp.699-702, 2014
Author Profile
Dr.D.Maria Manuel Vianny (Devadass Maria Manuel Vianny) has got more than nine years excellence of academic experience in various Engineering institutions and currently working as Assistant Professor in the Department of Computing Science and Engineering, Chitkara Institute of Engineering and Technology,Chitkara University, Punjab, India. He received his Doctorate Degree in Computer Science and Engineering from in St.Peter‟s University Avadi, Chennai, India. He has completed his B.E Computer Science and Engineering, Annamalai University, Chidamabaram, India in 2009 ,M.E. from Annamalai University, Chidamabaram, India in 2011 and M.B.A degree in Human Resource Management from the Annamalai University, Chidambaram ,India in 2011. He has authored over 11+ research papers in various national and international journals and conferences. His publications are indexed in SCI, Scopus, Web of Science and Google scholar. He is member of Professional bodies like Indian Society for Technical Education. His research interests include Data Science,IOT,Big Data analytics, Cloud Computing, Cluster Artificial Intelligence, Machine Learning and Deep Learning.
Dr. S. Manikandan is working as Associate Professor of IT in E.G.S Pillay Engineering College, Nagapattinam. He completed Ph.D in Information and Communication Engineering from Anna University, 2020, M.E-CSE in Annamalai University with First class with Distinction, 2012 and B.Tech - IT in E.G.S Pillay Engineering College with First class with Distinction, 2010. His research work includes Artificial Intelligence, Network Security, Deep learning, Algorithms and Cloud Computing. He is member in IEEE, ISTE, IEI, CSTA
Dr. K.Vaidehi is an Associate Professor in the Department of Computer Science and Engineering, Stanley College of Engineering and Technology for Women, Hyderabad, Telangana, India. She received her M.E. and Ph.D degree in Computer Science & Engineering from Annamalai University. She worked as a project fellow of the University Grants Commission (UGC) major research project. She worked as a research associate in DST PURSE Programme. She is a chartered Engineer and member of IEI and member of IETE. She has organized several Workshops/FDP‟s, International and National Conferences. Her research interests include image processing, medical image analysis, pattern recognition, machine learning, artificial intelligence and computer visio n.
Dr.Syed Khasim, Obtained Ph.D degree in Computer Science & Engineering from Rayalaseema University, Kurnool, Andhra Pradesh, India. At present, working as a Professor in Department of Computer Science & Engineering in Dr.Samuel George Institute of Engineering & Technology, Markapur, Andhra Pradesh, India. Having 16 years of experience in Teaching and Research.
Published Various National and International Journals. His research interests include Software Engineering, algorithm design and analysis, Internet of things, Machine learning & AI.
