Proceedings of the 11th INDIACom; INDIACom-2017; IEEE Conference ID: 40353 2017 4 International Conference on “Computing for Sustainable Global Development”, 01 st - 03rd March, 2017 Bharati Vidyapeeth's Institute of Computer Applications and Management (BVICAM), New Delhi (INDIA) th A review of solving real domain problems in Engineering for Computational Intelligence using Soft Computing Nikhat Akhtar Research Scholar-Ph.D. (Computer Science & Engineering) Department of Computer Science & Engineering, Babu Banarasi Das University, Lucknow, India dr.nikhatakhtar@gmail.com Firoj Parwej 1) Research Scholar-Ph.D. (Computer Science & Engineering) Department of Computer Science & Engineering Singhania University, Pacheri Bari, Jhunjhunu, Rajasthan, India dr.firojparwej@gmail.com Abstract-Now a day’s, well known accepted soft computing methods likes as neural sets and fuzzy sets, adaptive evolutionary computing and neuro fuzzy based system, and Intelligence Computing’s etc. for carrying out numerical varying data simulation analysis. These approaches become applied on different engineering problems as independently. In this research paper many introducer and researchers describe the soft computing review technique which using for solving real domains problems and simulate the reappearance of the intelligence, as adaptation and learning for real times engineering problems... The intelligence computing Computational intelligence is a universal approximate, and it has the great function of non-linear mapping and optimization techniques. Also we discuss a brief of intelligent systems in Neural Network. And discuss it features and constituents of real problems. We concentrate on solving real domain problems in Neural Network of Intelligent System as Intelligence computing and soft computing. Keywords: Neural Network, Machine Learning, intelligent systems, computational intelligence. I. INTRODUCTION As review of problem solving proves to better understand for opened problems for engineering, according to abstraction level, activity, planning, design and reporting. We can develop quantitative outcome which conducted a soft design of experiments to retrieve the effects that the process variables have on the response variables. In this paper discuss different computational, designing process modeling effort, also discuss review their implications for the general specific model for different engineering problems [6]. Practicing real domain problems which are hired and retained as rewarded for solving problems. So that specific engineers learn how to solve different problems for workplace. Many Engineer problems are different form the finds of problems which solve in workplace. Complex work place problems are ill-structured due to their process as well as their goals, different solutions technique for non-engineering standards, nonengineering [1]collaborative activity and unanticipated refer to importance of experience of multiple form of representation of problems. Several computational tools for analytic [26] become matured in that facilitated problem solving which was impossible or difficult to solve. In above figure 1 a design process of engineering problems in real domains describe the problems of definitions, gathering information’s, analyze and select the appropriate solution then testing occurs for the implantations. From the different perspective of solving computations of real domain problems, system become characterized by its adaptability, flexibility, Dr Yusuf Perwej Assistant Professor, Deptt of Computer Information System AI BAHA University, AL BAHA Kingdom of Saudi Arabia (KSA) yusufperwej@gmail.com Jai Pratap Dixit 2) Research Scholar-Ph.D. (Computer Science & Engineering) Department of Computer Science & Engineering, Ambalika Institute of Management and Technology, Lucknow jpdixit.iiita@gmail.com reasoning and the ability to manage imprecise and uncertain information’s. Fig .1 Component of Software Design Process II. THE DESIGN LAYOUT STRUCTURE There are basic five-step processes usually used in a problemsolving works for design problems as well. Since design problems are usually defined more vaguely and have a multitude of correct answers, the process may require backtracking and iteration. Fig.2 Real domain engineering problem formulation Solving a design problem is a contingent process and the solution is subject to unforeseen complications and changes as it develops. Until the Wright brothers actually built and tested their early gliders, they did not know the problems and difficulties they would face controlling a powered plane. There are the five steps basically used solving design problems such as: Define the problem, Gather pertinent information, Generate Copy Right © INDIACom-2017; ISSN 0973-7529; ISBN 978-93-80544-24-3 706 Proceedings of the 11th INDIACom; INDIACom-2017; IEEE Conference ID: 40353 2017 4 International Conference on “Computing for Sustainable Global Development”, 01 st - 03rd March, 2017 th Quality: The percentage of the design objectives the client thought the team achieved the closeness of the final outcome to client’s initial expectations [9]. Design’s feasibility in its The first step in the design process is the problem definition. application and fabrication Client’s opinion on implementing This definition usually contains a listing of the product or the design Client’s opinion on students’ knowledge of math, customer requirements and specially information about product science and engineering in developing solutions Overall functions and features among other things. In the next step, satisfaction with the design outcome relevant information for the design of the product and itsA. Basic: Requirements The design meets the technical criteria functional specifications is obtained. Considering cost, safety, and the customer requirements and other criteria for selection, the more promising alternativesB. Feasibility: The design is feasible in its application and are selected for further analysis [27]. fabrication / assembly C. Creativity: The design incorporates original and novel ideas, non-intuitive approaches or innovative solutions. III. DECISIONS FOR THE DESIGN PROCESS multiple solutions, Analyze and select a solution, Test and implement the solution After analyzing the alternative solution that you required to decide that which design solution is best [13]. You will refine and develop the solution in detail during the different stages of the design process of particular problems. In different level to determine the each solution against the design criteria as requirement and also design a alternative solution. Fig.3. Typical Design Process Model These attributes can include factors such as safety, manufacturing considerations, the ease of fabrication and assembly, cost, portability, compliance with government regulations, etc. You then assign to each attribute or criteria a value factor related to the relative importance of that attribute. For example, suppose you decide that safety is twice as important to the success of your design as cost. You would assign a value factor of 20 for safety and a value factor of 10 for cost. You assign value factors on a basis of 0 to 100, representing relative importance of each criterion to the decision. Next you evaluate each design alternative against the stated criteria [24]. Each design-related activity received two codes. The first is level of abstraction where we identify three levels. Concept design (C) addresses a problem or sub-problem with preliminary ideas, strategies, and/or approaches. V. COMPUTATIONAL INTELLIGENCE Natural Computing, Quantum computing, Soft Computing are defines as computational intelligence. The development of digital computers made possible the invention of human engineered systems that show intelligent behavior or features. In other words, AI builds up an intelligent system by studying first the structure of the problem (typically in formal logical terms), then formal reasoning procedures are applied within that structure. Alternatively, non-symbolic and bottom-up approaches (in which the structure is discovered and resulted for man unordered source) to intelligent systems are also known. A. Natural Computing: Natural computing, also called Natural computation, is a terminology introduced to encompass three classes of methods: 1) Those that take inspiration from nature for the development of novel problem-solving techniques; 2) Those that are based on the use of computers to synthesize natural phenomena; and 3) Those that employ natural materials (e.g., molecules) to compute. The main fields of research that compose these three branches are artificial neural networks, evolutionary B. Quantum computing : Quantum computing is the area of study focused on developing computer technology based on the principles of quantum theory, which explains the nature and behavior of energy and matter on the quantum (atomic and subatomic) level. C. Soft Computing: proposed a new approach for Machine Intelligence; separating Hard Computing techniques based Artificial Intelligence from Soft Computing techniques based Computational Intelligence . Hard computing is oriented towards the analysis and design of physical processes and systems, and has the characteristics precision, formality, and category. IV. METRICES FOR CLIENT SPECIFICATION There are the following matrices for client specification Copy Right © INDIACom-2017; ISSN 0973-7529; ISBN 978-93-80544-24-3 707 A review of solving real domain problems in Engineering for Computational Intelligence using Soft Computing possible. Many engineering programs are incorporating design experiences throughout their curricula. Design problems are the most complex and ill-structured of all kinds of problems [9], and there are different kinds of design problems [25]. A. Problem-Based Learning Environments: For engineering faculty who are committed to problem solving but do not have the support to develop PBL programs, they can with minimal support design, develop, and implement problem based learning environments. Fig.4. Computational intelligence vs. Artificial Intelligence VI. KNOWLEDGE AND SKILL FOR SOLVING APPROCHESS There are the following stages by which knowledge and skill become measure for the solving real domain approaches. 1. Instructional time, laboratory activities using safe, ethical practices and conduction of different engineering fields: i. Safe practices demonstrations during laboratory activities and engineering fields ii. Choice make among the legal disposal of material, conversions of resources, recycling of materials etc. 2. Expectations of knowledge, tools and technology: i. discuss concept out line , essential knowledge skills relevant to real engineering design problems ii. Selections of appropriate soft computing model iii. Integration of technique of soft computing to develop solution for real domain engineering problems. iv. Justify appropriate model v. Integrate and apply relevant tools or Martials 3. Expectations representation of graphics, written documents and presentations tools: a. Sketching a communication model. b. Study of specification and procedure iii. Prepare a specific model iv. Analysis of appropriate formats. 4. Expectations of development and practices of engineering professions: i. Build of appropriate team of professional engineers’ ii. Emphasizing guidelines for ethical iii. Interactions among engineers 5. Expectations of design practices and processes and creation of justifiable solutions. 6. Expectations of managing engineering design projects VII. DIFFERENT KIND OF PROBLEMS There are different kinds of problems related with real domain engineering problems. Another implication of this study is to engage engineering students in solving as many different kinds of problems as Fig.5. Problem-Based Learning Environments We are working on design architectures for scaling the development of story problems [26] and troubleshooting problems [22]. We describe an example of a problem-based learning environment to introduce undergraduates to the range of nuclear applications [13]. B. Meaningful Collaboration: In order to address ABET requirements that engineers become able to function on multidisciplinary teams, team work, and collaborative learning have become staples of engineering classrooms [12]. It is also important to avoid bias or marginalization that underrepresented students often experience when participating in team related activities. C. Frame work: As a methodological framework, we employed a modified analytic induction process, a qualitative research methodology that uses a systematic set of procedures to develop an inductively derived grounded theory [10]. In order to systematically identify our assumptions and derive new aspects of problem solving informed by data, we utilized two approaches: (a) The development of a case-based reasoning (CBR) library indexing semi-structured interviews with engineers based on our assumptions and existing problem-solving research followed by (b) A grounded theory approach to elicit new perspectives on workplace problem solving that are informed by the CBR indexes but go beyond them. Copy Right © INDIACom-2017; ISSN 0973-7529; ISBN 978-93-80544-24-3 708 Proceedings of the 11th INDIACom; INDIACom-2017; IEEE Conference ID: 40353 2017 4 International Conference on “Computing for Sustainable Global Development”, 01 st - 03rd March, 2017 th D. Structured Problems: A recurring characteristic of workplace problems is that they are ill-structured. Initially, some problems appeared fairly well structured, however, as constraints and unanticipated problems (described later) became apparent, the problems became more ill-structured. For example, one problem looked very well-structured: measuring the flow of a certain pipe and the temperature coming out of a large container. E. Well-Structured Problems: Within large projects, numerous well-structured problems are solved, such as “what is the load strength for material x” and how big the radius of machinery to clear a path is. Engineering students learn to solve wellstructured problems in university courses; however, they rarely experience well-structured problems in everyday contexts. F. Structured Problems with Have Multiple, Often Conflicting Goals : For example, the primary goal of one project was to “find a solution that will meet the purpose and needs statement that we include in our environmental impact statement that has a level of public and community support along the corridor that is politically acceptable and ultimately that we can afford.” Accommodating the goals and expectations of each of those factors is a complex undertaking. Sub-goals can often conflict with the primary goal, so the engineer must determine which goals have higher priority. G. Structured Problems Are Solved in Many Different Ways: In textbook problems, there is a preferred solution path or method. In many ill-structured problems, the problem solvers never know which solution method is optimal or even how to evaluate the efficacy of different solutions. H. Success Is Rarely Measured by Engineering Standards: Engineering classroom problems often assume that engineering problems are solved using only engineering criteria as the criteria of success. VII NON ENGINEERING’S CONSTRAINTS Engineering education programs treat problems as engineeringonly problems. However, workplace problem constraints, like standards, usually had little to do with engineering. Rather they most often related to time (“We had a very aggressive schedule from start to finish”) and budgets (“Dollars, it is always dollars.”). When the clients are other companies, the constraints are determined by cost, functionality, and the requirements that new solutions have to work together with elements already in place, such as overall corporate brand, jobs, tasks, and tools that are already in place. The list of criteria is developed by the design team. The design team is made up of people from various engineering backgrounds that have expertise pertinent to the problem. For example, if you were designing a critical life support system, you would not include the criterion of "must be minimum cost," because cost is not an important factor in evaluating this design. Fig. 6. Non Engineering design VIII. DISTRIBUTION OF KNOWLEDGE SOLVING AMONG TEAM MEMBER There are the following basic facts related with knowledge solving problems among team members: Traditional conceptions of learning have focused on knowledge that is acquired by individuals. Early theories of cognition focused on information processing and knowledge in the heads of individuals. According to newer perspectives, learning is less a solitary act of individuals but rather is distributed among people, their tools and communication media, history, and the artifacts they create. A. Establish Criteria for Success Criteria for success are the specifications a design solution must meet or the attributes it must possess to be considered successful. You should include criteria in the problem statement to provide direction toward the solution. At this point in the design process, the criteria are preliminary. As the design solution develops, you will most likely find that the initial criteria need to be redefined or modified. Fig.7. Engineering Successful design The following is a list of preliminary criteria for a better mousetrap design. This list would be included in the problem definition statement. • The design must be low cost. • The design should be safe, particularly with small children. • The design should not be detrimental to the environment. • The design should be aesthetically pleasing. • The design should be simple to operate, with minimum human effort. • The design must be disposable (you don't reuse the trap). • The design should not cause undue pain and suffering for the mouse. B. Pertinent Information collection: Copy Right © INDIACom-2017; ISSN 0973-7529; ISBN 978-93-80544-24-3 709 A review of solving real domain problems in Engineering for Computational Intelligence using Soft Computing other; no one person is in possession of all the information needed to make a decision. IX. IMPLICATIONS FOR ENGINEERING EDUCATORS There are the following implications for engineering educators such as: Transfer workplace, Problem Based Learning, Problem Structured. The study of the parameters [12]of workplace real domain problem solving. We can recognize the successful efforts to achieve the specific goals that may have made by expert engineering programs. Fig.8. Pertinent Information Design Which type of information may be collected for the pertinent information such as - Is the real problem and have statement accurate? - Is there really a need for a new solution or has the problem already been solved? And what are the existing solutions to the problem? (Such as many aesthetics, safety and environmental issues etc….)? C. Requirement of extensive collaboration: Very few engineers engage in solitary problem solving. In the overwhelming majority of workplace problems, engineers must collaborate with a variety of personnel in order to identify and solve the problem. Collaborations are most successful when the roles and relationships are well defined, and (like any good system), they share a common goal. D. Experiential knowledge based on primarily engineer rely: Research has confirmed that experience is the most common determinant of expertise, and that the recall of historical information is the most frequent strategy for solving problems [26]. Many For example, found that troubleshooters base their diagnosis on their beliefs about the cause once a discrepant symptom is found. E. Unanticipated problems encountered: Most everyday problems are dynamic; that is, the conditions change over time. Most of the problems the engineers talked about were large scale, in which a set of problems (some of which were unanticipated) occurred. What is interesting is that the unanticipated problems that arose were a combination of engineering and non-engineering problems, as described by an electrical engineer. F. Multiple problems representation: Representing the problem space is an essential part of all problem solving [27]. Experts are able to represent problems in multiple ways, whereas novices are typically restricted to a single form of problem representations [30]. Representing problems to others directs further interpretation of information about the problem, simulates the behavior of the system based on knowledge about the properties of the system, and triggers particular solution schemas [11]. G. Communication skills: In Engineering Curricula: Communication is the “sine qua non” of cognition [23]. Individuals may have mental representations derived from experience or observations, but that knowledge is often useless unless it is shared. Components of distributed systems, such as workplace problem solving teams, must trust and rely on each Workplace Transfer: Assumptions that underlying with goals of engineering programs that become faster to transfer work place in modern engineering contexts. The professional real domain engineering programs that’s clearest goal is learning for future work Learning based problem: Once a solution for preparing engineering graduates to become better problem with workplace solvers is converting their curricula to learning based learning (LBP). Structured problem: Many learning based problems represent the innovations in history of solving real domain problems. X. MULTIPLE SOLUTION GENERETOR We consider a multiple solution generator for begins to the design process with new ideas which solve the specific problems. Rules of the systematic applications to solve particular real domain technical problems. Concentrate and focus on the problem as Selection of appropriate solution and analysis procedure and Analysis of solution designs A. Selection of appropriate solution and analysis procedure: Once you've conceived alternative solutions to your design problem, you need to analyze those solutions and then decide which solution is best suited for implementation. Analysis is the evaluation of the proposed designs. B. Analysis of solution designs: When we start to implement a solution for particular design for specific problems, we start a tentative modal approach with a alternative solution based on selection criteria. Engineers can perform several types of analytic technique which required for the different level of problems. Fig. 9. Solution for process design Prepare a list of requirement that to be considered as functional analysis, liabilities, industry process design, manufacturability and testability with specific parameters. XI. CONCLUSION Computational Intelligence engineering problems and their applications easily solve by soft computing approaches. Their experimental result desire to achieve an appropriate or equivalent outputs with better performance rather than Copy Right © INDIACom-2017; ISSN 0973-7529; ISBN 978-93-80544-24-3 710 Proceedings of the 11th INDIACom; INDIACom-2017; IEEE Conference ID: 40353 2017 4 International Conference on “Computing for Sustainable Global Development”, 01 st - 03rd March, 2017 th traditional methods. Current scenario uses multiple soft algorithms in field of engineering, mainly use of real data due to their nature as incomplete, inconsistent and noisy etc. due to lack of incomplete information ruling the phenomena under consideration. Here we describe the different approaches which identify the workplace attributes with different engineering real problems which make them ill structured, complex and ambiguous. Computational problems of real domain solve by the appropriate constraints, distributed knowledge and also collaborative activities in multiple form of problem solution representation. We discussed much implication for real domain engineering education, including with conceptualizing the concepts of solving real domain different kind of as problem based learning and its environments, engineering real domain problems solved by extending implication for precipitate research among the different field of computational intelligence which validate to the effective approaches, techniques. ACKNOWLEDGMENTS I acknowledge my great gratitude and immense to different researchers for their encouragement, inspiration and insightful research. REFERENCES [1] Kumar K., Sakthibala D. and Palaniswami S., (2010), “Efficiency Optimization of Induction Motor Drive using Soft computational Techniques,” International Journal of Computer Applications, 3(1), pp. 6-12. [2] Marcos Gestal Pose, and Daniel Rivera Cebrián (University of A Coruna, Spain) "Soft Computing Methods for Practical Environment Solutions: Techniques and Studies" Release Date: May, 2010. Copyright © 2010. [3] Balamurugan S., Xavier R. and Jeyakumar A., (2009) , “Control Of Heavy-duty Gas Turbine Plantsfor Parallel Operation Using Soft Computing Techniques”, Electric Power Components and Systems, 37(11), pp.1275 – 1287. [4] Esmaeili V., Assareh A., Shamsollahi M.B. Maoradi M.H. and Arefian N.M. (2008), “Estimating the depth of anesthesia using Fuzzy soft computation applied to EEG features,” Intelligent data Analysis, 12, pp. 393-407. [5] Guangwen Li, QiulingJia, and Jingping Shi, "The Identification Of Unmanned Helicopter based on Improved Evolutionary Strategy", 2009 Second International Conference on Intelligent Computation Technology and Automation. [6] M. Dorigo ET L.M. Gambardella, Ant Colony System: A Cooperative Learning Approach to the Traveling Salesman Problem, IEEE Transactions on Evolutionary Computation, Volume 1, pages 53-66, 1997. [7] X Hu, J Zhang, and Y Li (2008). Orthogonal methods based ant Colony search for solving continuous optimization problems. Journal of Computer Science and Technology, 23(1), pp.2-18. [8] ShahriarJahan Hossain* and Nafis Ahmad, "Adaptive neuroFuzzy inference system (ANFIS) based surface roughness Prediction model for ball end milling operation", Journal of Mechanical Engineering Research Vol. 4(3), pp. 112-129, March 2012ISSN 2141-2383 ©2012 Academic Journals [9] ZENG Hui, LI Yuanxiang, "Optimization of Fuzzy Controller Based on Dynamic Evolutionary Algorithm "2010 International Conference on Intelligent Computing and Cognitive Informatics. [10] J. Rudas, János Fodor, "Intelligent Systems" Int. J. of Computers, Communications & Control, ISSN 1841-9836, EISSN 1841-9844 Vol. III (2008), Suppl. issue: Proceedings of ICCCC 2008, pp. 132-138M. [11] Shelly Xiao Nan Wu* Wolfgang Banzhaf, "The Use of Computational Intelligence in Intrusion Detection Systems: A Review" Department of Computer Science", Memorial University of Newfoundland St. John’s, NL, Canada A1B 3X5November 2008. [12] D. Martens, M. De Backer, R. Hansen, J. Vanthienen, M. Snoeck, B. Baesens, Classification with Ant Colony Optimization, IEEE Transactions on Evolutionary Computation, Volume 11, number 5, pages 651—665, 2007. [13] M.A. Dena, F. Palis and A. Zeghbib, "Modeling and control of Nonlinear systems using soft computing techniques", Applied Soft Computing, 7:728-738, 2007 [14] U.S. Department of Labor, What Work Requires of Schools, Washington, DC: U.S Department of Labor, Secretary’s Commission on Achieving Necessary Skills, (1991). 148 Journal of Engineering Education April 2006 [15] Clough, W., the Engineer of 2020: Visions of Engineering in The New Century, National Academy of Engineering: Washington, DC, 2004. [16] Cho, K.L., and D.H. Jonassen, “The Effects of Argumentation Scaffolds on Argumentation and Problem Solving,” Educational Technology: Research & Development, 50, (3), 2002 pp. 5-22. [17] LaPlaca, M C., W.C. Newsletter, and A.P. Yoga Nathan, “Problem-Based Learning in Biomedical Engineering Curricula,” Proceedings - Frontiers in Education Conference, 2, 2001, F3E/16-F3E/21 (IEEE cat n 01CH37193). [18] Cline, Matthew, J. Powers, and J. Gary, “Problem Based Learning In a Chemical Engineering Undergraduate Laboratory,” IEEE Frontiers in Education, 1997, pp. 350–354. [19] Armargosa, J., “Advanced Software Design: A Case in Problem Based Learning,” IEEE Computer Society, Proceedings of the 15th Annual Conference on Software Engineering Education and Training, (2002). [20] Mitchell G.G., and J.D. Delaney, “An Assessment Strategy To Determine Learning Outcomes in a Software Engineering Problem Based Learning Course,” International Journal of Engineering Education, 20 (3), 2004, pp. 494–502. [21] Van Kampen, P., C. Manahan, M. Kelly, E. Mcloughlin, and E. O’Leary, “Teaching a Single Physics Module Through Problem Based Learning in a Lecture-Based Curriculum,” American Journal of Physics, 72 (6), 2004, pp. 829–834. [22] Denayer, I., K. Thaels, J. Vander Sloten, and R. Gobin, “Teaching A Structured Approach to Design Process for Undergraduate Engineering Students by Problem-Based Education,” European Journal of Engineering Education, 28 (2), 2003, pp. 203–214. [23] Brodeur, D., P.W. Young, and K.B. Blair, “Problem-Based Learning In Aerospace Engineering Education,” Proceedings, American Society for Engineering Education Annual Conference And Exposition, 2002. [24] Zywno, M.S., and D.C.I. Kennedy, “Integrating the Internet, Multimedia Components, And Hands-on Experimentation Into Problem Based Control Education,” Proceedings, Frontiers in Education Conference, 1, 2000, IEEE, Piscataway, New Jersey, 00CB37135. T2D-5-T2D-10. [25] Jonassen, D.H., “Learning To Solve Problems Online,” in C. Vrasidas and G. Glass, eds., Distance Education and Distance Learning (pp. 75–98) Greenwich, Connecticut: Information Age Publishing, 2002. [26] Sobek, II, D.K., (2002) “Preliminary Findings from Coding Student Design Journals,” Proceedings of the 2002 American Society of Engineering Education Conference, Montreal, Canada. Copy Right © INDIACom-2017; ISSN 0973-7529; ISBN 978-93-80544-24-3 711