A cognition graph approach for insights generation from event sequences

Cluster Computing, Volume 20, Issue 2, 2017, Pages 1679-1690.

Cited by: 2|Views70
EI
Weibo:
We propose a systematic approach named Temporal-IdeaGraph to build a directed cognition graph for human insights generation by mining temporal event sequences

Abstract:

In recent years, cognition map techniques for human insights have already played a significant part in complex or ill-structured problem solving. There are increasing interests on computational methods rather than hand-drawing methods to build an cognition graph for insights generation. In this paper, a systematic approach called Temporal...More

Code:

Data:

0
Introduction
  • An event sequence is a set of events happened in a temporal order, such as a user’s clickstream from a portal website and a patient’s illness changes in the electronic medical record (EMR).
  • A lot of researches have been focusing on mining frequent patterns or episodes from event sequences [1,2,3]
  • Such a pattern or episode can be used to generate relevant rules to describe or predict sequential events [3].
  • With the help of Fig. 1, the doctor is able to timely diagnose the illness and make it on the way to Episode 4 when a patient’s illness is changing from Symptom 1 to 2.
Highlights
  • An event sequence is a set of events happened in a temporal order, such as a user’s clickstream from a portal website and a patient’s illness changes in the electronic medical record (EMR)
  • We propose a systematic method called Temporal-IdeaGraph to automatically generate a directed cognition graph based on amounts of event sequences
  • We propose a systematic approach named Temporal-IdeaGraph to build a directed cognition graph for human insights generation by mining temporal event sequences
  • We apply proposed method in two real case studies and validate its effectiveness to trigger valuable human insights
  • The proposed approach will be integrated into our iChance platform [9,23,41,42] to accelerate human cognition for creative design in a computer supported cooperative environment
  • As the big data era is coming [43], our method will be widely used in information flow detection [44], user analysis [45], graph visualization [46], sequence data process [3,47,48,49,50], event detection[51] and intelligent recommendation [52,53,54]
Methods
  • Sequence pattern ε Threshold of the 9 (Dataset 1); 5 mining minimum (Dataset 2).
  • Threshold of the 3 length of extracted sequential patterns.
  • Bridge events and bridge patterns discovering.
  • Nbr gevent Nbr g pat t er n.
  • Threshold of the 10 bridge events.
  • Threshold of the 6 bridge patterns
Conclusion
  • The authors propose a systematic approach named Temporal-IdeaGraph to build a directed cognition graph for human insights generation by mining temporal event sequences.
  • The authors apply proposed method in two real case studies and validate its effectiveness to trigger valuable human insights.
  • The proposed approach will be integrated into the iChance platform [9,23,41,42] to accelerate human cognition for creative design in a computer supported cooperative environment.
  • As the big data era is coming [43], the method will be widely used in information flow detection [44], user analysis [45], graph visualization [46], sequence data process [3,47,48,49,50], event detection[51] and intelligent recommendation [52,53,54]
Summary
  • An event sequence is a set of events happened in a temporal order, such as a user’s clickstream from a portal website and a patient’s illness changes in the electronic medical record (EMR).
  • Keywords Cognition graph · Human insight · Bridge event · Event sequence · Sequential pattern
  • It is natural to raise some problems of how to map a cognition graph for human insights like Fig. 1 by mining large amounts of event sequences?
  • We propose a systematic approach named Temporal-IdeaGraph to build an effective cognition graph for human insights generation in the decision-making process by mining temporal event sequences.
  • We define two new concepts of bridge event and bridge pattern, and propose relevant methods to detect them for further insights generation.
  • We devote ourself to cognition graph construction for insights generation by mining temporal event sequences.
  • We focus on generating a cognition graph by mining event sequences and on this basis, we try to discover rare and important events or event patterns.
  • There are some classical methods to mining frequent sequential patterns from event sequences, such as AprioriAll [25], GSP [26], FreeSpan [27], PrefixSpan [28].
  • Due to the high performance of PrefixSpan algorithm on large-scale sequential pattern mining, we apply it to capture frequent event patterns in this paper.
  • We propose a systematic method called Temporal-IdeaGraph to automatically generate a directed cognition graph based on amounts of event sequences.
  • Given event sequences S and support threshold ε, the problem of sequential pattern mining is to detect the complete set of sequential patterns from S.
  • To deal with large-scale event sequences, the algorithm of PrefixSpan [28] is employed to mine sequential patterns, which may greatly improve the mining efficiency through avoiding time-consuming candidate generation [30].
  • We conduct two case studies and evaluate the effectiveness of proposed TICG with bridge events and bridge patterns on triggering human insights.
  • Figure 6 shows a TICG constructed by clickstream data, where the rectangle nodes colored by red are bridge events and the directed edges with red color are the bridge patterns.
  • Figure 7 shows that a cognition with bridge events and patterns can well trigger human insights generation.
  • The bridge events in Fig. 7 are partly shown in Fig. 8, IdeaGraph fails to consider temporal information of sequence data and capture bridge patterns.
  • We propose a systematic approach named Temporal-IdeaGraph to build a directed cognition graph for human insights generation by mining temporal event sequences.
  • As the big data era is coming [43], our method will be widely used in information flow detection [44], user analysis [45], graph visualization [46], sequence data process [3,47–50], event detection[51] and intelligent recommendation [52–54]
Tables
  • Table1: The statistical information of two datasets Description
  • Table2: Parameters setting of Temporal-IdeaGraph
  • Table3: Bridge events extracted from users’ clickstream
  • Table4: Bridge patterns extracted from users’ clickstream
  • Table5: Bridge events extracted from customer purchasing record e
  • Table6: Bridge patterns detected from customer purchasing record p
  • Table7: Evaluation on the importance of bridge events
Download tables as Excel
Related work
  • 2.1 Human insights for complex or ill-structured problem

    In the past few years, decision support system (DSS) has been well applied in solving well-structured problems [6]. However, researchers have recently realized that computer-centric

    DSS does not play the same role in complex or ill-structured problem solving. Most of these problems, such as innovative product design and strategy formulation, cannot be simply divided into some sub-problems to be dealt with due to their complexity, vagueness and uncertainty. As defined in [7], “ill-structured problems have no initial clear or spelled out goals, set of operations, end states, or constraints”. To solve the uncertainty of ill-structured problems, groups’ information exchange including interrogatives, data, facts, ideas and evaluation is employed for a decision [8], which indicates collective intelligence is highly valuable [9].

    Complex problem solving (CPS) have also received extensive attention from cognitive science in recent years. In fact, the solutions of complex and ill-structured problems need to rely on not only some standard linear procedures supported by a computer, but more importantly humans’ abilities of intuition, perception and cognition. In recent years, creativity support techniques are integrated into DSS to enhance human’s cognition and knowledge creation for complex and ill-structured problem solving. Wijekumar and Jonassen [10] indicated that computer-aided cognition has a good effect on analyzing, judging, and solving ill-structured problems. Lu et al [11] proposed a decision-oriented situation retrieval (SR) model for cognitive decision support in digital business ecosystem. A SR process is to seek knowledge and information relevant to a decision situation, which drives human cognition for decision making. Snchez-Pi et al [12] emphasized the importance of contextual information for knowledge-based system to represent complex problems and developed a context-aware system. Memon et al [6] used a semantic de-biased associations (SDA) model to refine human cognition by reducing cognition biases for ill-structured problems. Gu and Tang [13] introduced a systematic methodology called meta-synthesis approach (MSA) which emphasizes the synthesis of collected information, quantitative models and human knowledge for CPS. Liu and Ke [14] showed a knowledge support approach for CPS through knowledge discovery and case-based reasoning, where knowledge discovery was employed to extract key concepts of situations and actions, and case-based reasoning was adopted to identify similar situations and actions. Goodea and Beckmann [15] investigated the relationships between structural knowledge, control performance and fluid intelligence in a CPS task, and indicated that CPS needs to combine domain knowledge and abstract thinking skills.
Funding
  • This work is supported by Natural Science Foundation of China (Grant Nos. 61672501, 61303164, 61402447 and 61502466)
  • This work is also sponsored by Development Plan of Outstanding Young Talent from Institute of Software, Chinese Academy of Sciences (ISCAS2014-JQ02)
Study subjects and analysis
real case studies: 2
School of Geophysics and Information Technology, China University of Geosciences, Beijing 100083, China. Finally, two real case studies validate the effectiveness of proposed approach. Keywords Cognition graph · Human insight · Bridge event · Event sequence · Sequential pattern

real case studies: 2
Section 3 presents our proposed approach of Temporal-IdeaGraph. We demonstrate the performance in two real case studies in Sect. 4

case studies: 2
4.2 Parameters setting. In this section, we conduct two case studies and evaluate the effectiveness of proposed TICG with bridge events and bridge patterns on triggering human insights. 4.1 Data description

datasets: 2
4.1 Data description. We use two datasets. Dataset 1 is the users’ clickstream data from a Hungarian on-line news portal [39]

is a customers: 2
Clickstream data is a set of event sequences and a event sequence consists of a user’s continuously clicking behavior on the website. Dataset 2 is a customers’ purchasing log from an E-commerce site [40], which records the PC purchasing behavior of different users from July 12th of 2012 to June 5th of 2014. In Dataset 2, an event sequence is a list of PCs purchased by a user and an event denotes a PC with known name and price

datasets: 2
In Dataset 2, an event sequence is a list of PCs purchased by a user and an event denotes a PC with known name and price. Table 1 shows the details of two datasets. The relevant parameters of Temporal-IdeaGraph are listed in Table 2

real case studies: 2
In this paper, we propose a systematic approach named Temporal-IdeaGraph to build a directed cognition graph for human insights generation by mining temporal event sequences. We apply proposed method in two real case studies and validate its effectiveness to trigger valuable human insights. In our future work, the proposed approach will be integrated into our iChance platform [9,23,41,42] to accelerate human cognition for creative design in a computer supported cooperative environment

datasets: 2
. The statistical information of two datasets Description. Parameters setting of Temporal-IdeaGraph

Reference
  • Patnaik, D., Butler, P., Ramakrishnan, N., Parida, L., Keller, B.J., Hanauer, D.A.: Experiences with mining temporal event sequences from electronic medical records: initial successes and some challenges. In: Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 360– 368. ACM (2011)
    Google ScholarLocate open access versionFindings
  • Mannila, H., Toivonen, H., Verkamo, A.I.: Discovery of frequent episodes in event sequences. Data Min. Knowl. Discov. 1(3), 259– 289 (1997)
    Google ScholarLocate open access versionFindings
  • Zhou, W., Liu, H., Cheng, H.: Mining closed episodes from event sequences efficiently. In: Pacific-Asia Conference on Knowledge Discovery and Data Mining, pp. 310–318. Springer, Berlin (2010)
    Google ScholarLocate open access versionFindings
  • Yan, X., Han, J.: Clospan: mining closed sequential patterns in large datasets. In: Proceedings of the Third SIAM International Conference on Data Mining, vol. 112, p. 166. SIAM (2003)
    Google ScholarLocate open access versionFindings
  • Cheng, H., Yan, X., Han, J.: Incspan: incremental mining of sequential patterns in large database. In: Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 527–532. ACM (2004)
    Google ScholarLocate open access versionFindings
  • Memon, T., Lu, J., Hussain, F.K.: Human-centric cognitive decision support system for ill-structured problems. In: Human-Centric Decision-Making Models for Social Sciences, pp. 289–313. Springer, Berlin (2014) 7. Wikiversity. Introduction to ill structured problems. http://en.wikiversity.org/wiki/Introduction_to_IllStructured_Problems (2016)
    Locate open access versionFindings
  • 8. Silver, S.D.: Designing technology for managing the information exchange of decision making teams. Decis. Support Syst. 61, 136– 146 (2014)
    Google ScholarFindings
  • 9. Wang, H., Ohsawa, Y.: Idea discovery: a scenario-based systematic approach for decision making in market innovation. Expert Syst. Appl. 40(2), 429–438 (2013)
    Google ScholarLocate open access versionFindings
  • 10. Wijekumar, K.K., Jonassen, D.H.: The role of computer tools in experts solving ill-structured problems. Comput. Hum. Behav. 23(1), 664–704 (2007)
    Google ScholarLocate open access versionFindings
  • 11. Jie, L., Niu, L., Zhang, G.: A situation retrieval model for cognitive decision support in digital business ecosystems. IEEE Trans. Ind. Electron. 60(3), 1059–1069 (2013) 12. Sánchez-Pi, N., Carbó, J., Molina, J.M.: A knowledge-based system approach for a context-aware system. Knowl. Based Syst. 27, 1–17 (2012)
    Google ScholarLocate open access versionFindings
  • 13. Jifa, G., Tang, X.: Meta-synthesis approach to complex system modeling. Eur. J. Oper. Res. 166(3), 597–614 (2005)
    Google ScholarLocate open access versionFindings
  • 14. Liu, D.-R., Ke, C.-K.: Knowledge support for problem-solving in a production process: a hybrid of knowledge discovery and casebased reasoning. Expert Syst. Appl. 33(1), 147–161 (2007)
    Google ScholarLocate open access versionFindings
  • 15. Goode, N., Beckmann, J.F.: You need to know: there is a causal relationship between structural knowledge and control performance in complex problem solving tasks. Intelligence 38(3), 345–352 (2010)
    Google ScholarLocate open access versionFindings
  • 16. Dumas, A.: Building totems: metaphor making in product development. Des. Manag. J. (Former Ser.) 5(1), 71–82 (1994)
    Google ScholarLocate open access versionFindings
  • 17. Buzan, T., Buzan, B., Harrison, J.: The mind map book: unlock your creativity, boost your memory, change your life. Pearson BBC Active (2010)
    Google ScholarLocate open access versionFindings
  • 18. Hohmann, L.: Innovation Games: Creating Breakthrough Products Through Collaborative Play. Pearson Education, Upper Saddle River (2006)
    Google ScholarFindings
  • 19. Fayyad, U., Piatetsky-Shapiro, G., Smyth, P.: From data mining to knowledge discovery in databases. AI Mag. 17(3), 37 (1996)
    Google ScholarLocate open access versionFindings
  • 20. Louis, A.L., Engelbrecht, A.P.: Unsupervised discovery of relations for analysis of textual data. Digit. Investig. 7(3), 154–171 (2011)
    Google ScholarLocate open access versionFindings
  • 21. Wang, H., Ohsawa, Y., Hu, X., Xu, F.: Idea discovery: a contextawareness dynamic system approach for computational creativity. In: Smart Modeling and Simulation for Complex Systems, pp. 99– 111. Springer, Berlin (2015)
    Google ScholarFindings
  • 22. Wang, H., Zhang, C., Wang, W., Hu, X., Xu, F.: Humancentric computational knowledge environment for complex or ill-structured problem solving. In: 2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 2940–2945. IEEE (2014)
    Google ScholarLocate open access versionFindings
  • 23. Zhang, C., Wang, H., Cao, L., Wang, W., Fanjiang, X.: A hybrid term-term relations analysis approach for topic detection. Knowl. Based Syst. 93, 109–120 (2016)
    Google ScholarLocate open access versionFindings
  • 24. Wang, H., Ohsawa, Y., Lv, P., Hu, X., Xu, F.: Ideagraph: turning data into human insights for collective intelligence. In: Foundations and Applications of Intelligent Systems, pp. 33–44. Springer, Berlin (2014)
    Google ScholarLocate open access versionFindings
  • 25. Agrawal, R., Srikant, R.: Mining sequential patterns. In: Data Engineering, 1995. Proceedings of the Eleventh International Conference on, pp. 3–14. IEEE (1995)
    Google ScholarLocate open access versionFindings
  • 26. Srikant, R., Agrawal, R.: Mining sequential patterns: generalizations and performance improvements. In: International Conference on Extending Database Technology, pp. 1–17. Springer, Berlin (1996)
    Google ScholarLocate open access versionFindings
  • 27. Han, J., Pei, J., Mortazavi-Asl, B., Chen, Q., Dayal, U., Hsu, M.-C.: Freespan: frequent pattern-projected sequential pattern mining. In: Proceedings of the Sixth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 355–359. ACM (2000)
    Google ScholarLocate open access versionFindings
  • 28. Han, J., Pei, J., Mortazavi-Asl, B., Pinto, H., Chen, Q., Dayal, U., Hsu, M.C.: Prefixspan: mining sequential patterns efficiently by prefix-projected pattern growth. In: Proceedings of the 17th International Conference on Data Engineering, pp. 215–224 (2001)
    Google ScholarLocate open access versionFindings
  • 29. Agrawal, R., Srikant, R., et al.: Fast algorithms for mining association rules. In: Proceedings of the 20th International Conference on Very Large Data Vases, VLDB, vol. 1215, pp. 487–499 (1994)
    Google ScholarLocate open access versionFindings
  • 30. Aggarwal, C.C., Han, J.: Frequent Pattern Mining. Springer, Berlin (2014)
    Google ScholarFindings
  • 31. Ohsawa, Y.: Chance discoveries for making decisions in complex real world. New Gener. Comput. 20(2), 143–163 (2002)
    Google ScholarLocate open access versionFindings
  • 32. Bezerra, F., Wainer, J., van der Aalst, W.M.P.: Anomaly detection using process mining. In: Enterprise, Business-Process and Information Systems Modeling, pp. 149–161. Springer, Berlin (2009)
    Google ScholarLocate open access versionFindings
  • 33. Fruchterman, T.M.J., Reingold, E.M.: Graph drawing by forcedirected placement. Software 21(11), 1129–1164 (1991)
    Google ScholarLocate open access versionFindings
  • 34. Ohsawa, Y., Benson, N.E., Yachida, M.: Keygraph: automatic indexing by co-occurrence graph based on building construction metaphor. In: Research and Technology Advances in Digital Libraries, 1998. ADL 98. Proceedings. IEEE International Forum on, pp. 12–18. IEEE (1998)
    Google ScholarLocate open access versionFindings
  • 35. Matsumura, N., Matsuo, Y., Ohsawa, Y., Ishizuka, M.: Discovering emerging topics from www. J. Contingencies Crisis Manag. 10, 73–81 (2002)
    Locate open access versionFindings
  • 36. Chiu, T.-F., Hong, C.-F., Chiu, Y.-T.: Visualization of financial trends using chance discovery methods. In: International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, pp. 708–717. Springer, Berlin (2008)
    Google ScholarLocate open access versionFindings
  • 37. Wang, H., Xu, F., Hu, X., Ohsawa, Y.: Ideagraph: a graph-based algorithm of mining latent information for human cognition. In: 2013 IEEE International Conference on Systems, Man, and Cybernetics, pp. 952–957. IEEE (2013)
    Google ScholarLocate open access versionFindings
  • 38. Zhang, C., Wang, H., Wang, W., Xu, F.: An improved ideagraph algorithm for discovering important rare events. In: 2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 3290–3295. IEEE (2014) 39. wintersong. The click-stream dataset of a hungarian on-line news portal. http://www.datatang.com/datares/go.aspx?dataid=602465 (2011)40. Yiaipai. The comment data of the best-selling 284 laptop in Jingdong.http://www.datatang.com/data/46283 (2014)
    Locate open access versionFindings
  • 41. Wang, H., Ohsawa, Y.: ichance: a web-based innovation support system for business intelligence. Int. J. Organ. Collect. Intell. 2(4), 48–61 (2011)
    Google ScholarLocate open access versionFindings
  • 42. Wang, H., Ohsawa, Y., Nishihara, Y.: Innovation support system for creative product design based on chance discovery. Expert Syst. Appl. 39(5), 4890–4897 (2012)
    Google ScholarLocate open access versionFindings
  • 43. Cui, B., Mei, H., Ooi, B.C.: Big data: the driver for innovation in databases. Natl. Sci. Rev. 1(1), 27–30 (2014)
    Google ScholarLocate open access versionFindings
  • 44. Zhao, M., Wang, H., Cao, L., Zhang, C., Yin, H., Xu, F.: Lsif: a system for large-scale information flow detection based on topic-related semantic similarity measurement. In: 2015 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT), vol. 1, pp. 417–424. IEEE (2015)
    Google ScholarLocate open access versionFindings
  • 45. Lu, S., Zhao, M., Zhang, H., Zhang, C., Wang, W., Wang, H.: Genderpredictor: a method to predict gender of customers from e-commerce website. In: 2015 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT), vol. 3, pp. 13–16. IEEE (2015)
    Google ScholarLocate open access versionFindings
  • 46. Wang, Y., Zhang, C., Wang, W., Xu, F., Wang, H.: Cifdal: a graph layout algorithm to enhance human cognition in idea discovery. In: Systems, Man, and Cybernetics (SMC), 2015 IEEE International Conference on, pp. 1545–1550. IEEE (2015)
    Google ScholarLocate open access versionFindings
  • 47. Wang, F., Lu, S., Zhang, C., Wang, Q., Xu, F.: Timing-ideagraph: a directed cognition graph approach for decision making based on temporal event sequences. In: Computer Supported Cooperative Work in Design (CSCWD), 2016 IEEE 20th International Conference on, pp. 322–326. IEEE (2016)
    Google ScholarLocate open access versionFindings
  • 48. Su, B., Zhou, J., Ding, X., Wang, H., Wu, Y.: Hierarchical dynamic parsing and encoding for action recognition. In: European Conference on Computer Vision, pp. 202–217. Springer, Berlin (2016)
    Google ScholarLocate open access versionFindings
  • 49. Su, B., Ding, X., Liu, C., Wu, Y.: Heteroscedastic max-min distance analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4539–4547 (2015)
    Google ScholarLocate open access versionFindings
  • 50. Su, B., Ding, X.: Linear sequence discriminant analysis: a modelbased dimensionality reduction method for vector sequences. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 889–896 (2013)
    Google ScholarLocate open access versionFindings
  • 51. Zhang, C., Wang, H., Wang, W., Xu, F.: Rcfged: retrospective coarse and fine-grained event detection from online news. In: Systems, Man, and Cybernetics (SMC), 2015 IEEE International Conference on, pp. 139–144. IEEE (2015)
    Google ScholarLocate open access versionFindings
  • 52. Xie, M., Yin, H., Wang, H., Xu, F., Chen, W., Wang, S.: Learning graph-based poi embedding for location-based recommendation. In: Proceedings of the 25th ACM International on Conference on Information and Knowledge Management, pp. 15–24. ACM (2016)
    Google ScholarLocate open access versionFindings
  • 53. Yin, H., Zhou, X., Shao, Y., Wang, H., Sadiq, S.: Joint modeling of user check-in behaviors for point-of-interest recommendation. In: Proceedings of the 24th ACM International on Conference on Information and Knowledge Management, pp. 1631–1640. ACM (2015)
    Google ScholarLocate open access versionFindings
  • 54. Yin, H., Zhou, X., Cui, B., Wang, H., Zheng, K., Nguyen, Q.V.H.: Adapting to user interest drift for poi recommendation. IEEE Trans. Knowl. Data Eng. 28(10), 2566–2581 (2016) Wei Wang received B.E. and Ph.D. from the University of Science and Technology of China in 2009 and 2014, respectively. While working toward the Ph.D. degree, she did research at the National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences, Beijing, China. She is currently an assistant professor at the Institute of Software, Chinese Academy of Sciences. Her research interests include machine learning, data mining and computer vision.
    Google ScholarLocate open access versionFindings
  • Chen Zhang received his Ph.D. degree from China University of Geosciences of Beijing in 2013. He is currently an assistant professor at the Institute of Software, Chinese Academy of Sciences since 2013. Now he is visiting Rutgers University as a visiting scholar (2016–2017). His main research interests are focused on Big Data on Social Media Mining, Big Data on Scientific and Information Visualization techniques.
    Google ScholarFindings
  • Yang Gao is an associate professor in the Institute of Software, Chinese Academy of Sciences (ISCAS). He obtained his Bachelor’s degree from Northwestern Polytechnical University in China, and his Ph.D. degree from Imperial College London in the UK. Before he joined ISCAS in September 2015, he worked in Imperial College London as a Research Associate for one year. His research mainly focuses on machine learning and knowledge representation.
    Google ScholarFindings
  • Yuanman Zheng received his Ph.D. degree from China University of Geosciences of Beijing in 2011. He is assistant professor in China University of Geosciences now. His main research interests are focused on Geophysics and Scientific Visualization, especially on Gravity and Magnetic Inversion Method and System Design.
    Google ScholarFindings
Your rating :
0

 

Tags
Comments