Dear Dr. Xiaowei, I see. Interesting work. I will give you my opinion about how to address these comments. 1) The first comment is about how to set the parameters. Generally, how to set the minsup parameter is dataset dependent. This is because the number of rules depends of characteristics of datasets such as the length of sequences, the number of distinct items, how similar the sequen
Forum: The Data Mining / Big Data Forum

Call for Paper The 35th International Conference on Industrial, Engineering & Other Applications of Applied Intelligent Systems IEA/AIE 2022 https://ieaaie2022.wordpress.com/ continues the tradition of emphasizing on applications of applied intelligent systems to solve real-life problems in all areas including engineering, science, industry, automation & robotics, business & finance,
Forum: The Data Mining / Big Data Forum

Hi, There is no C# version of that algorithm yet ( to my knowledge) despite that it is one of the fastest algorithm for sequential pattern mining. But if you are interested to make one you can check the Java source code of CMSPAM in SPMF as inspiration and rewrite it in C#. Best regards
Forum: The Data Mining / Big Data Forum

For FP-stream, I dont know. But there is an implementation of the FP-Tree structure in SPMF as part of the FPGrowth algorithm.
Forum: The Data Mining / Big Data Forum

Good afternoon Dr. Xiaowei, Thanks for your interest in the paper. And happy to receive a messsage from someone else in China! I have been to Zhejiang and it is nice place ;-) This is a good question and I understand that terms can be confusing. I will explain these terms and how I use them to make this clearer. - Memory usage or memory consumption mean the amount of RAM memory that is
Forum: The Data Mining / Big Data Forum

Thanks for reporting the bug. The solution is to deactivate the SKIP strategy in the code of gSpan and TKG. /** skip strategy */ private static final boolean SKIP_STRATEGY = false; We already discussed about that by email. But I post the solution here just in case some other people are looking for it. The bug will be fixed in the next release of SPMF.
Forum: The Data Mining / Big Data Forum

Good morning, Sorry for the delay to answer. I have been a bit busy recently. ­> For the past 2 years, during the implementation of the final project of the master's course, I have been asking you questions and you have answered them very well. Thank you for your guidance. You are welcome ;-) > I want to implement an algorithm that works like a hui-miner, based on list (utility-
Forum: The Data Mining / Big Data Forum

http://www.cacml.net/ 2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML 2022) Website: http://www.cacml.net/ Venue: Hangzhou, China (both online and in-person) Conference Date: March 25-27, 2022 2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML 2022) will be held in Hangzhou, China during March 25-27, 2022. It is sponsored by The
Forum: The Data Mining / Big Data Forum

Good afternoon everyone. Just a short message to wish you a happy new year. And thanks for participating to the forum. If you want to discuss anything feel free to post in the forum. We can discuss data mining or some more general topics related to academia. Best regards, Philippe
Forum: The Data Mining / Big Data Forum

Good afternoon and happy new year. 1) It is good that you have submitted to Applied Intelligence. I am associate EiC in that journal but did not see your paper yet. Perhaps that I will see it later. 2) For research ideas, I understand. Sometimes it is not easy to find some new ideas. I can maybe give you one or two suggestions. But it is better to discuss this by e-mail otherwise, someone e
Forum: The Data Mining / Big Data Forum

Good afternoon, I am sorry for the delay to answer. I have been very busy. I think it is likely because the data is very sparse with so many dimensions. In the visualization, the results may look strange but I think it is because we can only visualize two dimensions at a time. By trying to look more in your data, maybe you can find some other reasons. Best regards, Philippe
Forum: The Data Mining / Big Data Forum

24th International Conference on Big Data Analytics and Knowledge Discovery - DAWAK August 22-24, 2022 WU (Vienna University of Economics and Business), Vienna, Austria, http://www.dexa.org/dawak2022 IMPORTANT DATES -------------------------------------------------------------------------------- Abstract submission deadline: March 7, 2022 Paper submission deadline: March 7, 2022 Ac
Forum: The Data Mining / Big Data Forum

Hi all, Just let you know that the deadline has been updated to 20th December
Forum: The Data Mining / Big Data Forum

Hi all, This is to let you know that a new version of SPMF has been released today (version 2.50) with two new algorithms: http://philippe-fournier-viger.com/spmf/index.php?link=download.php The SFUI_UF algorithm for mining skyline utility itemsets using utility filtering (thanks to Wei Song et al., 2021 for the original code) The HAUIM-GMU algorithm for mining high average utility ite
Forum: The Data Mining / Big Data Forum

DASFAA2022: Call for PhD Consortium Papers and Tutorial Proposals ************************* Ph.D. Consortium proposal submission due: Dec 12, 2021 (extended) Tutorial proposal submission due: Dec 16, 2021 (extended) Paper submission (Closed) Workshop proposal submission (Closed) Industry paper submission due: (Closed0 Demo paper submission due: (Closed) ****************
Forum: The Data Mining / Big Data Forum

Website: https://attend.ieee.org/aset/call-for-papers-2/ Dear all, I am sharing this call for papers for the IEEE IC-ASET 2022 conference, that will be held in Tunisia and published by IEEE. I am in the committee for the AI track. Hope to see some of your submissions. Philippe ================================================= 5th International Conference on Advanced Systems and E
Forum: The Data Mining / Big Data Forum

下午好！ Thanks for using SPMF. This data is suitable for SPMF. However, as you have noticed the data must be transformed to be used by SPMF. To transform the data, there is some tools available in SPMF. However, it is impossible to have a tool for all possible types of data. If the type of data is not supported, you may write a simple program or script to convert the data by yourse
Forum: The Data Mining / Big Data Forum

Good morning, Thanks for using SPMF! I am sorry for the late reply. I have been very busy recently at work. Yes, the size of output file can be very large. It depends on how many patterns exist in your data for the parameters that you have set. And it also depends on how much information is stored for each patterns (e.g. if you store the sequence identifiers in the results, as you have not
Forum: The Data Mining / Big Data Forum

Please accept our apologies if you receive multiple copies of this UbiSec 2021 Final Second Batch Call for Papers (CFPs) with Deadline (Extended to November 15, 2021, Firm Deadline, No further extension will be granted). ============================== UbiSec 2021 ============================== Conferences Pivoting to a Part-Virtual Platform - Now Taking Place Part-Virtually Due to the cur
Forum: The Data Mining / Big Data Forum

We need your papers Please consider submitting :-) About one month left!
Forum: The Data Mining / Big Data Forum

Hi all, I am glad to announce a new Workshop on Pattern Mining and Machine Learning in Big Complex Databases (PMDB 2021) that I co-organize at the DASFAA 2022 virtual conference. This is the website: https://philippe-fournier-viger.com/PMDB_2021/index.html A good thing is that all papers will be published in a Springer LNCS (Lecture Note in Computer Science) volume with other worksho
Forum: The Data Mining / Big Data Forum

Good evening, Thanks for reading the paper. There was indeed an error in the example. Since <(a)> and <(a),(f)> have the same support, the pattern <(a)> cannot be closed! I have fixed the PDF of the paper that is hosted on my website to remove this error. If you spot some other problems, please let me know. Best regards,
Forum: The Data Mining / Big Data Forum

Hi again, I am trying to reproduce the problem, but I do not succeed. With the GUI of SPMF, I run FHN on pumsb_negative.txt and minutil = 9999995 and there is no problem: ============= FHN ALGORITHM v0.96r18 - STATS ============= Total time ~ 3663 ms Memory ~ 837.130859375 MB High-utility itemsets count : 0 Candidate count : 0 ===================================================
Forum: The Data Mining / Big Data Forum

Hi, I think that you have probably used the wrong version of these datasets. On the dataset page of SPMF, there are different versions of these datasets. The version of these datasets for frequent itemset mining should not be used with FHN because it does not contain utility information. It will thus throw some error. Instead you should use the version of these datasets for high utilit
Forum: The Data Mining / Big Data Forum

Good evening, How to calculate the similarity between two rules? I think there are maybe different ways. It may depends on what is your goal A simple way is to calculate the edit distance, that is how many items do you need to add or remove to make the two rules become the same. For example: a b --> c and a b d --> c e would have a distance of 2 because you need to
Forum: The Data Mining / Big Data Forum

Hi, Yes unfortunately, that website went down. But I have a copy of the JAR file of PPSF on my computer. It allows to run the software but it does not contain the code... just the compiled code. If you send me an e-mail at philfv8 AT yahoo DOT com, I can send it to you. However, I do not have the source code, but you could recover it by decompiling the code from the jar file (it is not tha
Forum: The Data Mining / Big Data Forum

The 35th International Conference on Industrial, Engineering & Other Applications of Applied Intelligent Systems (IEA/AIE 2022) continues the tradition of emphasizing on applications of applied intelligent systems to solve real-life problems in all areas including engineering, science, industry, automation & robotics, business & finance, medicine and biomedicine, bioinformatics, cyber
Forum: The Data Mining / Big Data Forum

Hi all, This is to let you know that a new version of SPMF (v. 2.49) has been released. It includes 11 new algorithms. - 9 new algorithms are for classification using association rules, something that was missing in SPMF until now. - 1 algorithm called HUIM-AF uses artificial fish swarm for high utility itemset mining - And the last algorithm is an implementation of KNN for classificati
Forum: The Data Mining / Big Data Forum

The 9th IEEE International Conference on Progress in Informatics and Computing (PIC-2021) will be in Shanghai / online. Website: http://www.picconf.com/#myCarousel As one of the publicity chairs, I would like invite you to submit your papers :-) Dates: Conference Date: December 17-19, 2021 Full Paper Submission : September 30, 2021 Acceptance Notification: November 10, 2021 Registrati
Forum: The Data Mining / Big Data Forum

Dear Carter, I am happy to hear about your tests using the SPMF software. I am sorry to answer almost two weeks later. It is here the vacation time in China and I did not check the forum for a while. It is indeed a good idea to set these maximum constraints to filter longer patterns. While FPGrowth can be used to generate rules, the FHM+ algorithm is only designed to generate itemsets (se
Forum: The Data Mining / Big Data Forum