iTrustBD: Study and Analysis of Bitcoin Networks to Identify the Influence of Trust Behavior Dynamics
cryptocurrency network_analysis epidemic_spread behavior_dynamics trusty
Citation:
M. J. Islam, M. R. Islam, and M. A. Basar. "iTrustBD: Study and Analysis of Bitcoin Networks to Identify the Influence of Trust Behavior Dynamics", SN Computer Science, 2024, Vol: 5, 476, doi: 10.1007/S42979-024-02824-2.
Abstract:
The concept of cryptocurrency is a significant advancement in digital currencies. “Cryptocurrency” refers to a form of electronic or virtual currency that is secured through the application of encryption. It is a common practice to trade cryptocurrencies on decentralized exchanges where neither governments nor financial institutions can exert any form of authority over them. This being the case that cryptocurrencies are not regulated either by the government or financial institutions presents a potential risk for investors. Although a few nations have authorized cryptocurrency, the vast majority of nations, including Bangladesh, have not recognized it due to concerns over the safety of the cryptocurrency system. In this paper, we analyze cryptocurrency networks, “Bitcoin Alpha trust weighted signed network” and “Bitcoin OTC trust weighted signed network”. Following an investigation into the characteristics of the networks, we came to the conclusion that they are robust and reliable, as well as capable of withstanding any kind of attack. Additionally, we forecast the future condition of the trader’s conduct in terms of trustworthiness; as a consequence, we identified more trustworthy behaviors on the behalf of traders. As a result, this work has the potential to make a contribution to the process of legalizing cryptocurrency transactions.
Performance Analysis of Modern Garbage Collectors using Big Data Benchmarks in the JDK 20 Environment
garbage collectors big_data memory_management jdk_20
Citation:
M. J. Islam, A. M. Rahman, and S. Rana. "Performance Analysis of Modern Garbage Collectors using Big Data Benchmarks in the JDK 20 Environment", 2023 5th International Conference on Sustainable Technologies for Industry 5.0 (STI), 2023, doi: 10.1109/STI59863.2023.10464900.
Abstract:
Garbage collection is a fundamental aspect of Java Virtual Machine (JVM) memory management, and choosing the optimal garbage collector is essential for attaining optimal application performance. In this work, we conduct experiments with the big data benchmarks from DaCapo and Renaissance benchmark suites in both fixed and variable heap environments to determine the efficacy of JDK 20's garbage collectors. The ZGC algorithm has the highest throughput and the shortest pause periods, whereas the Serial GC algorithm has the lowest throughput and the longest pause intervals. Additionally, it is discovered that the G1 algorithm manages the previous generation heap and metaspace less efficiently. Our work offers valuable insights into the efficacy of garbage collection algorithms and can aid application developers in selecting the optimal garbage collection algorithm. Our investigation can be expanded by analyzing additional benchmark suites and garbage collection algorithms across a broader range of heap sizes in future work.
Actual rating calculation of the zoom cloud meetings app using user reviews on google play store with sentiment annotation of BERT and hybridization of RNN and LSTM
reviews ratings sentiment zoom_app bert rnn lstm
Citation:
M. J. Islam, R. Datta, and A. Iqbal. "Actual rating calculation of the zoom cloud meetings app using user reviews on google play store with sentiment annotation of BERT and hybridization of RNN and LSTM", Expert Systems with Applications, 2023, Vol: 223, 119919, ISSN 0957-4174, doi: 10.1016/J.ESWA.2023.119919.
Abstract:
The recent outbreaks of the COVID-19 forced people to work from home. All the educational institutes run their academic activities online. The online meeting app the “Zoom Cloud Meeting” provides the most entire supports for this purpose. For providing proper functionalities require in this situation of online supports the developers need the frequent release of new versions of the application. Which makes the chances to have lots of bugs during the release of new versions. To fix those bugs introduce developer needs users’ feedback based on the new release of the application. But most of the time the ratings and reviews are created contraposition between them because of the users’ inadvertent in giving ratings and reviews. And it has been the main problem to fix those bugs using user ratings for software developers. For this reason, we conduct this average rating calculation process based on the sentiment of user reviews to help software developers. We use BERT-based sentiment annotation to create unbiased datasets and hybridize RNN with LSTM to find calculated ratings based on the unbiased reviews dataset. Out of four models trained on four different datasets, we found promising performance in two datasets containing a necessarily large amount of unbiased reviews. The results show that the reviews have more positive sentiments than the actual ratings. Our results found an average of 3.60 stars rating, where the actual average rating found in dataset is 3.08 stars. We use reviews of more than 250 apps from the Google Play app store. The results of our can provide more promising if we can use a large dataset only containing the reviews of the Zoom Cloud Meeting app.
Improving Patient Cohort Identification using Neural Word Embedding with Structured Analysis
patient-cohort word-embedding structured-analysis
Citation:
M. J. Islam, J. Rahman and M. K. Ben Islam, "Improving Patient Cohort Identification using Neural Word Embedding with Structured Analysis," 2019 3rd International Conference on Electrical, Computer & Telecommunication Engineering (ICECTE), 2019, pp. 5-8, doi: 10.1109/ICECTE48615.2019.9303568.
Abstract:
Patient cohort is similar symptoms of group of patients over a time period. It is important to correctly identify patient cohort for observational study or interventional study. To identify patient cohort, we can easily retrieve information from large structured and unstructured data tables, but this information may not fulfill our interest. We need to obtain knowledge from the unstructured medical data for further detailed inspection. In this work, we have improved structured extraction by presenting context on a health record dataset for identifying cohort of diabetic patients. Results shows that traditional structured query-based data extraction methods accurately identified 97.14% positive patients to our question of interest where adding natural language processing supported technique have retrieved 98.37% precisely.
The 12B8T Multilevel Line Coding Scheme in Digital to Digital Data Conversion
12b8t line-coding data-conversion
Citation:
M. J. -U. Rahman and M. J. Islam, "The 12B8T multilevel line coding scheme in digital to digital data conversion," 2017 IEEE Region 10 Humanitarian Technology Conference (R10-HTC), 2017, pp. 864-867, doi: 10.1109/R10-HTC.2017.8289090.
Abstract:
12B8T multilevel line coding scheme has been used as an alternative to traditional line coding schemes e.g. 4B3T, 8B6T schemes in digital to digital data conversion. Unipolar, polar, bipolar, multilevel and multiline schemes are used in line coding. But these approaches have some characteristics e.g. costly, no self-synchronization, DC-components, baseline wandering, high bandwidth etc. These characteristics are mainly known as the limitations of these line coding systems. In this paper, we introduced the 12B8T multilevel line coding scheme which eliminates no self-synchronization, DC-components and the performance of this scheme is better than 4B3T, 8B6T multilevel schemes in terms of speed of transmission, bandwidth, and signal rate.