Trends in Computer Science and Information Technology

Journal Information
EISSN : 2641-3086
Published by: Peertechz Publications Inc. (10.17352)
Total articles ≅ 51
Filter:

Latest articles in this journal

Peng Xiuli, Li Quanzhong, Wang Yannian, Yan Dengfeng
Trends in Computer Science and Information Technology, Volume 7, pp 074-080; https://doi.org/10.17352/tcsit.000053

Abstract:
Objective: The performance of blood glucose prediction and hypoglycemia warning based on the LSTM-GRU (Long Short Term Memory - Gated Recurrent Unit) model was evaluated. Methods: The research objects were 100 patients with Diabetes Mellitus (DM) who were chosen from Henan Provincial People’s Hospital. Their continuous blood glucose curves of 72 hours were acquired by a Continuous Glucose Monitoring System (CGMS). The blood glucose levels were predicted based on the LSTM, GRU and LSTM-GRU models, respectively. Analyses of the best predictive model were performed using Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), Mean Absolute Error (MAE) and correlation analysis between the prediction blood glucose level and the original blood glucose level acquired by CGMS and Clark Error Grid Analysis (EGA). Repeated-measures analysis of variance (ANOVA) was used to analyze whether the RMSE values of the three models were statistically significant. 60 patients who had experienced hypoglycemia among 100 cases were selected for hypoglycemia warning. The sensitivity, false-positive rate and false-negative rate were used to evaluate the hypoglycemia warning performance of the LSTM-GRU model. This paper explored the changing relationship of the hypoglycemia warning performance of the model over time. Results: The predicted blood glucose levels of the three models were strongly correlated with the blood glucose levels acquired by CGMS (p < 0.001). The correlation coefficient (R-value) of the LSTM-GRU model remained stable over time (R = 0.995), nevertheless, a reduction in the R-value of the LSTM and GRU models when the Prediction Horizon (PH) was 30 min or longer. When PH was 15min, 30min, 45min and 60min, the mean RMSE values of the LSTM-GRU model were 0.259, 0.272, 0.275 and 0.278 (mmol/l), respectively, which were lower than the LSTM and GRU models and the RMSE values were statistically significant (p < 0.001). The EGA results showed the LSTM-GRU model had the highest proportion in zones A and B, as the PH extended. When PH was 30min or longer, the sensitivity and false-negative rate of the hypoglycemia warning of the LSTM-GRU model had subtle changes and the false-positive rate remained stable over time. Conclusions: The LSTM-GRU model demonstrated good performance in blood glucose prediction and hypoglycemia warning.
, Shukur Zarina
Trends in Computer Science and Information Technology, Volume 7, pp 057-073; https://doi.org/10.17352/tcsit.000052

Abstract:
The Smartphone industry has expanded significantly over the last few years. According to the available data, each year, a marked increase in the number of devices in use is observed. Most consumers opt for Smartphones due to the extensive number of software applications that can be downloaded on their devices, thus increasing their functionality. However, this growing trend of application installation brings an issue of user protection, as most applications seek permissions to access data on a user’s device. The risks this poses to sensitive data are real to both corporate and individual users. While Android has grown in popularity, this trend has not been followed by the efforts to increase the security of its users. This is a well-known set of problems, and prior solutions have approached it from the ground up; that is, they have focused on implementing reasonable security policies within Android’s open-source kernel. While these solutions have achieved the goals of improving Android with such security policies, they are severely hampered by the way in which they have been implemented them. In this work, a framework referred to as CenterYou is proposed to overcome these issues. It applies pseudo data technique and cloud-based decision-making system to scan and protect Smartphone devices from unnecessarily requested permissions by installed applications and identifies potential privacy leakages. The current paper demonstrated all aspects of the CenterYou application technical design. The work presented here provides a significant contribution to the field, as the technique based on pseudo data is used in the actual permissions administration of Android applications. Moreover, this system is user and cloud-driven, rather than being governed by over-privileged applications.
Trends in Computer Science and Information Technology, Volume 7, pp 055-056; https://doi.org/10.17352/tcsit.000051

Abstract:
In this brief overview, we give examples of economic dynamics problems with references to works in which such problems are studied using modern computer technologies, as well as to works that provide a theoretical basis for such studies. Following [1, 657], by reliable computing experiment (RCE) we mean such purposeful computer calculations combined with analytical studies that lead to the strict establishment of new facts (theorems).
, Chen Yuheng, Rana Zeeshan A
Trends in Computer Science and Information Technology, Volume 7, pp 047-054; https://doi.org/10.17352/tcsit.000050

Abstract:
The challenge of improving the accuracy of monocular Simultaneous Localization and Mapping (SLAM) is considered, which widely appears in computer vision, autonomous robotics, and remote sensing. A new framework (ORB-GMS-SLAM (or OG-SLAM)) is proposed, which introduces the region-based motion smoothness into a typical Visual SLAM (V-SLAM) system. The region-based motion smoothness is implemented by integrating the Oriented Fast and Rotated Brief (ORB) features and the Grid-based Motion Statistics (GMS) algorithm into the feature matching process. The OG-SLAM significantly reduces the absolute trajectory error (ATE) on the key-frame trajectory estimation without compromising the real-time performance. This study compares the proposed OG-SLAM to an advanced V-SLAM system (ORB-SLAM2). The results indicate the highest accuracy improvement of almost 75% on a typical RGB-D SLAM benchmark. Compared with other ORB-SLAM2 settings (1800 key points), the OG-SLAM improves the accuracy by around 20% without losing performance in real-time. The OG-SLAM framework has a significant advantage over the ORB-SLAM2 system in that it is more robust for rotation, loop-free, and long ground-truth length scenarios. Furthermore, as far as the authors are aware, this framework is the first attempt to integrate the GMS algorithm into the V-SLAM.
Trends in Computer Science and Information Technology, Volume 7, pp 026-034; https://doi.org/10.17352/tcsit.000048

Abstract:
Recent advances in specialised equipment and computational methods had a significant impact in the Humanities and, particularly, cultural heritage and archaeology research. Nowadays, digital technology applications contribute in a daily basis to the recording, preservation, research and dissemination of cultural heritage. Digitisation is the defining practice that bridges science and technology with the Humanities, either in the tangible or in the intangible forms. The digital replicas support a wide range of studies and the opening of new horizons in the Humanities research. Furthermore, advances in artificial intelligence methods and their successful application in core technical domains opened up new possibilities to support Humanities research in particularly demanding and challenging tasks. This paper focuses on the forthcoming future of intelligent applications in archaeology and cultural heritage, by reviewing recent developments ranging from deep and reinforcement learning approaches to recommendation technologies in the extended reality domain.
Trends in Computer Science and Information Technology, Volume 7, pp 017-025; https://doi.org/10.17352/tcsit.000047

Abstract:
This study aims to examine whether elementary science curricula can be combined with the teaching of entrepreneurship, based on the approach of Lackéus, which is considered an important point of focus for present-day education systems. Entrepreneurship is not commonly handled as an autonomous subject. According to relevant approaches, teaching entrepreneurship relies on certain competencies, knowledge, skills, and attitudes. This research aims to identify whether science curricula include these competencies and can assist in developing entrepreneurial qualities. The data for the research was derived from the science curricula of 16 different countries or regions. Findings showed that there are entrepreneurial competencies in the curricula examined.
Trends in Computer Science and Information Technology, Volume 7, pp 010-016; https://doi.org/10.17352/tcsit.000046

Abstract:
This paper considers that actual methods for addressing MODM or MCDM scenarios share two shortcomings along these lines: a) Failing to show equal results when different MCDM methods solve the same problem. b) Inability to replicate actual scenarios, by not taking into account existing conditions, and thus, producing an approximate representation of reality, which obviously, renders not reliable results. This paper shows how the SIMUS method addresses these two shortcomings.
Singhwani Dhruv
Trends in Computer Science and Information Technology, Volume 7, pp 007-009; https://doi.org/10.17352/tcsit.000045

Abstract:
The term ‘non-fungible’ is used in economics to denote the possession of unique objects and to describe things that cannot be replaced by others because they have a set of unique properties. A ‘token’ as a unit of account is a record in a distributed blockchain that is controlled by a computer algorithm of a smart contract, in which the values of the balances on the accounts of token holders are recorded, making it possible to transfer them from one wallet to another.
Khan Hilmand, Khan Hajra, Shauqat Ayesha, Tahir Sibgha, Hanif Sarmad, Hamza Hafiz
Trends in Computer Science and Information Technology, Volume 7, pp 001-006; https://doi.org/10.17352/tcsit.000044

Abstract:
In blockchain-based mobile crowdsensing, reporting of real-time data is stored on a public blockchain in which the address of every user/node is public. Now, the problem lies in the fact that if their addresses get shown to adversaries, all their transactions history is also going to be revealed. Therefore, crowdsensing demands a little privacy preservation strategy in which the identity of a user is unable to be revealed to an adversary or we can say that crowd sensors while reporting the real-time data must provide some level of anonymity to crowdsensing users/nodes [1]. The current crowdsensing architecture is not secure because of its centralized nature and the reason is a single point of failure also numerous kinds of attacks are possible by adversaries such as linkage attacks, Sybil attacks, and DDOS attacks to get the identity or any other valuable information about the nodes. The location of crowd sensors is also a threat that could lead to adversarial attacks. Consequently, some blockchain-based models must be proposed to attain privacy on the blockchain ledger. The solution can either be made up crowdsensing environment on a private blockchain or smart contracts may be the answer to this problem by which we can make the users secure from several attacks conducted by adversaries on the blockchain.
Trends in Computer Science and Information Technology, Volume 7, pp 035-046; https://doi.org/10.17352/tcsit.000049

Abstract:
This paper explains the process of e-commerce adoption through reasoned action theories (theory of reasoned action (TRA), theory of planned behavior (TPB), and integrated behavioral model (IBM)) in a developing country. Owing to a lack of precedent in the study settings, the study first validated empirical scales for measuring psychosocial drivers of behavior using exploratory and confirmatory factor analyses. Subsequently, the study validated the aforementioned models using structural equation modeling, and also integrated sociodemographic characteristics as precursor variables in the model with the greatest predictive power. Results depicted that while TRA and TPB explain behavior well, it is IBM that is the most effective in explaining online consumer behavior, and underlined the importance of using volitional, sociodemographic, and individual-level factors (knowledge of e-commerce and environmental constraints to use e-commerce) to explain online consumer behavior. The study has numerous implications for e-commerce vendors operating in developing countries as the validated scales and models can be used to assess individual perceptions regarding e-commerce and to design effective communication strategies, respectively.
Back to Top Top