MyMedR

Displaying all 4 publications

Abstract:

Sort:

Fulltext Heuristics to Evaluate Interactive Systems for Children with Autism Spectrum Disorder (ASD)

Khowaja K, Salim SS, Asemi A

PLoS One, 2015;10(7):e0132187.
PMID: 26196385 DOI: 10.1371/journal.pone.0132187

In this paper, we adapted and expanded a set of guidelines, also known as heuristics, to evaluate the usability of software to now be appropriate for software aimed at children with autism spectrum disorder (ASD). We started from the heuristics developed by Nielsen in 1990 and developed a modified set of 15 heuristics. The first 5 heuristics of this set are the same as those of the original Nielsen set, the next 5 heuristics are improved versions of Nielsen's, whereas the last 5 heuristics are new. We present two evaluation studies of our new heuristics. In the first, two groups compared Nielsen's set with the modified set of heuristics, with each group evaluating two interactive systems. The Nielsen's heuristics were assigned to the control group while the experimental group was given the modified set of heuristics, and a statistical analysis was conducted to determine the effectiveness of the modified set, the contribution of 5 new heuristics and the impact of 5 improved heuristics. The results show that the modified set is significantly more effective than the original, and we found a significant difference between the five improved heuristics and their corresponding heuristics in the original set. The five new heuristics are effective in problem identification using the modified set. The second study was conducted using a system which was developed to ascertain if the modified set was effective at identifying usability problems that could be fixed before the release of software. The post-study analysis revealed that the majority of the usability problems identified by the experts were fixed in the updated version of the system.
Fulltext An integrated model for evaluation of big data challenges and analytical methods in recommender systems

Asemi A, Asemi A, Ko A, Alibeigi A

J Big Data, 2022;9(1):13.
PMID: 35127333 DOI: 10.1186/s40537-022-00560-z

The study aimed to present an integrated model for evaluation of big data (BD) challenges and analytical methods in recommender systems (RSs). The proposed model used fuzzy multi-criteria decision making (MCDM) which is a human judgment-based method for weighting of RSs' properties. Human judgment is associated with uncertainty and gray information. We used fuzzy techniques to integrate, summarize, and calculate quality value judgment distances. Then, two fuzzy inference systems (FIS) are implemented for scoring BD challenges and data analytical methods in different RSs. In experimental testing of the proposed model, A correlation coefficient (CC) analysis is conducted to test the relationship between a BD challenge evaluation for a collaborative filtering-based RS and the results of fuzzy inference systems. The result shows the ability of the proposed model to evaluate the BD properties in RSs. Future studies may improve FIS by providing rules for evaluating BD tools.
A speech pronunciation practice system for speech-impaired children: A study to measure its success

Salim SS, Mustafa MB, Asemi A, Ahmad A, Mohamed N, Ghazali KB

Res Dev Disabil, 2016 Sep;56:41-59.
PMID: 27262125 DOI: 10.1016/j.ridd.2016.05.013

BACKGROUND: The speech pronunciation practice (SPP) system enables children with speech impairments to practise and improve their speech pronunciation. However, little is known about the surrogate measures of the SPP system.
AIMS: This research aims to measure the success and effectiveness of the SPP system using three surrogate measures: usage (frequency of use), performance (recognition accuracy) and satisfaction (children's subjective reactions), and how these measures are aligned with the success of the SPP system, as well as to each other.
METHODS AND PROCEDURES: We have measured the absolute change in the word error rate (WER) between the pre- and post-training, using the ANOVA test. Correlation co-efficiency (CC) analysis was conducted to test the relation between the surrogate measures, while a Structural Equation Model (SEM) was used to investigate the causal relations between the measures.
OUTCOMES AND RESULTS: The CC test results indicate a positive correlation between the surrogate measures. The SEM supports all the proposed gtheses. The ANOVA results indicate that SPP is effective in reducing the WER of impaired speech.
CONCLUSIONS AND IMPLICATIONS: The SPP system is an effective assistive tool, especially for high levels of severity. We found that performance is a mediator of the relation between "usage" and "satisfaction".
Fulltext Experimental Analysis in Hadoop MapReduce: A Closer Look at Fault Detection and Recovery Techniques

Saadoon M, Hamid SHA, Sofian H, Altarturi H, Nasuha N, Azizul ZH, et al.

Sensors (Basel), 2021 May 31;21(11).
PMID: 34072632 DOI: 10.3390/s21113799

Hadoop MapReduce reactively detects and recovers faults after they occur based on the static heartbeat detection and the re-execution from scratch techniques. However, these techniques lead to excessive response time penalties and inefficient resource consumption during detection and recovery. Existing fault-tolerance solutions intend to mitigate the limitations without considering critical conditions such as fail-slow faults, the impact of faults at various infrastructure levels and the relationship between the detection and recovery stages. This paper analyses the response time under two main conditions: fail-stop and fail-slow, when they manifest with node, service, and the task at runtime. In addition, we focus on the relationship between the time for detecting and recovering faults. The experimental analysis is conducted on a real Hadoop cluster comprising MapReduce, YARN and HDFS frameworks. Our analysis shows that the recovery of a single fault leads to an average of 67.6% response time penalty. Even though the detection and recovery times are well-turned, data locality and resource availability must also be considered to obtain the optimum tolerance time and the lowest penalties.