Jan'2020
Focus
AI users and practitioners state that AI has a bright future in academia and applications such as expert systems, natural language processing, robotic control, pattern recognition, machine learning, etc. HCI is acquiring all attributes of a scientific specialty in the area of computer science. The diversity of the required skill base for AI and HCI makes it difficult for a single research organization to sustain the minimum skill requirements. Although AI and HCI explore computing intelligent behavior, the fields have seen some crossover. A consequence was competition for resources, with HCI flourishing in AI winters and moving more slowly when AI was in favor. The situation today is much more promising, in part because of platform convergence: AI can be exploited on widely used systems.
This issue consists of four papers. The first paper, "A Contemporary View of Human
System Integration in System Development Process", by Adejoro Cornelius
Onimisi and Ogwueleka Fransica Nonyelum, states that in response to the challenges related to the increasing size and complexity of systems, organizations have recognized the need for integrating human considerations in the beginning stages of systems development. The authors have presented different views on how far Human Systems Integration (HSI) has been able to accomplish the objective of incorporating human factors within systems development process and engineering process. The paper examines various modern necessities as it concerns Human System Integration (HSI) in developing system as offered through scholarly research and firsthand reports of system implementations within Military Institution and Rail Company, and discovers that many answers lie outside the bounds of technology.
The second paper, "Feature Extraction and Dimensionality Reduction Techniques with Their Advantages and Disadvantages for EEG-Based BCI System: A Review", by Abhilasha Nakra and Manoj Duhan, states that BCI is a technique used to build up the interface between the human brain and computer so that the system can read the signal produced in the brain and interpret it with the best accuracy. It translates the EEG signal produced by the brain and the features of the signals are extracted which will be used for classification. Feature extraction is the most significant and one of the initial stages of the BCI system. One of the crucial fundamental issues is feature extraction and dimensionality reduction techniques with their advantages and disadvantages. Moreover, a comparison of various techniques is also done to know about the overall aspects of the techniques so that the use of appropriate technique leads to the precision of the classification stage.
The third paper, "Extracting High Utility Itemset with Positive and Negative Utilities Using High-Utility Itemset Mining Algorithm" by N Umadevi and N Uthra, describes that the way of data increases as the usage of computer increases, and then the manipulation of data is a must to mine the information perfectly. In the jargon of big data, bulk information plays an important role where a large amount of information creates an issue while extracting the data. To overcome this issue, many algorithms and techniques have been introduced; one such technique is the High Utility Itemset Mining (HUIM). The HUIM is used to mine the customer interoperating databases like departmental store data and stock market data. In the existing research, there are only predictions on positive utility or negative utility. The idea is to combine both the positive and negative utilities and process by developing an algorithm called HUPNU. This algorithm infers by deploying opinion mining to recognize the reviews of the users or customers. By considering those reviews and frequencies of the items bought, high positive utility and high negative utility are calculated.
The last paper, "Predictive Modeling for Student Performance Analytics Through Data Mining Techniques", by Gadisa Nemomsa, Durga Prasad Sharma and Addisu Mulugeta, describes the performance of the students through experimental analysis and predictive modeling. There is a lack of predictive studies and models used in the Ethiopian context to accurately determine the influencing factors of the students' performance in academics by categorizing student status into drop out/fail, poor, good, excellent or average performer. Many educational institutions have not enough strategic plans to predict or determine the student performance in order to improve it, reduce dropout and help to implement the curriculum/academic policies based on student performance and status. The authors have aimed at conducting a comparative analysis and predictive modeling for knowing the student performance status through data mining techniques so as to improve their performance and status. The study used the KDD process model to find and interpret patterns in repositories. Decision tree (J48 and Random Forest), Bayes (Naive Bayes and Bayes Net) and Rule-Based (JRip and PART) algorithms are used for classification. The results revealed that the overall accuracy of the tested classifiers is above 80%. In addition, classification accuracy for the different classes revealed that the predictions are worst for fail class and fairly good for the average class. The J48 and JRip classifiers relatively produced the highest classification accuracy for the average performer/status. Finally, the study suggests that data mining can be used as a significant technique to figure out student performance based on salient affecting factors.
Article | Price (₹) | ||
A Contemporary View of Human System Integration in System Development Process |
100
|
||
Feature Extraction and Dimensionality Reduction Techniques with Their Advantages and Disadvantages for EEG-Based BCI System: A Review |
100
|
||
Extracting High Utility Itemset with Positive and Negative Utilities Using High Utility Itemset Mining Algorithm |
100
|
||
Predictive Modeling for Student Performance Analytics Through Data Mining Techniques |
100
|
A Contemporary View of Human System Integration in System Development Process
System implementation efforts offer extraordinary challenges to information technology professionals and the organizations impacted by the implementations. A successful implementation can reap vast rewards in organizational strengths and efficiencies. In response to the challenges related to the increasing size and complexity of systems, organizations have recognized the need to integrate human considerations in the beginning stages of systems development. The paper looks into the different views of how far Human Systems Integration (HSI) has been able to accomplish the objective of incorporating human factors within system development process and System Engineering (SE) process. It examines various modern necessities as it concerns HSI in developing system as offered through scholarly research and firsthand reports of system implementations within Military Institution and Rail Company, and discovers that many answers lie outside the bounds of technology.
Feature Extraction and Dimensionality Reduction Techniques with Their Advantages and Disadvantages for EEG-Based BCI System: A Review
Brain Computer Interface (BCI) is a technique used to build the interface between human brain and computer so that the system can read the signal produced in the brain and interpret it with the best accuracy. It translates the Electroencephalo Graph (EEG) signal produced by the brain and the features of the signals are extracted which are used for classification. Feature extraction is the most significant and one of the initial stages of the BCI system. This stage is the base of the classification. The paper presents an overall analysis of recent methodology of feature extraction methods. It also highlights the advantages and disadvantages of methods by reviewing the literature, books and other related documents. This review helps in choosing a suitable and efficient method of feature extraction which leads to the proper and error-free classification of the signals. Moreover, comparison among various techniques is also done to know about the overall aspects of the techniques so that appropriate use of the technique leads to classification stage precision.
Extracting High Utility Itemset with Positive and Negative Utilities Using High Utility Itemset Mining Algorithm
Data increases as the usage of computer increases, then the manipulation of data is must to mine the information perfectly. In the jargon of big data, bulk information plays an inevitable role, where a large amount of information creates an issue while extracting the data. To overcome this issue, many algorithms and techniques have been introduced. One such technique is the High Utility Itemset Mining (HUIM) which is an extension of Frequent Pattern Mining (FPM). HUIM was used to mine the customer interoperating databases like departmental store data, stock market data, etc. In the existing research, there were only predictions on positive utility or negative utility. So, the paper proposes both positive and negative utilities, combined and processed by developing an algorithm called High Utility itemset mining with Positive and Negative Utilities (HUPNU). This algorithm infers by deploying opinion mining to recognize the reviews of the users or customers. By considering the reviews and frequencies of the items bought, the high positive and negative utilities are calculated.
Predictive Modeling for Student Performance Analytics Through Data Mining Techniques
The paper attempts to predict the performance of the students, through experimental analysis and predictive modeling. There is a lack of predictive studies and models used in the Ethiopian context to accurately determine the influencing factors of the students' performance in academics by categorizing student status into dropout/fail, poor, good, excellent or average performer. Many educational institutions have still no strategic plan to predict or determine the student's performance in order to improve it, reduce dropouts and help to implement the curriculum/academic policies based on student's performance and status. The study aims at conducting a comparative analysis and predictive modeling for knowing the student's performance status through data mining techniques. The study uses the KDD process model and interpret patterns in repositories. Decision tree (J48 and Random Forest), Bayes (NaiveBayes and BayesNet) and Rule-Based (JRip and PART) algorithms are used for classification. The results reveal that the overall accuracy of the tested classifiers is above 80%. In addition, classification accuracy for the different classes reveals that the predictions are worst for fail class and fairly good for the average class. The J48 and JRip classifiers relatively produce the highest classification accuracy for the average performer/ status. Finally, the study suggests that data mining can be used as a significant technique to figure out student's performance based on salient factors affecting.