International Journal of Education and Management Engineering @ijeme
Статьи журнала - International Journal of Education and Management Engineering
Все статьи: 625
Analyzing the Performance of the Machine Learning Algorithms for Stroke Detection
Статья научная
A brain stroke is a condition with an insufficient blood supply to the brain, which causes cell death. Due to the lack of blood supply, the brain cells die, and disabilities occurs in different parts of the brain. Strokes have become one of the major causes of death and disability in recent years. Investigating the affected individuals has shown several risk factors that are considered to be causes of stroke. Considering such risk factors, many research works have been performed to classify and predict stroke. In this research, we have applied five machine learning algorithms to identify and classify the stroke from the individual’s medical history and physical activities. Different physiological factors have are considered and applied to machine learning algorithms such as Naïve Bayes, AdaBoost, Decision Table, k-NN, and Random Forest. The algorithm Decision Table performed the best to predict the stroke based on different physiological factors in the applied dataset with an accuracy of 82.1%. The machine learning algorithms can be a helpful for clinical prediction of stroke against individual’s medical history and physical activities in a better way.
Бесплатно
Статья научная
With the expansion of worldwide security concerns and a consistently expanding requirement for successful checking of open places, i.e. air terminals, railroad stations, shopping centres, crowded sports fields, army bases or smart healthcare facilities such as daily activity monitoring and fall detection in old people’s homes is increasing very rapidly. The visual occlusions and ambiguities in crowded scenes, usage of suitable method and in addition the perplexing practices and scene semantics make the investigation a challenging task. This research demonstrates comprehensive and critical analysis of crowd scene involves in object detection, tracking, feature extraction and learning from visual surveillance which helps to recognize behavioural pattern. This research refers scene understanding as scene layout, i.e. finding streets, structures, side-walks, vehicles turning, person on foot intersection and scene status such as crowd congestion, split, merge etc. The significance of the proposed comprehensive review to create crowd administration procedures and help the development of the group or people, to maintain a strategic distance from the group calamities and guarantee general society security. Based on the observation of previous research in three aspects, i.e. review based on methods, frameworks and critical existing results analysis, this research propose a framework for anomaly detection in crowded scene using LSTM (long Short-Term Method). Proposed comprehensive review is expected to contribute significantly for the investigation of behavior pattern analysis in computer vision research domains.
Бесплатно
Статья научная
Smaller time loss and smoother information communication mode is the urgent pursuit of the software R&D enterprise. Information communication is difficult to control and manage and it needs more technical to support. Data mining is an intelligent way tried to analyze knowledge and laws which hidden in massive amounts of data. Data mining technology together with share repositories can improve the intelligent degree of information communication mode. In this paper, the framework of intelligent information communication mode which based on data mining technology and share repositories is advanced, and data mining model for information communication of software development is designed. In view of the extant single decision tree algorithm existence the characteristics that counting inefficient and its learning based on supervise, a new semi-supervised learning algorithm three decision trees voting classification algorithm based on tri-training (TTVA) is proposed. This algorithm in training only requests a few labeled data, and can use massively unlabeled data repeatedly revision to the classifier. It has overcome the single decision tree algorithm shortcoming. Experiments on the real communicated data sets of software developmental item indicate that TTVA has the good identification and accuracy to the crux issues mining, and can apply to the decision analysis of the development and management of the software project. At the same time, TTVA can effectively exploit the massively unlabeled data to enhance the learning performance.
Бесплатно
Application and security issues of internet of things in Oil-Gas industry
Статья научная
Article proposes an architecture based on new Internet of Things (IoT) for easy, safe, reliable and rapid data collection from sensors installed in oil and gas industry. Use of several Wireless Sensor Networks in management of oil and gas platforms is researched. New opportunities created by processing of data collected via sensors for improvement of safety of oil platforms (deposits), optimization of operations, prevention of problems, troubleshooting and reduction of exploitation costs in oil and gas industry. At the same time, the article analyses safety issues of different layers of monitoring system with IoT architecture.
Бесплатно
Application of CDIO Model for "Microcomputer Principle" at Technology University
Статья научная
CDIO Model, the trend of education at present, was introduced to the course of "Microcomputer Principle". CDIO teaching is the teaching activities of teachers and students together to complete several entire projects. The CDIO education model embodies the teaching philosophy that teachers are guiders, students are subject, the combination of works and studies and "Learning by Doing". It improves teaching effectiveness and teaching quality.
Бесплатно
Application of DFS in the Study of Edge-connected Graph
Статья научная
In this paper a simple method is proposed to determine whether a graph is edge-connected. This method may calculate the minimum pre-order number of each vertex by back edge for the depth-first search spanning tree, and then find out the bridges in the graph. Finally, it may determine whether the graph is edge-connected. The best nature of method is to understand and hold the algorithm easily. It can help teaching improvement and practice application. It is also worth popularization.
Бесплатно
Статья научная
This study aims to identify digital audio forensics using the System Development Life Cycle (SLDC) method which is used as a reference in the audio forensic investigation process. The process of testing the application of the framework that was carried out succeeded in identifying audio evidence with the identification results that subject x sampling (known) was identical to recorded evidence (unknown) with the results obtained for more than 4 identical words and supporting the prosecution hypothesis. Also, the results of the feasibility test of a framework that has been developed as a reference standard for comparison of frameworks related to other audio forensics, show that the framework that has been developed has a more complete stage to be used in the audio forensic investigation process. The results of Spectrogram analysis and Pict analysis on values matrix cross similarity level of evidence with audio subject Nasri4Y has the highest similarity value 0.9575822. The results of reading the audio evidence matrix with audio subject Bakrim5Y have the lowest similarity value 0.48924464. The results of reading the matrix, audio subject- B with audio subject Bakrim3Y have the highest similarity value of 0.9287775 because it is a sample voice from the same person. The results of the reading of the matrix, Nasri2Y audio subject, and Nasri4Y audio subject have a similarity value of 0.9575822 because they are sound samples from the same person. The results of reading the matrix audio subject Nasri2Y with audio subject Nasri4Y have the highest similarity value of 0.9575822, from this result it can be said a significant value because the audio subject Nasri2Y and Nasri4Y have the most similar level of sound samples from other subjects because Nasri2Y and Nasri4Y are sound samples from the same person.
Бесплатно
Application of Greedy Algorithm on Traffic Violation Enforcement
Статья научная
The background of this research is how the application of the algorithm in traffic control systems, with the Greedy algorithm, the system will decide what action and what punishment will be given to traffic offenders on the highway, with the Greedy algorithm, the decisions taken will be based on data and facts. based on existing laws, so decisions made based on law and the human side cannot influence the decisions to be taken by the system based on the application of the Greedy algorithm. The research method used in this study uses literature reviews by reading many previous research journals, it will be able to add knowledge and deepen the research we are doing this time, with the literature review method, we will be able to find new problems and can be used as new research because The literature review is very helpful for our research this time. The system that is being used is using CCTV and can determine what decisions and punishments will be given to traffic offenders, through evidence based on images taken by cameras placed at red lights or corners of the capital's highway, the system this has been active effectively but with the implementation of the algorithm will increase. This research will produce a system proposal and be able to find out whether the application of the Greedy algorithm is correct and can help the current system by implementing the algorithm, so the existing system is more perfect. The main contribution of this research is that the use of the Greedy algorithm can help control the traffic system to enforce the law.
Бесплатно
Application of Machine Learning and Predictive Models in Healthcare – A Review
Статья научная
The use of predictive analytics or models in healthcare has the potential to revolutionize patient care by identifying high-risk patients and intervening with targeted preventative measures to improve health outcomes. This makes the application of analytics in healthcare a concept of utmost interest, which has been explored in various fashions by several scholars. From predicting patients’ ailments to prescribing appropriate drugs, predictive models have seen massive interest. This work studied published works on predictive models in healthcare and observed that the implementation of predictive models in healthcare is experiencing a notable upswing, with a particular focus on research in the United States, where a majority of the top publications originated. Surprisingly, all of the leading nations in this sector have affiliations spanning many continents, with the exception of Africa and South America, together producing a substantially larger volume of research than other countries. The United States also shone out, accounting for 60% of the top five researchers. Notably, although it was published in 2017 (relatively later), Jiang et al. had the most citations (1,346). These studies' core themes were clinical standards, machine learning terminology, and model accuracy. The Journal of Biomedical Informatics topped among journals, with 54 articles, while Luo Gang emerged as the top-performing author, with 12 publications.
Бесплатно
Application of Network and Multimedia Technology in University Physical Experiment Teaching
Статья научная
University physical experiment is a compulsory basic course for the science and engineering students in the university. To activate students’ enthusiasm in learning and make students master the basic methods and skills of physical experiment, the physical experiment teaching should comply with era development and establish a kind of innovative teaching system to cultivate creative students. This paper discusses the necessity and advantages of the teaching method by applying network and multimedia technology for the teaching of university physical experiment. This method would make full use of network and multimedia technology to activate the students’ initiative and creativity in learning, enhance the students’ efficiency in learning and boost the quality in physical experiment teaching.
Бесплатно
Статья научная
This research aims to obtain the best accuracy in classifying stunting children's data using K-Nearst Neighbor (KNN) by combining Particle Swarm Optimization (PSO). The K-NN algorithm is an algorithm which is an unsupervised algorithm, and is proven to be good in data mining while Particle Swarm Optimization (PSO) show. Better optimization performance compared to other methods. The methodology in this research is data collection, data pre-processing, classification of stunted children, data sharing, searching for the optimal k value to the classification process and performance testing or Particle Swarm Optimization. This dataset has an abnormal data structure where certain attribute values have quite wide ranges.The results of the K-NN classification, the average accuracy of each fold, shows that the highest accuracy was obtained at a value of k = 10, namely 86.08% and the lowest was in the last experiment with a value of k = 7500 of 72.67%. It can be concluded that the higher the k value, the resulting accuracy will increase. Meanwhile, the results of K-NN classification with PSO can be concluded that the higher the w value, the greater the possibility of getting better fitness. This result is also in accordance with research where the best w value is above 0.5 and less than 1. This is because if the w value is more than 1 it can cause the particles in the PSO to become unstable because the resulting speed is not controlled. It is proven from the test results that the range This value produces better average accuracy and starts to decrease again when entering the value w = 1. Then the test results also show that a small value of w can result in the role of particle speed becoming insignificant and can increase the possibility of early convergence. It can be seen from the results of testing the number of PSO popsizes that the highest average accuracy was 93.2% at a value of w = 0.9. From the description above, KNN shows an accuracy of 86.08%, while KNN with PSO increases to 93.9%, so this shows that KNN with PSO is more accurate in classifying stunted children.
Бесплатно
Application of Task-Based Approach in College English Teaching Based on Internet-assisted Multimedia
Статья научная
College English teaching in China is an essential part of the whole education system, but there have been some problems that students have been undergoing with low efficiency and instrumental motivation, and that their language input is confined in what teachers taught. In order to solve the problems, this article designs a test and collects data to check the effectiveness of the task-based approach within the Internet-assisted multimedia in college English teaching. The results show that Linguistic form was analyzed and practiced with task-based approach which may help the learners notice the linguistic problems and try out new language forms and structures, and that Internet-assisted multimedia has been effective in intriguing learners' interests and greatly enhanced their self-esteem.
Бесплатно
Application of memory effect in an inventory model with price dependent demand rate during shortage
Статья научная
The purpose of this paper is to establish the memory effect in an inventory model. In this model, price dependent demand is considered during the shortage period. Primal geometric programming is introduced to solve the minimized total average cost and optimal ordering interval. And finally we have taken a numerical example to justify the memory effect of this type inventory system. From the result it is clear that the model is suitable for short memory affected business i.e. newly started business.
Бесплатно
Статья научная
The cancer cell prolonged and continues proliferation is a major cause of tumorigenesis. In general, Insulin like growth factor receptor (IGF-1R) and Insulin receptor (IR-A) protein are responsible for such cell proliferations. However, with respect to cancers, the specific over-expression of these receptors along with the elevated levels of their agonist, i.e. insulin-like growth factor 1 (IGF-1) and insulin-like growth factor 2 (IGF-2) have shown to be the integral part of cancer cell’s proliferation. The understanding of the dual targeting of (IR) and (IGF-1R) through Artificial Intelligence in tumorigenesis is now considered to be a possible aspect to achieve the desired results. In this research we signify that according to data based on artificial intelligence, the tyrosine kinase domain of these two receptors can accommodates number of small molecules inhibitors to block the ongoing signaling cascade for cell proliferation. It is indeed found to be of paramount importance to develop such candidates as clinical solutions to block the activity of tyrosine kinase domain of IR and IGF-1R. Therefore, this study aims to use artificial intelligence for understanding the key molecular interactions responsible for activation and inhibition of the proliferation signal via tyrosine kinase domain. Further, we optimized docking protocol on crystal structures of such system from protein databank. Our study revealed that H-bond donor and hydrophobic pocket play a key role in the initiation of the signal cascade for cell proliferation. The simulations ran produced an acceptable solution based on the statistical measures of Mathew’s correlation factor and delineated two H- bonds distances between 12-22. Our study also concluded that how a docking protocol can be optimized to accommodate the non-congeneric series small molecules. We successfully ran the simulation to conclude that LYS 1030, GLU 1077, MET 1079 and ASP 1083 amino acids positions play an important role in binding of small molecules to inhibit cancer cell proliferation. This research bridges the gap between in-silico and in-vitro experimentations and paves a way to reproduce the results experimentally.
Бесплатно
Applied the experimental teaching model of three phases into the environmental monitoring experiment
Статья научная
The course of the environmental monitoring experiment is one of the important course in environmental science specialty. And it is also a compositive and practical required course. At present, there are some questions in the practical teaching of this course. Based on these questions, the experimental teaching model of three phases are put forward. That is, the course of the environmental monitoring experiment is divided into three training phases and carried out the teaching models of three phases. It was proved that this teaching model would be fit to develop the teaching quality, strengthenthe operational ability, shorten the adaptive time at working.
Бесплатно
Apply Student-Centered Learning on Computer Education
Статья научная
It has been long noticed that students are lacking the motivation for those type of teacher-centered learning environment. Student-Centered Learning (SCL) is used in the literature to indicate the shift of emphasis from the teacher to the student as the heart of the learning process. In this work we have discussed the methodology of SCL, presented our experience of applying SCL on computer education. Students play the active role in this process and take responsible for their own learning. Tutors are required to use new method to deliver knowledge, being a guider more than an expert.
Бесплатно
Статья научная
With the popularity of network, web is becoming one of the most effective ways in information sharing. However, with the increase of clicking index, a high-function server can hardly meet the increasing demand for service. This thesis provides the schedule strategy in the asynchronous mechanism of multiqueue double servers polling, which is conducted based on theory of polling multi-access and simulation experiments on computer, along with consideration to the load features of Web. It concludes that this strategy enables Web server to take on the features of good extendibility, utility and function.
Бесплатно
Apriori Algorithm using Hashing for Frequent Itemsets Mining
Статья научная
Data Warehousing, data mining and analysis plays a very important role in decision support. Various commercial organisations are using tools based on these techniques to be used for decision support system. Apriori algorithm is a classic algorithm which works on a set of data in the database and provides us with the set of most frequent itemsets. It is used to find the association rules and mines the most frequent itemsets in a set of transactions. Here the frequent subsets are extended one item at a time. In this paper a hash-based technique with Apriori algorithm has been designed to work on data analysis. Hashing helps in improving the spatial requirements as well as makes the process faster. The main purpose behind the work is to help in decision making. The user will select an item which he/she wishes to purchase, and his/her item selection is analysed to give him/her an option of two and three item sets. He/she can consider choosing a combination of two item sets or three item sets, or he/she can choose to go with his/her own purchase. Either ways, the algorithm helps him in making a decision.
Бесплатно
Architecture Design Selection Scheme for Usability Quality Attribute
Статья научная
Usability quality attribute is one of the important quality attributes because it is a basic need for end-user stakeholder. Usability provides the ease of use and learnability to end user. Usability is very useful quality attribute of software architecture and architect should remember about usability aspect. Usability aspect means such type of software architecture which provides the learnability, memorability and performance. In this paper we discuss software architecture design based on usability aspect. Usability is necessary for end-users and business stakeholders. We measure and evaluate the usability through one of the mathematical equations. For the selection of usability aspect, or to evaluate the highest usability score in different architecture designs, we have taken the questionnaire from technical persons on the basis of nonfunctional requirements or sub-characteristics of usability quality attributes such as learnability, memorability and performance. Then finally we calculate the usability score.
Бесплатно
Статья научная
The increase in value of security and privacy is compounded by the rapid advancements in the digital landscape sprouting new problems in information security. This research explores the use of artificial intelligence (AI) to enhance cybersecurity and to strengthen data protection. This research aims to first assess and critically evaluate the potential of applying AI methods to improve predicting, mitigating, and resolving cyber threats while addressing important ethical issues. Specifically, it wants to determine AI’s advantages compared to traditional cybersecurity ways and the plausible technological risks and ethical implications associated with its use. We show that AI tools, especially machine learning and deep learning, can greatly aid the threat detection and response automation. The rise of AI, however, brings forth new vulnerabilities and necessitates stronger ethical frameworks to preclude their misuse. This study offers a balanced view of potential with AI and hazards. The results emphasize the importance of AI in securing both the cybersecurity and data protection portfolio, and urge strongly for ethical standards to be met and the research to be continued in order to mitigate risks and promote responsible AI integration.
Бесплатно
