D. Ozsahin, Mubarak Taiwo Mustapha, A. Mubarak, Zubaida Said Ameen, B. Uzun
{"title":"Impact of feature scaling on machine learning models for the diagnosis of diabetes","authors":"D. Ozsahin, Mubarak Taiwo Mustapha, A. Mubarak, Zubaida Said Ameen, B. Uzun","doi":"10.1109/aie57029.2022.00024","DOIUrl":"https://doi.org/10.1109/aie57029.2022.00024","url":null,"abstract":"Due to its high prevalence and incidence, diabetes is considered significant public health. Since diabetes has no known cure, early diagnosis plays a vital role in effectively managing the disease. Feature scaling is a vital step in pre-processing data before building a model using machine learning. The datasets used for model training in machine learning often contain unpredictable values that may have varying scales. This can result in inequalities in comparing these values. Feature scaling techniques can address these challenges by adjusting the values and promoting easy and fair comparisons among values. This study aims to evaluate the impact of normalization, standardization, and no feature scaling on the performance of five machine learning models in diagnosing diabetes. The machine learning algorithms implemented for this study include random forest, naive Bayes, k-nearest neighbor (KNN), logistic regression, and support vector machine (SVM). These algorithms support supervised learning. Furthermore, several open-source frameworks and libraries were implemented. They include; Jupyter notebook, SkLearn, Pandas, NumPy, Matplotlib, and seaborn. The result obtained from the study indicates that the random forest model performed significantly well without implementing any feature scaling technique. This contrasts with the KNN and SVM model, which performed better when the normalization technique was implemented. Also, the naive Bayes model shows no changes when either standardization, normalization, or no feature scaling was implemented. This study concludes that not all model requires feature scaling techniques to be applied to the dataset to achieve optimal performance. Furthermore, distance-based and gradient descent algorithms previously thought to be sensitive to feature scaling may not necessarily be true, as indicated by the outcome of this study. Finally, feature scaling techniques significantly impact some models while others do not.","PeriodicalId":351292,"journal":{"name":"2022 International Conference on Artificial Intelligence in Everything (AIE)","volume":"47 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120995940","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Discussion on B2B international marketing strategy based on customer relationship theory","authors":"Zheng Zeng","doi":"10.1109/AIE57029.2022.00080","DOIUrl":"https://doi.org/10.1109/AIE57029.2022.00080","url":null,"abstract":"B2B international marketing strategy discussion based on customer relationship theory is about understanding the needs and aspirations of customers and the importance of their existing relationship with you. It also involves how to communicate effectively with them and what communication should be used in various situations. This means that a company must have an effective business model in order to survive in the global market. In other words, this means that the company needs to understand the needs of customers in order to develop products or services that meet these needs. Under the trend of globalization, B2B marketing mode, as a sales mode of industrial products, how to create value for customers, maintaining market status and increasing market share is the goal of marketing and management of all suppliers. Customer relationship is the most important element of B2B marketing and is key to maintaining market competitiveness in the B2B model. This paper analyzes how to establish a good customer relationship in B2B international trade from the perspective of customer relationship marketing.","PeriodicalId":351292,"journal":{"name":"2022 International Conference on Artificial Intelligence in Everything (AIE)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115068046","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"The Photoelectric Sensor Network for AGV High-precision Spatial Positioning","authors":"Jingyu Liu, Yan Wang, Mingyan Ren","doi":"10.1109/AIE57029.2022.00032","DOIUrl":"https://doi.org/10.1109/AIE57029.2022.00032","url":null,"abstract":"As a kind of automated loading and unloading, handling equipment and high-precision transportation platform, the AGV mobile platform has a range of applications in the fields of smart factories, smart warehousing and smart logistics. It is important for the research of AGV automatic navigation and positioning. Aiming at the application scenarios of AGV motion millimeter-level spatial positioning accuracy, this paper studies an angle measurement method of orthogonal line laser scanning mechanism and photoelectric sensor network perception, and proposes a spatial positioning method based on a virtual camera projection model. The system parameter calibration method that is based on the beam adjustment method is studied to realize the high-precision 3D positioning of the AGV mobile platform.","PeriodicalId":351292,"journal":{"name":"2022 International Conference on Artificial Intelligence in Everything (AIE)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116057923","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Design and application analysis of College Students' psychological early warning system based on mining algorithm","authors":"Jun Liao","doi":"10.1109/AIE57029.2022.00079","DOIUrl":"https://doi.org/10.1109/AIE57029.2022.00079","url":null,"abstract":"This is a psychological warning system that students can use to identify potential suicide risks. Based on a series of questions and answers, this method aims to help students identify their thoughts and behaviors related to suicide. The main features are as follows: (1) it can be used by teachers and parents to detect the abnormal behavior of students' psychological state, help them control their behavior and better decide their own life; (2) Students can use it to understand how they should behave, or what kind of psychology they need in different situations; The development of students' psychological management system has become an important tool to monitor and prevent students' mental health.","PeriodicalId":351292,"journal":{"name":"2022 International Conference on Artificial Intelligence in Everything (AIE)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116743281","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Critical Thinking on the Turing Test as a Standard for Testing Artificial Intelligence","authors":"W. Ouyang, H. Feng","doi":"10.1109/AIE57029.2022.00064","DOIUrl":"https://doi.org/10.1109/AIE57029.2022.00064","url":null,"abstract":"Artificial intelligence is a fashionable topic in the current world. In the domain of artificial intelligence, the most basic concept is intelligence. How to judge whether a machine or program has intelligence is an important problem. By studying the famous original paper \"computing machine and intelligence\" which proposed Turing test, and combining with the Chinese house thought experiment and the chat program Eliza experiment, this paper points out that the popular saying that Turing test is regarded as the standard to judge whether a machine has intelligence neither conforms to the actual research in artificial Intelligence, nor conform to the meaning expressed by Turing himself. We are not trying to belittle Turing’s great contribution to AI, but to clarify some misunderstandings from the perspective of critical thinking, and to point out the problems caused by these misunderstandings in current AI research and publicity.","PeriodicalId":351292,"journal":{"name":"2022 International Conference on Artificial Intelligence in Everything (AIE)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129573890","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Predicting the Student Performance via Machine Leaning Techniques","authors":"Abdul Rehman Siddiqui, Fadi M. Al-Turjman","doi":"10.1109/AIE57029.2022.00048","DOIUrl":"https://doi.org/10.1109/AIE57029.2022.00048","url":null,"abstract":"Machine learning (ML) is the ability of a system to acquire and integrate knowledge based on large-scale observations, as well as to develop and extend itself by acquiring new knowledge rather than being programmed with it. In today’s competitive world, an individual’s academic qualifications are a must. Employers' selection criteria of potential applicant are frequently based on the grade point average (GPA). Planning is an essential step in attaining a decent GPA, regardless of a student’s intellectual capacity. Many students, on the other hand, lack the essential skills and time to plan and manage their GPA. An automated education planner system would be extremely beneficial in assisting students in achieving the best CGPA possible depending on their existing skills. Despite the existence of course planning systems, students continue to fall short of their objectives. Educational data mining tools have recently been used to learn more about the educational environment and to help students perform better. Artificial Neural Networks, Support Vector Machines, nave Bayesian, Decision trees, and other approaches are utilized in educational data mining.","PeriodicalId":351292,"journal":{"name":"2022 International Conference on Artificial Intelligence in Everything (AIE)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123336948","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"The method of determining the weight of the evaluation index of students’ comprehensive quality","authors":"Kai Huang, Zhenghui Guo, Jun Ye","doi":"10.1109/AIE57029.2022.00126","DOIUrl":"https://doi.org/10.1109/AIE57029.2022.00126","url":null,"abstract":"The traditional comprehensive quality assessment of students focuses on students’ academic performance in school. This method of judging the development of students cannot objectively and truly evaluate the quality of a student. Some students have an excellent academic performance during their studies in school, but after graduation, the scores of comprehensive quality school do not seem to reflect the students’ performance in society. The reason is that in the work, what is needed is a truly comprehensive quality, and the comprehensive development of comprehensive quality has a better development space. With the advent of the era of information processing, students’ comprehensive quality management also needs to get rid of the traditional quality assessment methods. It is against this background that the comprehensive quality assessment of students in this paper is proposed. This paper proposes a comprehensive empowerment method for students’ comprehensive quality assessment combining fuzzy method and analytic hierarchy process, which can reasonably carry out the comprehensive quality assessment. It is convenient for school teachers and students to complete the evaluation work online, which can accurately and quickly analyze and rank different types of talents, and at the same time greatly enhance the practical application of the system and the rationality of the evaluation.","PeriodicalId":351292,"journal":{"name":"2022 International Conference on Artificial Intelligence in Everything (AIE)","volume":"220 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116362416","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zubaida Said Ameen, Abdullahi Umar Ibrahim, Auwalu Saleh Mubarak, F. Al-turjman, Umar Muhammad Ghali
{"title":"Deep Learning Methods For Prediction of HLA-Peptide Interactions in IDB","authors":"Zubaida Said Ameen, Abdullahi Umar Ibrahim, Auwalu Saleh Mubarak, F. Al-turjman, Umar Muhammad Ghali","doi":"10.1109/AIE57029.2022.00021","DOIUrl":"https://doi.org/10.1109/AIE57029.2022.00021","url":null,"abstract":"Inflammatory bowel disease (IBD) is a complicated gastrointestinal disease linked to so many factors. Studying the interactions and functions of proteins in diseases is a challenging task. Here, we tried to understand the relationship between Human Leukocyte Antigen (HLA) genes and peptides in the development of IBD. Two types of HLA genes, HLA DRB1* 13:01 and HLA DRB1*15:01 were considered which are highly important for presenting peptides to T-cells as one of their immunological activities, therefore, it is necessary to study their interaction with peptides. An improved version of deep learning models based on convolutional, recurrent neural networks and a hybrid of both models were proposed in this study by utilizing an embedding matrix as part of the model architecture for better encoding of amino acid features, this technique has proven to be highly effective when compared to the state of the art models. The different deep model architectures were trained and tested to predict HLA DRB1*13:01 and HLA DRB1*15:01 peptide interactions. The hybrid method gave the best performance with 0.987 as the Spearman correlation. The models proposed in this work will give better insight into the interaction between peptides and HLA genes in the development of IBD.","PeriodicalId":351292,"journal":{"name":"2022 International Conference on Artificial Intelligence in Everything (AIE)","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131463737","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Research on e-commerce security in data and cloud computing environment","authors":"Guoli Huang","doi":"10.1109/AIE57029.2022.00098","DOIUrl":"https://doi.org/10.1109/AIE57029.2022.00098","url":null,"abstract":"Big data is a new concept, which came into being in the process of society moving towards digitization. At present, e-commerce is involved in all walks of life. The big data environment promotes the development of e-commerce, but there are also some problems. This paper arranges the latest research re-sults on the safety issues of e-commerce, especially the security of e-commerce. Based on this, we analyzed the safety of e-commerce in big data and cloud computing environment by combining technology with big data and cloud computing. The research on e-commerce security in data and cloud computing environment is an important topic widely discussed by researchers. The main purpose of this research is to develop a secure e-commerce transaction system. In order to achieve this goal, we have developed a set of tools to analyze the security problems in the current system, and put forward solutions to these problems.","PeriodicalId":351292,"journal":{"name":"2022 International Conference on Artificial Intelligence in Everything (AIE)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133270508","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. Mubarak, M. Vubangsi, F. Al-turjman, Z. S. Ameen, Abdulmunaim Saleh Mahfudh, S. Alturjman
{"title":"Computer Vision Based Drone Detection Using Mask R-CNN","authors":"A. Mubarak, M. Vubangsi, F. Al-turjman, Z. S. Ameen, Abdulmunaim Saleh Mahfudh, S. Alturjman","doi":"10.1109/aie57029.2022.00108","DOIUrl":"https://doi.org/10.1109/aie57029.2022.00108","url":null,"abstract":"Security of private and military areas is very important, drones are becoming more available day by day even though they are used for different purposes. In no-fly zones like metros, airports, private properties and so on, unauthorized drones can be detected using computer vision models, in this study Mask-RCNN with two different backbones (ResNet-50 and MobileNet) was employed to detect drones. It was observed that the Mask-RCNN with ResNet-50 as backbone achieves mAP of 0.965, mAP-50 of 0.991, mAP-75 of 0.958 and recall of 0.961.","PeriodicalId":351292,"journal":{"name":"2022 International Conference on Artificial Intelligence in Everything (AIE)","volume":"142 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132100470","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}