– Millions of people use Twitter and other social media sites to share their everyday thoughts in the form of tweets. It is a short and straightforward way of expressing oneself, which is a hallmark of tweeting. As a result, we concentrated on sentiment analysis of Twitter data in our research. Sentiment Analysis is a subset of natural language processing and text data mining. It is feasible to investigate sentiment analysis using Twitter data. performed in a number of different circumstances The technique of finding valuable patterns from textual data is referred to as sentiment analysis. Using particular analysis tools, these valuable patterns include evaluating and categorizing feelings as neutral, positive, or negative. The study's authors look at a range of information processing approaches, including sentiment analysis, Twitter's network structure, event dispersion across the network, and impact identification. There have been several ways described for exploring semantics for sentiment analysis, which can be classified into contextual semantic and conceptual semantic approaches. One of the most important disciplines of natural language processing is sentiment analysis. The technique of finding valuable patterns from textual data is referred to as sentiment analysis. According to this research, sentiment analysis applications will continue to develop in the future, and sentiment analytical approaches will become more standardized across systems and services. Because of the vast amount of data available, Twitter is one of the best virtual environments for tracking and monitoring information.
{"title":"Sentiment Analysis Of Tweets Using Natural Language Processing","authors":"D. Ekmekci, Firas Shihab","doi":"10.36287/ijmsit.6.1.58","DOIUrl":"https://doi.org/10.36287/ijmsit.6.1.58","url":null,"abstract":"– Millions of people use Twitter and other social media sites to share their everyday thoughts in the form of tweets. It is a short and straightforward way of expressing oneself, which is a hallmark of tweeting. As a result, we concentrated on sentiment analysis of Twitter data in our research. Sentiment Analysis is a subset of natural language processing and text data mining. It is feasible to investigate sentiment analysis using Twitter data. performed in a number of different circumstances The technique of finding valuable patterns from textual data is referred to as sentiment analysis. Using particular analysis tools, these valuable patterns include evaluating and categorizing feelings as neutral, positive, or negative. The study's authors look at a range of information processing approaches, including sentiment analysis, Twitter's network structure, event dispersion across the network, and impact identification. There have been several ways described for exploring semantics for sentiment analysis, which can be classified into contextual semantic and conceptual semantic approaches. One of the most important disciplines of natural language processing is sentiment analysis. The technique of finding valuable patterns from textual data is referred to as sentiment analysis. According to this research, sentiment analysis applications will continue to develop in the future, and sentiment analytical approaches will become more standardized across systems and services. Because of the vast amount of data available, Twitter is one of the best virtual environments for tracking and monitoring information.","PeriodicalId":166049,"journal":{"name":"International Journal of Multidisciplinary Studies and Innovative Technologies","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133637112","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}
Mehmet Iscan, Ali Ihsan Tas, Berkem Vural, Ali Burak Ozden, Cuneyt Yilmaz
– Communication systems have recently been very important in mini unmanned aerial vehicles (UAV), which include many research subjects. Directional antennas are generally used in communication systems, and they should continuously and efficiently follow the UAVs with minimal errors. For this purpose, an “Antenna Tracker” system, which is capable of real-time autonomous orientation based on GPS data from the UAV, was designed. In the beginning, the system’s 3-dimensional solid model was obtained in SOLIDWORKS TM and its dynamical model was made in MATLAB / Simulink TM environment. For controlling the system, a discrete-time model-based computed torque proportional controller, which is the state-of-the-art innovation in this study, was designed in two axes, and then its simulation studies were conducted on the STM32 board. The simulation studies showed that controlling the pan and tilt axes is sufficient for effective tracking, and the presented antenna tracker system is suitable for use in mobile ground control stations (GCS). By using a short sampling time for the controller, stable and precise antenna tracking is accomplished for a given reference path. When a 0.5 Hz sinusoidal reference signal input which is the maximum speed for any antenna tracker was used as a sample reference track, ±0.3- and ±0.6-degrees position error of pan and tilt angles were obtained, respectively. The controller can easily satisfy a smooth tracking operation with high accuracy.
{"title":"Antenna Tracker Design With A Discrete Lyapunov Stability Based Controller For Mini Unmanned Aerial Vehicles","authors":"Mehmet Iscan, Ali Ihsan Tas, Berkem Vural, Ali Burak Ozden, Cuneyt Yilmaz","doi":"10.36287/ijmsit.6.1.77","DOIUrl":"https://doi.org/10.36287/ijmsit.6.1.77","url":null,"abstract":"– Communication systems have recently been very important in mini unmanned aerial vehicles (UAV), which include many research subjects. Directional antennas are generally used in communication systems, and they should continuously and efficiently follow the UAVs with minimal errors. For this purpose, an “Antenna Tracker” system, which is capable of real-time autonomous orientation based on GPS data from the UAV, was designed. In the beginning, the system’s 3-dimensional solid model was obtained in SOLIDWORKS TM and its dynamical model was made in MATLAB / Simulink TM environment. For controlling the system, a discrete-time model-based computed torque proportional controller, which is the state-of-the-art innovation in this study, was designed in two axes, and then its simulation studies were conducted on the STM32 board. The simulation studies showed that controlling the pan and tilt axes is sufficient for effective tracking, and the presented antenna tracker system is suitable for use in mobile ground control stations (GCS). By using a short sampling time for the controller, stable and precise antenna tracking is accomplished for a given reference path. When a 0.5 Hz sinusoidal reference signal input which is the maximum speed for any antenna tracker was used as a sample reference track, ±0.3- and ±0.6-degrees position error of pan and tilt angles were obtained, respectively. The controller can easily satisfy a smooth tracking operation with high accuracy.","PeriodicalId":166049,"journal":{"name":"International Journal of Multidisciplinary Studies and Innovative Technologies","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130142141","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}
– The widespread usage of Internet of Things (IoT) devices is increasing by the recent advances in embedded systems, cloud computing, artificial intelligence, and wireless communications. Besides, a huge amount of data is transmitted between IoT devices over insecure networks. The transferred data can be sensitive and confidential. On the other hand, these transmitted data may not appear to be sensitive or confidential data. However, machine learning techniques are used on these non-confidential data (such as packet length) to obtain data such as the type of the IoT device. An observer can monitor traffic to infer sensitive data by using machine learning techniques to analyze the generated encrypted traffic. For this purpose, padding can be added to the packets to ensure traffic privacy. This paper presents privacy problems that are caused by the traffic generated during the communication of IoT devices. Also, security and privacy measures that should be taken against the related privacy problems are explained. For this purpose, the current studies are examined by considering the attacker and the defender models.
{"title":"Ensuring IoT Privacy using Padding Strategies against Machine Learning Approaches","authors":"Ahmet Emre Ergun, Özgü Can","doi":"10.36287/ijmsit.6.2.193","DOIUrl":"https://doi.org/10.36287/ijmsit.6.2.193","url":null,"abstract":"– The widespread usage of Internet of Things (IoT) devices is increasing by the recent advances in embedded systems, cloud computing, artificial intelligence, and wireless communications. Besides, a huge amount of data is transmitted between IoT devices over insecure networks. The transferred data can be sensitive and confidential. On the other hand, these transmitted data may not appear to be sensitive or confidential data. However, machine learning techniques are used on these non-confidential data (such as packet length) to obtain data such as the type of the IoT device. An observer can monitor traffic to infer sensitive data by using machine learning techniques to analyze the generated encrypted traffic. For this purpose, padding can be added to the packets to ensure traffic privacy. This paper presents privacy problems that are caused by the traffic generated during the communication of IoT devices. Also, security and privacy measures that should be taken against the related privacy problems are explained. For this purpose, the current studies are examined by considering the attacker and the defender models.","PeriodicalId":166049,"journal":{"name":"International Journal of Multidisciplinary Studies and Innovative Technologies","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132936130","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}
Şebnem Bora, Aylin Kantarcı, A. Erdogan, Burak Beynek, Bita Kheibari, Vedat Evren, M. Erdoğan, Fulya Kavak, Fatmanur Afyoncu, Cansu Eryaz, H. Gönüllü
– Due to the rising number of visits to emergency departments all around the world and the importance of emergency departments in hospitals, the accurate and timely evaluation of a patient in the emergency section is of great importance. In this regard, the correct triage of the emergency department also requires a high level of priority and sensitivity. Correct and timely triage of patients is vital to effective performance in the emergency department, and if the inappropriate level of triage is chosen, errors in patients' triage will have serious consequences. It can be difficult for medical staff to assess patients' priorities at times, therefore offering an intelligent method will be pivotal for both increasing the accuracy of patients' priorities and decreasing the waiting time for emergency patients. In this study, we evaluate the machine learning algorithms in triage procedure. Our experiments show that Random Forest approach outperforms the others in e-triage .
{"title":"Machine Learning for E-triage","authors":"Şebnem Bora, Aylin Kantarcı, A. Erdogan, Burak Beynek, Bita Kheibari, Vedat Evren, M. Erdoğan, Fulya Kavak, Fatmanur Afyoncu, Cansu Eryaz, H. Gönüllü","doi":"10.36287/ijmsit.6.1.86","DOIUrl":"https://doi.org/10.36287/ijmsit.6.1.86","url":null,"abstract":"– Due to the rising number of visits to emergency departments all around the world and the importance of emergency departments in hospitals, the accurate and timely evaluation of a patient in the emergency section is of great importance. In this regard, the correct triage of the emergency department also requires a high level of priority and sensitivity. Correct and timely triage of patients is vital to effective performance in the emergency department, and if the inappropriate level of triage is chosen, errors in patients' triage will have serious consequences. It can be difficult for medical staff to assess patients' priorities at times, therefore offering an intelligent method will be pivotal for both increasing the accuracy of patients' priorities and decreasing the waiting time for emergency patients. In this study, we evaluate the machine learning algorithms in triage procedure. Our experiments show that Random Forest approach outperforms the others in e-triage .","PeriodicalId":166049,"journal":{"name":"International Journal of Multidisciplinary Studies and Innovative Technologies","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128077317","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}
– In this study, Al-6Si-0.3Cu ribbon alloys produced by melt-spinning method were consolidated by two different methods, which are spark plasma sintering and cryogenic ball milling + cold compaction. From X-ray diffraction analysis, it was found that the solubility of Si in Al matrix in melt-spun alloys increased, but Si precipitated in SPS and ball milled+cold compacted alloys. Optical and scanning electron microscope observation revealed that while melt spun alloys have a very fine and homogenous microstructure, Si phase has become coarser in SPS and cold compacted alloys due to the sintering. The results showed that the spark plasma sintering method is a very effective method for compaction of melt-spun Al-6Si-0.3Cu alloy.
{"title":"Consolidation of Rapidly Solidifying Al-6Si-0.3Cu Alloy by Spark Plasma Sintering and Cold Compaction Methods","authors":"F. Yasar, F. Yılmaz","doi":"10.36287/ijmsit.6.2.198","DOIUrl":"https://doi.org/10.36287/ijmsit.6.2.198","url":null,"abstract":"– In this study, Al-6Si-0.3Cu ribbon alloys produced by melt-spinning method were consolidated by two different methods, which are spark plasma sintering and cryogenic ball milling + cold compaction. From X-ray diffraction analysis, it was found that the solubility of Si in Al matrix in melt-spun alloys increased, but Si precipitated in SPS and ball milled+cold compacted alloys. Optical and scanning electron microscope observation revealed that while melt spun alloys have a very fine and homogenous microstructure, Si phase has become coarser in SPS and cold compacted alloys due to the sintering. The results showed that the spark plasma sintering method is a very effective method for compaction of melt-spun Al-6Si-0.3Cu alloy.","PeriodicalId":166049,"journal":{"name":"International Journal of Multidisciplinary Studies and Innovative Technologies","volume":"88 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126027431","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}
– Distance learning is an education model in which the educator and the student come together independently of time and place and the learning process is continued. Although it has positive aspects in terms of time and space, it has limitations such as weak interaction and poor functioning of evaluation processes. Assessment systems often include multiple-choice or open-ended questions. In other words, the result is evaluated in solving a given problem, and the student's actions can be ignored until the result is reached. In this study, while evaluating student performance, the student's behavior during the semester and the distractor weight coefficient for multiple-choice exams were added, and a performance evaluation was made on the student's incorrect answers. The proposed model was created based on fuzzy logic, and the uncertainties in the evaluation were attempted to be eliminated.
{"title":"A Novel Student Performance Evaluation Model Based on Fuzzy Logic for Distance Learning","authors":"Beyza Esin Ozseven, N. Çagman","doi":"10.36287/ijmsit.6.1.29","DOIUrl":"https://doi.org/10.36287/ijmsit.6.1.29","url":null,"abstract":"– Distance learning is an education model in which the educator and the student come together independently of time and place and the learning process is continued. Although it has positive aspects in terms of time and space, it has limitations such as weak interaction and poor functioning of evaluation processes. Assessment systems often include multiple-choice or open-ended questions. In other words, the result is evaluated in solving a given problem, and the student's actions can be ignored until the result is reached. In this study, while evaluating student performance, the student's behavior during the semester and the distractor weight coefficient for multiple-choice exams were added, and a performance evaluation was made on the student's incorrect answers. The proposed model was created based on fuzzy logic, and the uncertainties in the evaluation were attempted to be eliminated.","PeriodicalId":166049,"journal":{"name":"International Journal of Multidisciplinary Studies and Innovative Technologies","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133511230","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}
– The Digital Light Processing (DLP) 3D printer is a tool that utilizes Additive Manufacturing (AM) technology to build a 3D model straight from the CAD model. There are various 3D printing technologies that differ in many ways, including the material used, the techniques used to create the sample, the speed and accuracy, and a wide range of other factors. Choosing the best production method depends on the work at hand, ensuring that the product's material and quality meet the necessary standards. Although the DLP technology has a straightforward design, it offers an impressive array of quality and adaptability. This study offers a customized design that assures high manufacturing quality. To verify the functionality of the developed 3D printer, three distinct types of experiments using various CAD designs were conducted. Surface quality, minute details, and precise measurements have all been achieved in these trials. Additionally, two separate tests were created to confirm the desired output results.
{"title":"SUGGESTION OF A DLP BASED STEREOLITHOGRAPHY 3D PRINTER","authors":"Mohammed Sahib, Guzin Tirkes","doi":"10.36287/ijmsit.6.2.238","DOIUrl":"https://doi.org/10.36287/ijmsit.6.2.238","url":null,"abstract":"– The Digital Light Processing (DLP) 3D printer is a tool that utilizes Additive Manufacturing (AM) technology to build a 3D model straight from the CAD model. There are various 3D printing technologies that differ in many ways, including the material used, the techniques used to create the sample, the speed and accuracy, and a wide range of other factors. Choosing the best production method depends on the work at hand, ensuring that the product's material and quality meet the necessary standards. Although the DLP technology has a straightforward design, it offers an impressive array of quality and adaptability. This study offers a customized design that assures high manufacturing quality. To verify the functionality of the developed 3D printer, three distinct types of experiments using various CAD designs were conducted. Surface quality, minute details, and precise measurements have all been achieved in these trials. Additionally, two separate tests were created to confirm the desired output results.","PeriodicalId":166049,"journal":{"name":"International Journal of Multidisciplinary Studies and Innovative Technologies","volume":"135 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114831400","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}
– This paper presents applied physical proto results as a proof of technical concept of the patent: “ Specific Lens design for Automotive Headlamps” (European Patent Office, Specific Lens design for Automotive Headlamps: European Patent Office, The Hague PCT/TR2020/051125; 11/2021). It includes the base explanations of bending/cornering lights features; the relevant European regulations; and then proposes the new idea with defined new optomechanical targets. It gets deeper with design of the new non-uniform surface lens in five different versions for which the patent is applied on version 5 and it continues with physical proto construction of the complete LED Module; assembly of the module in the automotive headlights; making the new module functional in the headlamp and finally giving the applied physical results with a night drive test.
{"title":"Development Of Led Based Optical Module for Bending/Cornering Functions of Automotive Headlights","authors":"Ceren Altıngöz","doi":"10.36287/ijmsit.6.2.223","DOIUrl":"https://doi.org/10.36287/ijmsit.6.2.223","url":null,"abstract":"– This paper presents applied physical proto results as a proof of technical concept of the patent: “ Specific Lens design for Automotive Headlamps” (European Patent Office, Specific Lens design for Automotive Headlamps: European Patent Office, The Hague PCT/TR2020/051125; 11/2021). It includes the base explanations of bending/cornering lights features; the relevant European regulations; and then proposes the new idea with defined new optomechanical targets. It gets deeper with design of the new non-uniform surface lens in five different versions for which the patent is applied on version 5 and it continues with physical proto construction of the complete LED Module; assembly of the module in the automotive headlights; making the new module functional in the headlamp and finally giving the applied physical results with a night drive test.","PeriodicalId":166049,"journal":{"name":"International Journal of Multidisciplinary Studies and Innovative Technologies","volume":"211 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116409228","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}
S. P. Sari, N. S. Salahuddin, Sri Hayunningsih, R. Rochmawati, Ario Geraldi, Ichsan Purnama, Nora Trisna Tumewa
– Infectious waste is around 39.51 kg per day by waste products of independent practice facilities for midwives, health centers and maternity clinics. Most of the infectious waste is contaminated with bacteria, viruses, toxins, and radioactive materials that are harmful to humans and other creatures around them. To prevent the negative impact of infectious waste (underpad, cotton, bandages, and tissue), special handling of infectious waste materials is required. Based on the washing machine principle, we have designed the Infectious Waste Sterilization and Neutralization System, using three types of chemicals and 5 filter elements with a capacity of 5 kg. By using this system, the disposal of infectious waste contaminated with bacteria and viruses can be cleaned within 40 minutes so that it will be safer for the community and the sanitation of the environment around the disposal site and the manufacturing cost is not too expensive.
{"title":"Development of Infectious Waste Sterilization and Neutralization System","authors":"S. P. Sari, N. S. Salahuddin, Sri Hayunningsih, R. Rochmawati, Ario Geraldi, Ichsan Purnama, Nora Trisna Tumewa","doi":"10.36287/ijmsit.6.2.152","DOIUrl":"https://doi.org/10.36287/ijmsit.6.2.152","url":null,"abstract":"– Infectious waste is around 39.51 kg per day by waste products of independent practice facilities for midwives, health centers and maternity clinics. Most of the infectious waste is contaminated with bacteria, viruses, toxins, and radioactive materials that are harmful to humans and other creatures around them. To prevent the negative impact of infectious waste (underpad, cotton, bandages, and tissue), special handling of infectious waste materials is required. Based on the washing machine principle, we have designed the Infectious Waste Sterilization and Neutralization System, using three types of chemicals and 5 filter elements with a capacity of 5 kg. By using this system, the disposal of infectious waste contaminated with bacteria and viruses can be cleaned within 40 minutes so that it will be safer for the community and the sanitation of the environment around the disposal site and the manufacturing cost is not too expensive.","PeriodicalId":166049,"journal":{"name":"International Journal of Multidisciplinary Studies and Innovative Technologies","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123513359","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}
Ahmet Zencirli, Harun Çetin, Nedim Tuğ, Engin Seven, Tolga Ensari
Extended Abstract – Many different types of products can be sold on electronic commerce platforms. Products can be sold regardless of where customers are. The recommendation system on these platforms plays a critical role in selecting and displaying interesting products for users. In the study, the products to be purchased next to the customers were recommended in the most accurate way. For this, machine learning algorithms were used and the results were compared. The singular value decomposition (SVD) method has achieved more successful results. Research Problem/Questions – To make the most appropriate match between an infinite number of products and many customers in the most accurate way. Short Literature Review – Many algorithms have been developed for the best solution in recommendation systems that try to persuade their customers to sell niche products, and it is currently a subject open to research. Methodology and k nearest neighbor (kNN) algorithms are in the long queue in electronic commerce have been improved by developing the next item recommendation system. Results and Conclusions – Machine learning algorithms can be used to solve problems in product recommendation systems. The SVD method suggested less erroneous recommendations for large datasets.
{"title":"Makine Öğrenimi ile Uzun Kuyruk Ürünler için İyileştirilmiş Sonraki Öğe Önerisi","authors":"Ahmet Zencirli, Harun Çetin, Nedim Tuğ, Engin Seven, Tolga Ensari","doi":"10.36287/ijmsit.6.1.97","DOIUrl":"https://doi.org/10.36287/ijmsit.6.1.97","url":null,"abstract":"Extended Abstract – Many different types of products can be sold on electronic commerce platforms. Products can be sold regardless of where customers are. The recommendation system on these platforms plays a critical role in selecting and displaying interesting products for users. In the study, the products to be purchased next to the customers were recommended in the most accurate way. For this, machine learning algorithms were used and the results were compared. The singular value decomposition (SVD) method has achieved more successful results. Research Problem/Questions – To make the most appropriate match between an infinite number of products and many customers in the most accurate way. Short Literature Review – Many algorithms have been developed for the best solution in recommendation systems that try to persuade their customers to sell niche products, and it is currently a subject open to research. Methodology and k nearest neighbor (kNN) algorithms are in the long queue in electronic commerce have been improved by developing the next item recommendation system. Results and Conclusions – Machine learning algorithms can be used to solve problems in product recommendation systems. The SVD method suggested less erroneous recommendations for large datasets.","PeriodicalId":166049,"journal":{"name":"International Journal of Multidisciplinary Studies and Innovative Technologies","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129723906","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：