Signal Image Processing and Multimedia最新文献

{"title":"Hybrid Intrusion Detection Model for Computer Networks","authors":"Mohammad Besharatloo, Atiye Rahimizadeh, Masoud Besharatloo","doi":"10.5121/csit.2023.130906","DOIUrl":"https://doi.org/10.5121/csit.2023.130906","url":null,"abstract":"Intrusion detection is an important research topic in network security because of increasing growth in the use of computer network services. Intrusion detection is done with the aim of detecting the unauthorized use or abuse in the networks and systems by the intruders. Therefore, the intrusion detection system is an efficient tool to control the user's access through some predefined regulations. Since, the data used in intrusion detection system has high dimension, a proper representation is required to show the basis structure of this data. Therefore, it is necessary to eliminate the redundant features to create the best representation subset. In the proposed method, a hybrid model of differential evolution and firefly algorithms was employed to choose the best subset of properties. In addition, decision tree and support vector machine (SVM) are adopted to determine the quality of the selected properties. In the first, the sorted population is divided into two sub-populations. These optimization algorithms were implemented on these subpopulations, respectively. Then, these sub-populations are merged to create next repetition population. The performance evaluation of the proposed method is done based on KDD Cup99. The simulation results show that the proposed method has better performance than the other methods in this context.","PeriodicalId":176190,"journal":{"name":"Signal Image Processing and Multimedia","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114243677","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":"An Intelligent Recommendation Platform that Utilizes Artificial Intelligence to Drive People to Make Better Food Decisions","authors":"Julian Sun, Ang Li","doi":"10.5121/csit.2023.130911","DOIUrl":"https://doi.org/10.5121/csit.2023.130911","url":null,"abstract":"People are often given options on restaurants to eat at and are also given the ratings of those restaurants. However, the ratings can sometimes be rather similar and hard to choose from, and it can also be hard to find a restaurant that suits a person's special needs, and people often eat at a singular place once they find a good restaurant; we want to change that by trying to encourage people to try new restaurants. While our idea isn't original, we still decided to add it to the list of probably hundreds of sites out there that do the same thing. We made a restaurant recommendation with one purpose in mind, to gather data from restaurants and share that data with everyone. We used many methods to get that data, create a user interface, and add that data to the site so everyone can use it. This project had originated from another idea for a Roblox sniping site which I was told was a bit too advanced and was suggested something similar in design. A restaurant recommender and a Roblox sniping site are similar in the way they both use web scraping. Web scraping is the ability of a website to get the code from other sites. Our restaurant recommender gets data from Yelp to add to our database in the way that a Roblox sniping site can get information from the Roblox catalog to display to people to see when there's a good bargain. The restaurant recommender uses the data it gets to give recommendations for a better restaurant and it gives the 3 worst reviews on the restaurant, which are to highlight some of the potential flaws of the input restaurant. The main pieces of data the recommender gets are the restaurant genre for people to see what kind of restaurant it is, the restaurant region to see what type of food the restaurant serves, the restaurant type to see if its a bar or restaurant or what type it is, the restaurant's overall rating to see how good the restaurant is, and the Yelp page of the restaurant, for a deeper look into the restaurant itself. We then use the data to get a better restaurant. We use the restaurant type, region, and genre to find a similar restaurant, and we use the rating to find a restaurant with a better rating. We used many libraries and coding languages to build our site. We used HTML and CSS to build the user interface, we used Python to run the server we were using and build the web scraper, and then we used csv for the database containing all the data. We used beautiful soup to organize the data, and we used requests to get user input. We used pandas for the data analysis and we used sklearn to build the predictor for a better restaurant.","PeriodicalId":176190,"journal":{"name":"Signal Image Processing and Multimedia","volume":"52 41","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131470564","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":"An Survival Knowledge Training Platform to Self-Rescue From Campus Shooting using 3D Modeling and Machine Learning","authors":"Congyu Zhao, S. Singh","doi":"10.5121/csit.2023.130914","DOIUrl":"https://doi.org/10.5121/csit.2023.130914","url":null,"abstract":"School accidents have still been a major problem that happens frequently over decades [1]. Safety hazards are alsothe problem that parents and teachers were worried about, especially campus fire [2]. Schools are the main placeswhere we study and live, and are also special places where a large number of minors gather. How to do a goodjobin campus fire safety is not only related to the normal order of education and teaching on campus, but also tothesafety of teachers and students. the vital interests of households and the future of the motherland. Accordingtostatistics, more than 80% of school fires are caused by human factors, and classrooms, student dormitories, restaurants and other living places are more prone to fires. Habitual violations of regulations have become oneof the main factors that cause fires [3]. However, base on all those type of question, this paper designs an game forpreventing campus fire and other types of safety hazards might appearances at school. Our design builds upononunity engine and C# script [4].","PeriodicalId":176190,"journal":{"name":"Signal Image Processing and Multimedia","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121065209","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":"Character Archetypes in an Online Creative Course Setting: The Case of Femme Fatale","authors":"Xiaohan Feng, Makoto Murakami","doi":"10.5121/csit.2023.130912","DOIUrl":"https://doi.org/10.5121/csit.2023.130912","url":null,"abstract":"Creative writing courses have flourished in recent years. However, the accuracy of the content of some courses has yet to be examined. Character archetypes are an unavoidable topic in most courses requiring character creation. We found that some online creative courses include characters whose character archetypes are debatable. For example, the Femme Fatale is often considered a character archetype, but some scholars believe it is a stereotype bias. While the use of character archetypes and stereotypes in creative work is a matter of personal freedom, it is inappropriate to educationally disseminate content that is still controversial in the academic community. This study explores the history and reasons for the generalization of the Femme Fatale, the differences between the Femme Fatale and other character archetypes, and derives three reasons why the Femme Fatale is inappropriate as a character archetype in creative work. This study is intended to call attention to the rigor of the content of online creative writing courses.","PeriodicalId":176190,"journal":{"name":"Signal Image Processing and Multimedia","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116905494","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":"A Customer Service Text Label Recognition Method based on Sentence-Level Pre-Training Technology","authors":"Xiaoyu Qi, Bo-Ruei Cheng, Kang Yang, Lili Zhong, Yan Tang","doi":"10.5121/csit.2023.130915","DOIUrl":"https://doi.org/10.5121/csit.2023.130915","url":null,"abstract":"Customer service text data is known as the dialogue text data between users and customer service provider, and it contains a large amount of user information. The effective use of customer service text content can bring great business plan optimization to the service provider. Based on the traditional machine reading comprehension model, this paper builds a customer service text user's attribute label recognition model, and proposes a model pre-training method based on sentence-level pre-training technology: aiming at the background of poor performance of the model in answering comprehensive full-text content analysis questions such as user intent and text sentiment analysis. This paper extracts text summaries based on the T5-pegasus model, constructing a text summaries dataset for model pre-training. Then build a text summarization model including an ERNIE pre-training model, train the model's ability to understand the full text, and improve the model's ability to answer questions that need to be combined with full-text content understanding, such as user intent and sentiment analysis. Use the pre-trained model to solve customer service text label recognition tasks based on machine reading comprehension tasks. The test results based on the data set show that the improved model has an improvement in performance of customer service text label recognition task.","PeriodicalId":176190,"journal":{"name":"Signal Image Processing and Multimedia","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124049023","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":"A Topic Model based on Weighted Word Co-Occurrence Matrix and user Topic Relationships","authors":"Ziqi Xu, Bo-Ruei Cheng, Kang Yang, Lili Zhong, Yan Tang","doi":"10.5121/csit.2023.130917","DOIUrl":"https://doi.org/10.5121/csit.2023.130917","url":null,"abstract":"Various industries have widespread adopted the intelligent customer service, thus how to understand customer intent more accurately and extract key information has become a current research hotspot. However, the features that customer service dialog texts are short length, specialization and sparse lead to the poor performance of traditional topic extraction. Based on the above background and characteristics, this paper proposes a topic model WCMUT-HDP, which is based on a weighted word co-occurrence matrix and user topic relations. In the WCMUT-HDP model, this paper introduces a semantically weighted word co-occurrence matrix to mine the statistical and semantic features of customer service texts and optimize the effect of clustering. For the structure of customer service dialogues, this paper introduces temporal and author attributes of customer service dialog into the topic recognition of customer service texts. This method helps us to accurately extracts the user's intention. WCMUT-HDP is based on the Dirichlet process, and does not need to specify the number of topics in advance, which saving the time overhead of parameter experiments and evaluation. In the end of this paper, the experimental results show that the WCMUT-HDP model can effectively identify the topics of customer service conversations, and the extracted topics can accurately reflect the user's conversational intent.","PeriodicalId":176190,"journal":{"name":"Signal Image Processing and Multimedia","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131768310","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":"Smoothing Parameter Selection and Alpha-Stable P-Adic Time Signals","authors":"R. Sabre, W. Horrigue","doi":"10.5121/csit.2023.130902","DOIUrl":"https://doi.org/10.5121/csit.2023.130902","url":null,"abstract":"The estimation of the spectral density of stable p-adic signals is already done. Such estimation is based on smoothing the periodogram by using a spectral window. The convergence rate of this estimator depends on bandwidth of spectral window (called the smoothing parameter). The aim of this work is to give a technique for selecting the optimal parameter, i.e. the parameter that achieves the estimation with the best convergence rate. For that purpose, we were inspired by the cross-validation method of finding the optimal parameter. This method minimizes the integrated square error estimate.","PeriodicalId":176190,"journal":{"name":"Signal Image Processing and Multimedia","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132090129","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":"Creating an Equitable Option for High School Internship Opportunities: An Online Platform for Efficiently Connecting Students and Employers","authors":"E. Vuong, Kevin J. Jones","doi":"10.5121/csit.2023.130905","DOIUrl":"https://doi.org/10.5121/csit.2023.130905","url":null,"abstract":"Internships are nearly impossible to find as a highschooler outside of paying for one or having familial connections[1]. A reason for this is that there are only substandard public resources for finding these internships as ahighschooler [2]. So, by creating an equitable option through an online website, highschoolers would be able tofindinternships much better. Within the proposed website would include ways to search/filter for internships, haveemployers create accounts and create internship posts. Students would also need to quickly be able to browseinternship options, which was fixed through adding a list of random internships of dif erent varieties that canbescrolled through on the main page [3]. With this ease of access to obtaining an internship, many highschoolerswould be able to find what interests them easily and help them find experiences that are more worthwhile beyondjust the skills they learn such as helping with college applications or getting a job [4].","PeriodicalId":176190,"journal":{"name":"Signal Image Processing and Multimedia","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133501119","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":"A Structured Note-Taking Program to Aid in Data Retention and Promote Organization using Mobile Devices as a Medium","authors":"Mingyuan Gao, Armando Contreras","doi":"10.5121/csit.2023.130923","DOIUrl":"https://doi.org/10.5121/csit.2023.130923","url":null,"abstract":"In recent years, note-taking applications have become a common tool due to the simple organizational features it can provide. A key aspect of note-taking applications is the ability to efficiently record and edit large amounts of data. SQL databases are well suited to this task because they provide a reliable and scalable way to manage structured data, allowing note-taking applications to more efficiently store notes, tags and metadata associated with each note. They also support search and retrieval operations, enabling users to quickly find the information they have recorded. In addition, SQL databases provide features such as data stabilization, alternation and access, which help ensure the integrity and security of user-entered data. By utilizing SQL database replication and sharing features, note-taking applications can distribute their data across multiple servers, improving performance and reliability. In our experiments, the app demonstrated its reliability and memory capabilities. With a mean load time of 3 seconds. In summary, note-taking applications benefit from using SQL databases due to their efficiency, scalability, and data management features. These advantages help users maintain integrity, find information quickly, and keep their notes secure.","PeriodicalId":176190,"journal":{"name":"Signal Image Processing and Multimedia","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125192662","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":"Efficiently Navigating Information Overload: Developing a Machine-Learning-Based Application for Summarizing Academic Videos and Extracting Key Topics","authors":"Tianyang Wang, Aleksandr Smolin","doi":"10.5121/csit.2023.130921","DOIUrl":"https://doi.org/10.5121/csit.2023.130921","url":null,"abstract":"The internet is a vast treasure trove of information on any subject that has allowed students and scientists alikeunprecedented access to the world's collective knowledge [1]. Unfortunately, a lot of it is buried in hours longseminars, talks and other videos on video sharing websites like YouTube [2]. When researching a topic for anacademic essay or paper, one might rightly be shocked by the massive time investment required to dig uptherelevant data or citations from these monolithic recordings [3]. This paper develops an application that aims toapply new machine-learning-based transcription and keyword extraction methods to cut these videos into small, digestible chunks, which are labeled with their most important topics in order to allow us only to have to manuallyanalyze the parts of the video that are relevant to our research without losing valuable context details [4]. Weapplied our program to instructional videos on YouTube, in order to test how well we can rearrange videodocuments for a more convenient view of its contents and conducted a qualitative evaluation of the approach. Theresults show that the application works as expected to provide video clips titled with its central topic for the user todownload in a reasonable amount of time via a simple browser-based extension [5].","PeriodicalId":176190,"journal":{"name":"Signal Image Processing and Multimedia","volume":"1199 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134488783","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}