2023 15th International Conference on Electronics, Computers and Artificial Intelligence (ECAI)最新文献

{"title":"Industrial Expert System for Intelligent Traffic Lane Allocation Using Machine Learning and Pattern Recognition","authors":"Cătălin Adrian Iordache, Constantin-Viorel Marian","doi":"10.1109/ECAI58194.2023.10194210","DOIUrl":"https://doi.org/10.1109/ECAI58194.2023.10194210","url":null,"abstract":"This paper highlights how existing infrastructure can be used to feed data to an expert system for smart vehicle traffic management. The use of existing video cameras in road intersections for traffic pattern analysis is often overlooked due to their perceived limitations and varying technical specifications. We compare the advantages and disadvantages of both a system architecture that incorporates a Convolutional Neural Network and one that makes use of a Logistic Regression algorithm for traffic lane occupancy detection and optimizes the allocation of additional lanes based on occupancy data, thereby improving vehicle traffic flow, additionally, traffic patterns are viewed analyzed from point of origin to point of dissipation, the system allocating lanes accordingly on defined segments not just in individual intersections. Using existing video camera infrastructure for data collection offers a cost-effective approach that enhances traffic safety, enables emergency corridors, and allows flexibility in lane allocation without requiring a complete replacement of costly infrastructure already in use in most major cities around the world.","PeriodicalId":391483,"journal":{"name":"2023 15th International Conference on Electronics, Computers and Artificial Intelligence (ECAI)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121834051","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":"On the Decomposition Parameter of the RLS Algorithm Based on the Nearest Kronecker Product","authors":"R. Dobre, C. Paleologu, J. Benesty, F. Albu","doi":"10.1109/ECAI58194.2023.10193888","DOIUrl":"https://doi.org/10.1109/ECAI58194.2023.10193888","url":null,"abstract":"Decomposition-based algorithms have gained much attention lately, in the context of low-rank system identification problems. These algorithms exploit the nearest Kronecker product (NKP) decomposition of the impulse response (usually of long length) and take advantage of low rank approximations. Among them, the recursive least-squares (RLS) algorithm developed in this framework, namely RLS-NKP, has been found to be very suitable in challenging system identification problems that involve long length impulse responses, e.g., like in acoustic echo cancellation. The performance of the RLS-NKP algorithm depends on its decomposition parameter, which is related to the accuracy of low rank approximation. The current paper focuses on the investigation of this aspect and proposes a simple solution for choosing the decomposition parameter, using a preprocessing stage that relies on a low-complexity algorithm. Experiments are performed in the framework of acoustic echo cancellation and the obtained results support the validity of the proposed solution.","PeriodicalId":391483,"journal":{"name":"2023 15th International Conference on Electronics, Computers and Artificial Intelligence (ECAI)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124801108","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":"Revolutionizing Customer Experience with AI: A Path to Increase Revenue Growth Rate","authors":"Harsha Vijayakumar","doi":"10.1109/ECAI58194.2023.10194016","DOIUrl":"https://doi.org/10.1109/ECAI58194.2023.10194016","url":null,"abstract":"In this 21st century, customers expect every company or product organization to deliver exceptional customer experience not just in terms of fantastic product experience, its support or service, execution, and commitment to delighting the customer at every step of their journey. E.g., Apple, Inc. has been a pinnacle customer experience company of the 21st century with the largest market cap, revenue, and customer base due to its commitment towards experience and delighting customers in every step of the journey either in stores or products. Customer experience has a significant impact on a company's revenue growth rate. Companies that deliver a positive customer experience are more likely to retain and attract new customers, leading to increased revenue; this shows up in recurring revenue and annual growth rate. In contrast, companies that fail to deliver a good customer experience may experience a decline in customer satisfaction and loyalty, resulting in reduced revenue. Adding some spice to the customer experience is AI; Artificial Intelligence has been a scorching top topic of discussion in the 21st century; every organization wants to build an AI-Powered product and technology that can simplify the human effort to do things. e.g., ChatGPT (AI-Powered Search Interface by OpenAI) has been the talk of the town, with every company wanting to integrate with it to give a better customer experience. This research paper aims to explore the relationship between AI-Powered customer experience and revenue growth rate by analyzing the impact of customer experience on companies' annual subscriptions ($ value). This research paper discusses the critical characteristics of AI-Powered customer experience like NPS(Net promoter Score), event attendance, product upgrades, partner involvement, elevated productivity with automation, and product adoption. By understanding the importance of customer experience and how it impacts revenue growth, companies can take steps to optimize AI usage to drive customer experience and long-term business success.","PeriodicalId":391483,"journal":{"name":"2023 15th International Conference on Electronics, Computers and Artificial Intelligence (ECAI)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124919935","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":"MTAFinder - Unified OSINT platform for efficient data gathering","authors":"C. Rafailă, Florina Gurzau, Constantin Grumazescu, I. Bica","doi":"10.1109/ECAI58194.2023.10194004","DOIUrl":"https://doi.org/10.1109/ECAI58194.2023.10194004","url":null,"abstract":"Due to the digital era and rapid advancements in technology, an enormous amount of publicly available information is generated. Open Source Intelligence (OSINT) is a term used to describe the search, collection, analysis and use of information from open sources. OSINT has emerged as a valuable tool in cybersecurity, transitioning from its basic usage in social engineering to becoming a powerful tool in red teaming exercises and seamlessly integrating into the fabric of digital forensics. OSINT environment is constantly evolving with the emergence of new use cases and complex tools. This paper presents MTAFinder, an application for automated data collection that integrates OSINT open source tools and free online services. The platform is modular, scalable and provides a web API designed to gather data about people, phone numbers, web domains, e-mail addresses and IP addresses.","PeriodicalId":391483,"journal":{"name":"2023 15th International Conference on Electronics, Computers and Artificial Intelligence (ECAI)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123585720","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":"Trends and Advantages in Using Nanomaterials for Air Filtration","authors":"M. Oproescu, O. Ahmed, Gabriel V. Iana, M. Dicu, A. Balteanu, M. Bâldea","doi":"10.1109/ECAI58194.2023.10194091","DOIUrl":"https://doi.org/10.1109/ECAI58194.2023.10194091","url":null,"abstract":"In recent years, substantial progress has been achieved in the preparation and characterization of nanostructured materials, which have become available for a wide range of applications with filtering properties. In such materials it has been observed that, with decreasing crystallite sizes, grain boundaries contribute significantly to the material's microscopic properties. Numerous fundamental physical properties change dramatically when the dimensions of materials become in the nanometer range. Nanostructure properties are highly influenced by the interface between different particles, layers, or crystals or amorphous domains. An increasing number of studies are being done on metal oxide nanoparticles such as MgO, ZnO, CaO, CuO, Ag2O, TiO2, Ag, and carbon nanotubes for their potential application as antimicrobials in food, environment, and health settings. The paper aims to summarize the importance of using nanomaterials to increase the efficiency of filtration media.","PeriodicalId":391483,"journal":{"name":"2023 15th International Conference on Electronics, Computers and Artificial Intelligence (ECAI)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114892933","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":"P2G2P System - Case Study for A 5 MW Photovoltaic Park","authors":"M. Culcer, M. Iliescu, M. Răboacă, M. Raceanu, Adrian Enache, E. Carcadea","doi":"10.1109/ECAI58194.2023.10194064","DOIUrl":"https://doi.org/10.1109/ECAI58194.2023.10194064","url":null,"abstract":"In its most concise expression, the economy of hydrogen is synthesized by the use of hydrogen as an energy vector to allow the conversion of variable renewable energy (VRE) into electricity useful for operating various equipment and processes, in the so-called Power to Gas to Power (P2G2P) conversion. The paper deals with a P2G2P system based on solar energy to produce “green” hydrogen to be used as fuel to supply (pure or mixed with natural gas) a gas turbine to generate electricity. Hydrogen is produced by water electrolysis and stored in pressurized tanks in the so-called P2G (power to gas) technology. Its subsequent use for power generation in a G2P (gas to power) system allows the storage of the excess energy produced by the PV (photovoltaic) panels to be used later to compensate the solar energy intermittency. The issues relating to sizing such a P2G2P system supplied by a 5 MW PV panels park, its operating performances and economics are presented. Results are materialized in data regarding the monthly distribution of resources and production, as well as those related to revenues and the expenses involved. Ways to increase system efficiency are also suggested.","PeriodicalId":391483,"journal":{"name":"2023 15th International Conference on Electronics, Computers and Artificial Intelligence (ECAI)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122441489","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":"GSM Wireless Sensor Node Prototype for Infield Environmental Parameters Acquisition","authors":"D. Sacaleanu, Irina Petra Manciu, S. Rosu, L. Perisoara, A. Tannouche, Loredana-Elisabeta Stelian Cretu","doi":"10.1109/ECAI58194.2023.10194080","DOIUrl":"https://doi.org/10.1109/ECAI58194.2023.10194080","url":null,"abstract":"Wireless Sensor Networks (WSN) are an important part of the general framework known as the Internet of Things (IoT). Sensors collect data from any kind of environment: indoor or outdoor, terrestrial, or aerial (even space), commercial, industrial, agricultural, or domestic. As in any other type of network, communication is an essential element of the system. In the process of network design, a particular interest is shown in the resources available in order to ensure communication functionality. In agriculture, wireless communication is usually considered the most suitable for this task due to environmental conditions and communication distance. For outdoor applications, GSM protocol permits flawless communications over those large areas where the service coverage is available. The main advantage of the GSM is the coverage around the world, while the drawback is the high current consumption that has a direct impact on the system lifetime powered with batteries. In this paper, a GSM wireless sensor node (GWSn) is proposed for infield data acquisition. Tests were performed in the laboratory to analyze the current consumption and infield to observe the feasibility of the proposed prototype. To ensure an increased lifetime considering the current consumption acquired, the GWSn was equipped with a photovoltaic panel.","PeriodicalId":391483,"journal":{"name":"2023 15th International Conference on Electronics, Computers and Artificial Intelligence (ECAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122974751","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 personality model using genetic algorithms and behavioral psychology","authors":"Ciprian Nuţescu, Mariana Mocanu","doi":"10.1109/ECAI58194.2023.10194187","DOIUrl":"https://doi.org/10.1109/ECAI58194.2023.10194187","url":null,"abstract":"In this paper, we propose a genetic algorithm based on behavioral psychology developed by Carl Gustav Jung (16 Personalities model), in which we describe the person's behavioral features related to his personality. The model used for inherence is based on 40 years of psychology studies from the book “The 16personalityy types that determinate how we live, love and work” [1] by Otto Kroeger and Janet M. Thuesen, published in 1988, but using inference extracted from an MBTI (Myers-Briggs Personality Type Indicator) dataset of online posts based on person personality and it thinks from 2018 [2].","PeriodicalId":391483,"journal":{"name":"2023 15th International Conference on Electronics, Computers and Artificial Intelligence (ECAI)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121881959","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 Reliability Analysis of Self-Driving Vehicles: Evaluating the Safety and Performance of Autonomous Driving Systems","authors":"Aneesh Pradeep, Mironshokh Bakoev, Nazokat Akhroljonova","doi":"10.1109/ECAI58194.2023.10194188","DOIUrl":"https://doi.org/10.1109/ECAI58194.2023.10194188","url":null,"abstract":"Self-driving cars are a ground-breaking invention with the potential to revolutionize the transportation sector. As technology develops, it is more crucial than ever to guarantee the dependability of self-driving cars. The dependability analysis of self-driving cars is the main topic of this research article. The multiple levels of automation in self-driving cars and their accompanying reliability requirements are covered in the first section of the study. Afterwards, it examines the many parts of a self-driving car system, such as the perception, decision-making, and control subsystems, and talks about the dependability issues that each of these parts faces. The paper ends by highlighting the value of reliability analysis in ensuring the security and wide acceptance of self-driving cars. In order to overcome the remaining issues and provide more sophisticated methods for self-driving car dependability evaluations, the report advocates for additional research.","PeriodicalId":391483,"journal":{"name":"2023 15th International Conference on Electronics, Computers and Artificial Intelligence (ECAI)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116625938","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":"Feature selection using genetic algorithms for improving accuracy in image classification tasks","authors":"Andrei Dugaesescu, David-Traian Iancu","doi":"10.1109/ECAI58194.2023.10194193","DOIUrl":"https://doi.org/10.1109/ECAI58194.2023.10194193","url":null,"abstract":"Feature selection can be an effective tool for increasing the robustness and predictive accuracy of classifiers, especially in the presence of noisy features or when their dimensionality is high. Genetic algorithms (GA) lend themselves well for optimizing the search for the best subset of features. This paper present how GA can be integrated in the training of neural networks (NNs) as a feature selection step to increase the model performance. The reported experiments cover the effect such a technique can have when confronted with various sizes for the trained NN in the context of both harder and easier datasets. Moreover, the experimental setups make use of feature selection both as a traditional pre-processing step, before training the NN, as well as an intermediary processing layer between the features extractor part of a convolutional neural network (CNN), used in conjunction with more conventional statistical features, and the classification head. Although CNNs are known to inherently model the selection of features, meaning that the impact of a GA as a feature selector after the CNN backbone could be inhibited, marginal improvements in the final performance still show meaningful insight into the working of such a classifier, in the context of managing relevant features.","PeriodicalId":391483,"journal":{"name":"2023 15th International Conference on Electronics, Computers and Artificial Intelligence (ECAI)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129834092","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}