2023 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI)最新文献

{"title":"System Design for Financial and Economic Monitoring Using Big Data Clustering","authors":"S. Madem, P. Katuri, Anandasubramanian Cp, Anandasubramanian Cp, Akash Kalra, P. Singh","doi":"10.1109/ACCAI58221.2023.10200699","DOIUrl":"https://doi.org/10.1109/ACCAI58221.2023.10200699","url":null,"abstract":"Economic data executives are becoming increasingly important for the longevity and improvement of ventures due to the constant expansion in the influence of data innovation. This study lays out an undertaking economic data the executive’s structure for the intricate internal undertaking economic data the board business. It also includes the application of web-based big data technology to understand the fairness, reliability, and security of system database calculations, mainly to improve office capabilities and solve daily project management problems. used in the project. The aim is to evaluate the suitability of transfer clustering computation (DCA) for managing large amounts of data in energy systems and the suitability of data economics dispatch methods for harnessing new energies. Then, combine day-ahead shipping plans with continuous shipping plans to create a multi-period, data-economic shipping model. Consider how the calculations are performed using a case study on the use of new energies. This will enable new energy in multi-period data economics shipping models while meeting his DR requirements on the customer side.","PeriodicalId":382104,"journal":{"name":"2023 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114660507","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":"Ensemble Machine Learning Models in Predicting Personality Traits and Insights using Myers-Briggs Dataset","authors":"Prasanna Kumar R, Bharathi Mohan G, Gudivada Dhyana Sai","doi":"10.1109/ACCAI58221.2023.10199294","DOIUrl":"https://doi.org/10.1109/ACCAI58221.2023.10199294","url":null,"abstract":"Personality prediction refers to the use of machine learning techniques to predict an individual's personality traits based on various sources of data, such as text, images, and social media usage Personality traits refer to persistent patterns of behaviors, thoughts, and feelings that differentiate one individual from another. The prediction of people’s personality traits based on their social media posts using various machine learning models. With the help of this model, a person’s personality can be classified based on the 16 categories of Myers-Briggs personality types. With the availability of a huge amount of data on human behavior and personality traits, it is possible to train a machine-learning model and predict the personality trait of a person. The ML model assesses the person based on their social media posts. The data consists of the posts from social media and the personality type to which a person belongs. The model will be using the NLTK library to assess and pre-process the data. Here a model has been based on built four machine learning models, which include logistic regression, support vector machines (SVM), nave Bayes, and random forest. Finally, we compare the machine learning model results to determine which one is best based on evaluation metrics (accuracy score, geometric mean score, ROC-AUC score). Furthermore, this can be used in the personalization of online advertising ads and campaigns. Also, it can be used by social media companies to attract users based on their personality traits and preferences.","PeriodicalId":382104,"journal":{"name":"2023 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI)","volume":"195 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123368111","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":"Air Quality Improvement and Optimisation Using Machine Learning Technique","authors":"R. Veeranjaneyulu, S. Boopathi, Rina Kumari, A. Vidyarthi, J. S. Isaac, V. Jaiganesh","doi":"10.1109/ACCAI58221.2023.10201168","DOIUrl":"https://doi.org/10.1109/ACCAI58221.2023.10201168","url":null,"abstract":"Due to the increased use of automobiles, the manufacturing industry, and the emission of pollutants from other human activities, air pollution has risen above the expected safety level. Accurate estimating of the air quality index(AQI) is essential for effective pollution control. In this research, an AQI prediction ANFIS network model was created utilizing an already-existing data set. In this instance, the ANFIS system compares the performances of the back propagation neural network model, hybrid models, the Gaussian-BNN model, and the Gaussian-hybrid BNN model. Based on the actual raw data set, it was noted that the R and IA values of the Gaussian hybrid model are 0.9899. The ANFIS gauss-hybrid model might therefore be used to predict the most accurate model data.","PeriodicalId":382104,"journal":{"name":"2023 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126984204","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":"Biometric Recognition System using Minutiae based Technique Comparing with Correlation Based Technique to Improve the Accuracy","authors":"Ravirajan J, B. T. Geetha","doi":"10.1109/ACCAI58221.2023.10199573","DOIUrl":"https://doi.org/10.1109/ACCAI58221.2023.10199573","url":null,"abstract":"Research objective is to improve the accuracy of biometric recognition systems using novel minutiae based technique compared with correlation based technique. Two groups are present in this. Group 1 is novel minutiae technique and second group is correlation based technique each having a sample size of 50. The pretest power is obtained as 80%. There are 100 samples of fingerprints which are predefined in the MATLAB data storage directory named as FVC2002. It is done using MATLAB 2017. The novel minutiae based technique is better in terms of accuracy than the correlation based technique. The false acceptance ratio of novel minutiae based technique is 0 % but the FAR of correlation based technique is 0.01 %. Therefore it is evident, the novel minutiae based technique has a greater advantage over correlation based technique. Significance value p <0.05. 0.8 is taken as G-power value. It is observed that minutiae based technique appears significantly better than the correlation based technique in terms of accuracy and FAR.","PeriodicalId":382104,"journal":{"name":"2023 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122114254","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":"Multi-Key Privacy-Preserving Training and Classification using Supervised Machine Learning Techniques in Cloud Computing","authors":"R. Kishore, A. Chandra Sekhar, P. Patro, Debabrata Swain","doi":"10.1109/ACCAI58221.2023.10200291","DOIUrl":"https://doi.org/10.1109/ACCAI58221.2023.10200291","url":null,"abstract":"Cloud computing contains lots of processing power and storage. Cloud computing and machine learning (ML) techniques enable large-scale data processing. The enhanced ML-based categorization technique is established in the cloud. However, there is a risk of privacy leaking of training data in the data processing. The computational and communication costs of the information possessor(s) must be maintained to a minimum. This study suggests a multi-key enhanced support vector machine (MK-FHE) and multi-key fully homomorphic encryption (MK-FHE) supervised machine learning method for encrypted data (ESVM).The results suggest that MK-FHE protects data privacy and is more effective in processing.","PeriodicalId":382104,"journal":{"name":"2023 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123345703","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":"Efficient Removal of Real Time Rain Streaks from A Image using Novel Naive Bayes (NB) Compare over Linear Regression (LR) with Improved Accuracy","authors":"P. Kumar, B. T. Geetha","doi":"10.1109/ACCAI58221.2023.10199408","DOIUrl":"https://doi.org/10.1109/ACCAI58221.2023.10199408","url":null,"abstract":"Proposed study will examine the efficacy of removing real-time rain streaks from an image using novel NB and LR with the support of ML. Materials and Methods: A Realistic Single Image Dehazing (RESIDE) dataset has been collected from kaggle.com, which is a repository for our study. For all groups, a total sample of 22 was used. The proposed Naive Bayes algorithm is compared to the existing linear regression algorithms. The sample size is 44. Our proposed method includes steps for removing noise from images. For simulation, a pre-test power of 80% is used. Results: The proposed NB achieved an accuracy and sensitivity of 88.5% and 95.2%, whereas LR achieved an accuracy and sensitivity of 86.3% and 93%. The samples which are required for this investigation are calculated with the G power tool by fixing the minutest power to 0.8. In descriptive statistics, the observed effect size (p<0.05) in reference to the Naive Bayes and linear regression methods appeared significant. Conclusion: According to the experimental results, the novel NB algorithm performs significantly better than the existing LR.","PeriodicalId":382104,"journal":{"name":"2023 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125648084","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 AI Powered Threat Detector for Banking Sector Using Intelligent Surveillance Cameras","authors":"Aashish Kumar, Vinston Raja R, Mithun P, K. S. Arikumar, Arthiya A P, Bujitha Ra","doi":"10.1109/ACCAI58221.2023.10200738","DOIUrl":"https://doi.org/10.1109/ACCAI58221.2023.10200738","url":null,"abstract":"With mathematical technology, the depository and administration of surveillance movies are more adept, convenient, and approachable, admitting for advanced search methods that help in defining specific occurrences and labeling suspects with better ease, speed, and accuracy. Bank protection cameras counterbalance the continuous following of investment facilities, providing care except for typical business hours. This is especially useful for ATMs, which are used by customers 24 hours a day, seven days a week. Video following systems that use mathematical science are capable of progressive forms of dossier recognition that are useful in probing the programme footage for distinguishing bank undertakings and images of particular things. This architecture guarantees that only authorized individuals have access to a safe room. Illegal access generates an alarm and an email alert. The reliability of the face recognition system is enhanced by machine learning and neural networks, which use eye movements to recognize live faces and differentiate them from images. Faces are identified and matched to authorized people using the Haar cascade and LBPH algorithms. The technique utilizes artificial intelligence and image processing to minimize mistakes and background noise, ensuring precise identification. The technology detects restricted zones using web cams and AI analytics, making it suitable for real-time applications. The suggested method takes photos, identifies faces within them, and analyses them to provide results. If an unauthorized user tries to access the system, an alarm and email notice are sent. Noise reduction is essential for the best outcomes, and this is accomplished by removing irrelevant and blurry or out-of-bounds pictures. Video examination orders with artificial intelligence (AI) are appropriate as a fundamental finish for investment. On the individual hand, the Security Department has a scheme for envisioning and preventing violations before they happen, and, in another way, video orders are smart to accumulate dossiers associated with the countenances, process the ruling class, and present the appropriate information in a habitual manner. In this way, accountability is helped for the different consumer descriptions of the various areas that create the organization. This is the bigger reason banks invest in forceful protection measures. Another reason for managers working for the types of systems that banks require. Primarily, bank-following methods aim to check most criminal behavior and devise powerful alternatives for any project that does happen. As the bank’s programme administration system (VMS), this determines the skill to find, preserve, and share video evidence inside the arrangement and accompanying law enforcement. This saves time in all the while cases and helps guarantee a satisfactory judgment. Lastly, accompanying consumers at the heart of all banks, the first in rank concern for each bank is recognizing the life-return","PeriodicalId":382104,"journal":{"name":"2023 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI)","volume":"183 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131833115","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":"Road Lane Line Detection using Machine Learning","authors":"Joseph Nixon Kiro, Tannisha Kundu, Mohan Kumar Dehury","doi":"10.1109/ACCAI58221.2023.10201016","DOIUrl":"https://doi.org/10.1109/ACCAI58221.2023.10201016","url":null,"abstract":"Localization of the vehicle regarding street paths assumes a basic part in an attempt to make the vehicle completely independent. Perception oriented street lane line detection gives a practical and minimal expense arrangement as the vehicle's co-ordinates are obtained from the location. Deep learning has gained wonderful advancement in the area of classification and identification of objects in an image. However, in the pursuit of automated navigation, it becomes especially challenging to identify the continuous road line and assessing path offset during heavy traffic or during a traffic jam. Another complication that has evolved of late is the correct identification of road lane exit point. Thus, the common objective of any model designed for lane line detection and/or lane line exit point notification is to determine the trajectory of the road lane with accuracy, efficiency and in real time. Conventional detection strategies need manual change of limitations, they deal with numerous issues and troubles and are still exceptionally immune to impedance brought about by deterring objects, brightening changes, and asphalt wear. Another challenge for road lane line detection are curves where the chances of accidents are very high. Instructions to successfully recognize the path line while on a curve and appropriately predict the traffic status to the drivers is a troublesome task for the offering assistance to achieve safe driving. Therefore, in this paper we propose a straight-curve model-based curve identification algorithm. This technique has shown good efficiency for most curved lane conditions. This paper has mainly focused on driver assistant framework engineering using image processing method. We have used a mounted camera on the front window of the car to map the path trajectory using the road lines and calculate where the vehicle is in relation to the path lines. Some other lane line detection techniques have also been presented in this paper such as deep learning network for path offset assessment and lane line identification in a heavy traffic situation, Hough transformation algorithm which directly recognizes the lane lines in hough spaces, lane division extraction and edge connecting method etc.","PeriodicalId":382104,"journal":{"name":"2023 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI)","volume":"245 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131949069","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":"Potential of Solar Thermal and Photovoltaic Energy in the Dairy Products Sector: A Machine Learning Framework","authors":"M. Maheswari, Bindu K V, B. Kumar, Ashutosh Dixit, S. Kaliappan, G. Vijay","doi":"10.1109/ACCAI58221.2023.10200082","DOIUrl":"https://doi.org/10.1109/ACCAI58221.2023.10200082","url":null,"abstract":"This review describes the examination of a high, medium, and low-temperature generator-based triple-impact vapor ingestion refrigeration architecture by using a Machine learning framework. This appraisal makes proposals for the advancement of triple-effect fume maintenance refrigeration for warming and cooling applications in the dairy business. This investigation investigates solar warming and cooling. is applied in contemporary dairy settings. By depending on an exceptional, unbelievable asset, upgrading common sense, restricting contamination, decreasing the expenses of lessening a dangerous barometric deviation, and keeping up with oil subordinate costs lower than something different, solar energy vows to bring down power accuses of further developed headways and downsized costs. This forms nations' energy security. Utilizing different solar-situated heat improvements, the critical stock of warming is thought about to be solar-based. The discoveries recommend that fume maintenance refrigeration for warming and cooling applications in the dairy business has a triple effect associated with solar power. As the populace develops, the requirement for energy is rising rapidly in the twenty-first 100 years.","PeriodicalId":382104,"journal":{"name":"2023 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI)","volume":"604 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131660827","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":"Applying Cost-Sensitive Learning Methods to Improve Extremely Unbalanced Big Data Problems Using Random Forest","authors":"K. V. Ramana, Yuvasri. B, Sultanuddin Sj, P. Ponsudha, Sowmya Pd, A. V. Sangeetha","doi":"10.1109/ACCAI58221.2023.10199250","DOIUrl":"https://doi.org/10.1109/ACCAI58221.2023.10199250","url":null,"abstract":"In a larger part minority characterization issue, class irregularity in the dataset(s) can definitely misshape the exhibition of classifiers, creating an expectation predisposition for the greater part class. A negative (larger part) class expectation predisposition could make impeding impacts if the positive (minority) class is the gathering of interest and the application region being referred to states that a false negative is significantly more costly than a false certain. The decrease of class divergence is made more troublesome by big data because of the different and muddled design of the similarly bigger datasets. This exploration presents a wide evaluation of distributed works inside the past 8 years, zeroed in on fashionable unevenness (i.e., a greater part to-minority class proportion somewhere in the range of 100:1 and 10,000:1) in big data to survey the cutting edge in addressing ominous outcomes connected with class irregularity. In this paper we propose two methods for managing the imbalanced data grouping issue utilizing irregular backwoods. The other depends on an inspecting approach, though the first depends on cost-sensitive learning. Execution pointers like review and exactness, false-positive and false-negative rates.","PeriodicalId":382104,"journal":{"name":"2023 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134193476","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}