Proceedings of the 4th International Conference on Information Management & Machine Intelligence最新文献

{"title":"Artificial Intelligence-based Diagnostic Analysis for Wireless Capsule Endoscopy in Obscure Bowel Disease Detection: A Potential","authors":"Esha Saxena, Manoj Yadav, Meenakshi Yadav, Preety Shoran","doi":"10.1145/3590837.3590840","DOIUrl":"https://doi.org/10.1145/3590837.3590840","url":null,"abstract":"Wireless Capsule Endoscopy (WCE) has become one of the most practiced techniques in gastrointestinal (GI) tract disease detection. WCE is expecting to benefit more if examinations are carried out with more advanced AI technologies. Research development in the area of artificial intelligence (AI) for gastrointestinal endoscopy has increased widely to detect multiple lesions, bleeding areas, cancer with more accuracy and detecting the severity of the abnormal area. In this study, we have in view to summarize the importance of AI in Capsule Endoscopy bowel disease detection. Reading capsule endoscopy images and watching its videos is a very time-consuming and error-prone process, AI computerized algorithms if embedded with the device will surely help in detecting every minor problem efficiently. Through this work, we are trying to suggest how useful is AI- based predictive algorithms for WCE in detecting automatic abnormal region classification. A number of studies have shown that an AI-driven method has great potential for investigating various fields of the healthcare sector. This paper gives an outline of the existing position and future potential of AI in Wireless Capsule endoscopy.","PeriodicalId":112926,"journal":{"name":"Proceedings of the 4th International Conference on Information Management & Machine Intelligence","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123319348","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":"Adversarial Attack to Deceive One Stage Object Detection Algorithms","authors":"Satish Kumar, C. Krishna, Sahil Khattar, Raj Kumar Tickoo","doi":"10.1145/3590837.3590873","DOIUrl":"https://doi.org/10.1145/3590837.3590873","url":null,"abstract":"In this paper, we are focusing to fool one stage object detection algorithms and propose a black box method to generate adversarial example such that it is imperceptible to human eyes and can fool one stage object detectors. We are generating random perturbation and scaling it on the basis of unsuccessful attack and maximum number of iterations. The generated perturbation is added to original image to generate perturbed image. After that the output of one-stage object detector is compared. We have defined three success scenarios, hiding objects, misclassification and count of objects, if attack achieved one of these scenarios, it will be considered as successful attack. The proposed work is evaluated on the basis of perceptibility, average number of iterations and convergence rate. The results show that we have achieved 98.05% convergence rate on 4.7 average number of iteration with PASS score of 1.94*10-2 on RetinaNet, 98.73% convergence rate on 4.68 average number of iteration with PASS score of 1.58*10-2 on Single Shot multi-box Detection (SSD) and 77.11% convergence rate on 6.08 average number of iteration with PASS score of 2.04*10-2 on You Look Only Once version 3 (YOLO V3) which shows the effectiveness of proposed attack.","PeriodicalId":112926,"journal":{"name":"Proceedings of the 4th International Conference on Information Management & Machine Intelligence","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115867857","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":"Performance Evaluation of Jaya Algorithm During Search Space Violation","authors":"P. Dewangan, Praveen Mande, Ankur Gupta, P. Krishna, V. Meena, Vinay Singh","doi":"10.1145/3590837.3590841","DOIUrl":"https://doi.org/10.1145/3590837.3590841","url":null,"abstract":"In this work, the efficiency and performance of the Jaya optimizer are evaluated for two different initialization methods. In the course of the entire iterative process, these starting approaches are used whenever an aspect of any explanation violates the exploration area. The violating aspect is initially set up in the first technique close to the edge of the exploration area. In the second, the violating aspect of the exploration area is initialized at irregularly. For performance comparison, eight different unimodal measure exercises are reduced using the modified Jaya approach. The appraisal of the evenhanded exercise, or figure of merit, along with its mean, minimum, standard deviation, and maximum appraisals are used to compare efficacy and performance.","PeriodicalId":112926,"journal":{"name":"Proceedings of the 4th International Conference on Information Management & Machine Intelligence","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132015993","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":"Plant Disease Detection Over Multiple Datasets Using AlexNet","authors":"Palika Jajoo, Mayank Jain, Sarla Jangir","doi":"10.1145/3590837.3590838","DOIUrl":"https://doi.org/10.1145/3590837.3590838","url":null,"abstract":"Plants diseases are responsible for huge loss of crop yield. Manual inspection of plant disease is a time taken and inefficient process. Image processing and machine learning-based approaches have been offered as a solution for creating such automated plant disease detection systems. Plant diseases leads to change in color and texture of leave, this property is used for developing plant disease detection systems. Deep learning models such as Visual Geometry Group (VGG) and ResNET are extensively used in this field. However, most of these models are not scalable as they are either focused on disease classification on a particular crop or dataset. The focus of this study is to showcase a new method for identifying leaf diseases. AlexNet is used in the system's development, and it is trained and verified using data from many sources. Results indicate improved performance as compared to previously published works.","PeriodicalId":112926,"journal":{"name":"Proceedings of the 4th International Conference on Information Management & Machine Intelligence","volume":"223 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127294927","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":"Exploratory Data Analysis on Student Alcohol Consumption","authors":"Yashoda Verma, Aakansha Gupta, R. Katarya","doi":"10.1145/3590837.3590930","DOIUrl":"https://doi.org/10.1145/3590837.3590930","url":null,"abstract":"Alcohol is very common in youth these days; it is consumed by most individuals, especially Gen Z. Alcohol consumption is now taken as a status symbol in this millennial world where people only think about what makes them cooler for their fellow peers and indulge in such activities, but the overuse of alcohol has led to various drastic consequences in normal student's life. There is a common saying that excess of everything is bad; excessive consumption of alcohol has turned out to be a negative factor in any student's life, hindering their academics as well as psychological conditions. In this study, we have taken data through questionnaires from 2 different classes of Maths & Portuguese of Senior Secondary College. A total of 700 entries were taken and analyzed using various statistical and analytical tools. The results showed an evident relation between the alcohol consumption by the students and their academic performance; some factors were also seen affecting the alcohol consumption habits of the students and the trends in their alcohol consumption. Finally, the results concluded the impacts of excessive alcohol consumption and how we can work in this aspect to find out more about the psychological impacts of alcohol consumption on the students.","PeriodicalId":112926,"journal":{"name":"Proceedings of the 4th International Conference on Information Management & Machine Intelligence","volume":"9 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127375536","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":"Detection of Brain Tumors Using Magnetic Resonance Images through the Application of an Innovative Convolution Neural Network Model","authors":"S. B. Patil, D. J. Pete","doi":"10.1145/3590837.3590914","DOIUrl":"https://doi.org/10.1145/3590837.3590914","url":null,"abstract":"According to a report released by the WHO in February 2018, the mortality rate for people with brain or central nervous system cancer is highest in Asia. It is important that cancer screenings are conducted earlier to prevent these deaths. Due to the complexity of brain cancer diagnosis, it is very important that the development of effective and non-invasive tools for analyzing and predicting the grade of the disease is carried out. Currently, there are various imaging modalities that can be used to detect brain tumors, such as CT, MRI, and X-rays. Deep Learning is a type of artificial intelligence that imitates the brain's work. It can learn to recognize and interpret the voice, make decisions, and translate languages. It can also detect artifacts in data, and without human intervention, it can understand from unorganized information. A Convolutional Neural Network is a type of deep learning that is commonly used in optical representation analysis. Currently, there are systems that can detect brain tumors using small datasets. However, they only use image processing techniques and require a lot of computational resources. A new system that combines the three components of deep learning, namely image preprocessing, augmentation, and applying, is currently under development.","PeriodicalId":112926,"journal":{"name":"Proceedings of the 4th International Conference on Information Management & Machine Intelligence","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124927456","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":"Security Enhancement using Image verification method to Secure Docker Containers","authors":"V. Saxena, Deepika Saxena, U. Singh","doi":"10.1145/3590837.3590879","DOIUrl":"https://doi.org/10.1145/3590837.3590879","url":null,"abstract":"Now with the dawn of the internet, cloud computing has been reformed by opening new horizons at an inclusive level with auspicious opportunities. With the rise of opportunities, popularity, and public connectivity by the internet, it is the next foremost edge for Trojans, worms, viruses, hackers and cyber-attacks will broaden because a hacker would see this as a new edge to try to steal confidential interrupt, information, services and route damage to the originality cloud computing Docker system. Security in Docker container over the cloud is of great anxiety hence care needs to be taken to provide secure Docker containers and secure cloud services. Docker is usual within the software development community due to the portability, versatility, and scalability of containers. In this paper, we analyze the Docker storage-based security and by applying the methods of Docker image verification, checking capabilities, and storage selection, improve the security in Docker containers.","PeriodicalId":112926,"journal":{"name":"Proceedings of the 4th International Conference on Information Management & Machine Intelligence","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114429111","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":"Sky-Net: A Deep Learning Approach to Predicting Lung Function Decline in Sufferers of Idiopathic Pulmonary Fibrosis","authors":"Arjun Taneja, Anju Yadav","doi":"10.1145/3590837.3590883","DOIUrl":"https://doi.org/10.1145/3590837.3590883","url":null,"abstract":"Idiopathic Pulmonary Fibrosis (IPF) is a kind of Interstitial Lung Disease (ILD) that can be recognized by observing an atypical formation and accumulation of fibrotic tissue in the lungs. The lung's alveolar structure is damaged; as a result, people afflicted with IPF experience increasingly restricted lung capacity as time progresses. Diagnosis of this disease is typically performed by analyzing the patient's computed tomography (CT) scans and measuring their Forced Vital Capacity (FVC) using a Spirometer. However, the absence of an apparent cause of IPF restricts the ability of doctors to accurately diagnose the patient. Furthermore, IPF progression in patients is highly volatile and unpredictable, which means that one patient's health could deteriorate significantly quicker compared to another. Taking the problems mentioned above into account, in this paper a 3-layer ResNet machine learning model is proposed that determines the rate of lung function decline of sufferers from IPF. Proposed model is applied on the “OSIC Pulmonary Fibrosis Progression” dataset publicly available on Kaggle, and compare it against various state-of-the-art models and winning Kaggle entries.","PeriodicalId":112926,"journal":{"name":"Proceedings of the 4th International Conference on Information Management & Machine Intelligence","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116925146","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":"Protecting customer databases to shield business data against ransomware attacks and effective disaster recovery in a hybrid production environment","authors":"M. Singhal","doi":"10.1145/3590837.3590927","DOIUrl":"https://doi.org/10.1145/3590837.3590927","url":null,"abstract":"Backup and recovery are the processes of making copies of data and storing it securely for V. Chang and G. Wills, “A model to compare cloud and non-cloud storage of big data, Future Gener,” Future Gener. Compute. Syst. Int recovery in case the original data gets damaged or lost due to computer or storage system failures. During recovery, the data is restored to its operating location from the backup copy, so it can once again be used in business operations. In order to safeguard against ransomware risk, these backup copies should be immutable, which means once written to the storage these copies cannot be modified. The category of onsite and cloud-based technology solutions known as ‘backup and recovery’ also automates and supports this process, enabling business firms to safeguard their data and keep it for operational and regulatory requirements. Multiple backup solutions are available to protect a database running in a production environment. Customers can choose a specific or hybrid solution based on the deployment and requirements. For example, databases running in a virtual environment on a hypervisor in a data center may have a different solution than a database running on bare metal servers. Each method has its own benefits and limitations. The goal of this paper is to discuss the different solutions available for backup and recovery and come up with a proposal for effective backup and disaster recovery solutions in the event of any system failures.","PeriodicalId":112926,"journal":{"name":"Proceedings of the 4th International Conference on Information Management & Machine Intelligence","volume":"280 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122468279","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":"Global and Indian Perspectives on Russia-Ukraine War using Sentiment Analysis","authors":"Harshrim Pardal, Komal Nagarajan, T. Mahara, Helen Josephine V L","doi":"10.1145/3590837.3590876","DOIUrl":"https://doi.org/10.1145/3590837.3590876","url":null,"abstract":"In today's world, social media has become a platform through which people express their opinions and thoughts regarding various topics. Twitter is one such platform wherein people resort to expressing their opinions or portraying sentiments to the world. Today it has become easier to analyze mass opinion by using sentiment analysis. This paper investigates the ongoing Russia-Ukraine war by analyzing opinionated tweets, and it seeks to understand the sentiments from a global and Indian perspective. Operation Ganga was carried out to evacuate Indian citizens from the war-hit region. Multinomial Naive Bayes classifier classified the tweets into positive, neutral, and negative categories. The paper employed NRCLex for emotion classification and aspect-based sentiment analysis to divide opinions into aspects and determine the sentiment associated with each element. For the study, 4,31,857 tweets were extracted, and the results of sentiment analysis depict that 44.09% users had negative sentiments followed by 33.378% users expressing positive sentiment and remaining 22.53% people were neutral in their tweets. Fear, anger and sadness were amongst the top emotions expressed in the negative tweets whereas the positive tweets expressed trust and anticipation that the war would end soon. Operation Ganga was carried out to evacuate Indian citizens from the war-hit region. An analysis was performed on 1542 tweets that were obtained for Operation Ganga. 74.5% of the users had positive sentiments about Operation Ganga, whereas 16.67% and 8.5% had negative and neutral sentiments respectively. The people trusted this evacuation process resulting in more positive sentiments. Fear of losing near and dear ones and fear of safety was the topmost concern for Indians and leadership was one of the topmost aspects tweeted in the positive sentiments. Thus, the overall results depict that the common man does not prefer war and is fearful of the outcomes. The government should hear the voice of the common man and plan strategies and decisions considering the common man's sentiments.","PeriodicalId":112926,"journal":{"name":"Proceedings of the 4th International Conference on Information Management & Machine Intelligence","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121491898","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}