{"title":"Design and Evaluation of GAN based Regression Model","authors":"A. Jain, Anusree H, M. J","doi":"10.1109/ICONAT53423.2022.9726040","DOIUrl":"https://doi.org/10.1109/ICONAT53423.2022.9726040","url":null,"abstract":"Generative Adversarial Networks (GANs) are capable of generating realistic photos of objects, scenes and people that do not exist in real life. This is made possible due to the successful ability of GANs in modeling high dimensional data, handling missing data, providing multi-modal outputs and multi plausible answers. These positive features and capabilities of GANs have spearheaded research in the area of visual modeling using GAN. In this paper, an attempt is made to design a GAN model for solving regression problems. In order to assess the performance evaluation of proposed GAN model for regression problem, four basic functions and seven datasets from standard repositories are employed. It is observed that the proposed GAN model gave satisfactory results and can be employed for various other regression problems too.","PeriodicalId":377501,"journal":{"name":"2022 International Conference for Advancement in Technology (ICONAT)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122287228","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}
P. Yadlapalli, A. L. Teja, C. M. A. Raju, K. Reddy, Krishna Mithra, Bhavana Dokku
{"title":"Segmentation of Pulmonary Embolism Using Deep Learning","authors":"P. Yadlapalli, A. L. Teja, C. M. A. Raju, K. Reddy, Krishna Mithra, Bhavana Dokku","doi":"10.1109/ICONAT53423.2022.9726048","DOIUrl":"https://doi.org/10.1109/ICONAT53423.2022.9726048","url":null,"abstract":"Pulmonary Embolism (PE) is a condition that necessitates immediate medical attention. A doctor's examination is usually used to determine the severity of PE (Pulmonary Embolism), which takes time and can result in death. A deep learning-based methodology for detecting pulmonary embolism in CT scans is suggested in this study. Deep learning algorithms are widely employed in medical imaging for improved picture interpretation because instead of requiring a set of pre-programmed instructions, computers may autonomously learn representations from massive amounts of data [1]. They can assist doctors in making rapid diagnoses, saving time and effort in the process. Deep learning algorithms use a predetermined logical structure to analyze data and come to similar conclusions as humans. Deep learning achieves this through the use of neural networks, which are multi-layered algorithms. Some of the data pre-processing that is customary in machine learning is eliminated with deep learning.","PeriodicalId":377501,"journal":{"name":"2022 International Conference for Advancement in Technology (ICONAT)","volume":"209 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127034749","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":"Disease Predictor Using Random Forest Classifier","authors":"Swatik Paul, Pinku Ranjan, Somesh Kumar, Arun Kumar","doi":"10.1109/ICONAT53423.2022.9726023","DOIUrl":"https://doi.org/10.1109/ICONAT53423.2022.9726023","url":null,"abstract":"In this paper, a disease prediction system has been designed that takes the symptoms entered by an individual as input and shows the predicted output i.e. the most probable disease to them. Random Forest Classifier algorithm is being used in the backend for prediction purposes. The dataset that is being used consists of 132 symptoms that are linked to 41 diseases. In addition, the system could also suggest precautions and medicines to the user based on their disease. This can minimize the efforts and time invested by the doctors and patients by automatizing the process.","PeriodicalId":377501,"journal":{"name":"2022 International Conference for Advancement in Technology (ICONAT)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125412795","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":"Grey Wolf Optimization Inspired Maximum Power Extraction from SPV System for Water Pumping Application","authors":"Astitva Kumar, M. Bilal, M. Rizwan, U. Nangia","doi":"10.1109/ICONAT53423.2022.9726028","DOIUrl":"https://doi.org/10.1109/ICONAT53423.2022.9726028","url":null,"abstract":"The use of renewable energy resources is increasing to provide energy efficient and uninterrupted supply of power. The use of solar photovoltaics (SPV) in the agriculture sector is gaining importance due to its availability in abundance and other advantages. This paper presents SPV based water pumping system (WPS) for rural agricultural practice in Indian scenario. The proposed water pumping system comprises of SPV system, maximum power point controller, boost converter, inverter, and 3-Φ induction motor driving a water pump. The stochastic nature of SPV power is a concern for electrical engineers. Thus, the use of maximum power point tracking (MPPT) algorithms is of key focus to improve the efficiency and ensure the robust performance of SPV system. The proposed SPV system incorporates an artificial intelligence method for designing MPPT algorithm. The paper introduces a grey wolf optimization inspired algorithm to extract the maximum power under varying irradiance conditions from SPV system. The performance of the proposed algorithm is compared with other algorithms for partially shaded conditions on the basis of computational burden, maximum power tracked, and fluctuations. The proposed controller is better with least rise time of 0.11 s, and 0% error in tracking the power.","PeriodicalId":377501,"journal":{"name":"2022 International Conference for Advancement in Technology (ICONAT)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127937645","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}
H. C. Reddy, Vajjala Veera Karthik, Dedeepya V, A. Pavan, Sarasvathi V
{"title":"Data Storage on Cloud using Split-Merge and Hybrid Cryptographic Techniques","authors":"H. C. Reddy, Vajjala Veera Karthik, Dedeepya V, A. Pavan, Sarasvathi V","doi":"10.1109/ICONAT53423.2022.9725841","DOIUrl":"https://doi.org/10.1109/ICONAT53423.2022.9725841","url":null,"abstract":"Data protection is the most important consideration when storing data in the cloud. We use hybrid cryptography to provide data protection in the cloud, while most current approaches use a single cryptography algorithm. As a result, we need a method that is both efficient and safe. In this paper, we employ hybrid cryptography, which makes use of existing cryptographic algorithms. We use cloud platform to promote the tremendous benefits of distributed computing in a variety of ways, from reducing enterprise sizes to lowering development costs. Organizations are most concerned about the security of their data. A single algorithm is used for data encryption and decryption in current systems, which may not be sufficient to achieve high security. A problem of stable key transmission and storage arises when using a public key cryptography algorithm. We use hybrid cryptography and file splitting for data protection. To data less accessible to attackers, components of the files are sorted on separate data.","PeriodicalId":377501,"journal":{"name":"2022 International Conference for Advancement in Technology (ICONAT)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128786945","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":"Template-based Identification of Malignant and Non-malignant Skin-lesions to Minimize Biopsy Load Using Saturation Counts (HSV space) and Absolute Dark Area parameters: Experiments on ISIC Images","authors":"R. S. Prasad, V. Prasad","doi":"10.1109/ICONAT53423.2022.9726047","DOIUrl":"https://doi.org/10.1109/ICONAT53423.2022.9726047","url":null,"abstract":"Malignant skin lesion is the deadliest skin disease resulting in huge loss of lives in Europe, Australia and USA. Early detection of malignant lesions can save lives. It is highly challenging to differentiate between malignant and non-malignant skin lesions. Many non-invasive techniques have been proposed but none has been accepted in clinical practice. Consequently, biopsy remains the only gold standard for diagnosis of malignant lesions. The objective of this study which uses two master templates (MT) of dermoscopic images for identification, an improvement over the recently reported subtraction technique using only a single MT, is to propose a non- invasive technique to minimize biopsy load to an appreciable extent. This study proposes selection of two MTs, one a known 100% malignant (M) lesion, and the other a known nearly 100% benign (B) lesion. For identification of test lesions either belonging to $M$ or B category, each test image from the publicly available ISIC archive is subtracted from each of the two MTs and the resulting pixels (RGB) data on each subtraction are converted into HSV space. Scatter plot showing Saturation (S) data counts against pixels locations below and above a trial-and-error-based threshold of 0.35, decides the B or M category of test lesions according to a rule defined for identification. The proposed method introduces, for the first time ever, use of double MTs subtraction technique, which amounts to the filter action. The proposed subtraction method has sound mathematical and logical base. On a preliminary trial over fifty images from publicly available ISIC archive, an overall high accuracy of 94% was achieved which promises clinical applications to minimize biopsy load to a great extent. The proposed method is easy to implement by non-experts and takes only fifteen minutes on average for diagnosis.","PeriodicalId":377501,"journal":{"name":"2022 International Conference for Advancement in Technology (ICONAT)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129015044","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":"Multiobjective Optimization of Economic-Environmental Dispatch (EED) Problems Including CO2 Emission","authors":"S. Bhattacharyya, Anusuya B","doi":"10.1109/ICONAT53423.2022.9725860","DOIUrl":"https://doi.org/10.1109/ICONAT53423.2022.9725860","url":null,"abstract":"This paper considers the EED problem of a generator system cluster wherein simultaneous quadruple-objective optimization of cost, NOx, SO2 and CO2 emissions is carried out for the first time. The CO2 data is rarely considered in such problems, due to lack of data for generator systems. However, its high concentration and the resultant global warming was deemed to be sufficiently important to include it specifically in the analysis. Further, Almost all studies consider EED optimization for a single value of load demand, rather than the entire load demand range. Here, three (cost, NOx and SO2 emissions) and four (cost and all three emissions) objective optimizations show two principal branches of the Pareto front in the cost-emission plane, a feature that was not revealed before. The paper also shows that by considering even a two-objective EED problem over the entire load demand range, one can rank the effectiveness of the generators over this range. This has been done by introducing a measure called ‘specific objective function’, which is the objective functions per unit power output. The solution of EED problem over the load demand range can readily be useful for generator scheduling of power system operations.","PeriodicalId":377501,"journal":{"name":"2022 International Conference for Advancement in Technology (ICONAT)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132772778","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":"Extraction of 5 Parameters of Single Diode Model with and without Optimisation Method Along With I-V And P-V Characteristics Behavior","authors":"Supriya R. Patil, R. Agrawal","doi":"10.1109/ICONAT53423.2022.9726046","DOIUrl":"https://doi.org/10.1109/ICONAT53423.2022.9726046","url":null,"abstract":"The whole globe is moving toward open, widely utilized, and easily maintained renewable energy sources. When we compare the greatest energy sources, models, and methodologies, we find that sun-fueled energy is the best. Because daylight-based energy may be employed, we'll need to switch to a technology that converts sunlight into electrical energy, such as photovoltaic (PV) cells or modules. This concept use mathematical exhibiting and a nearly similar circuit to understand known and unknown limitations. Conclusion This is the critical examination that focuses on the constraint of the PV cell or the module. In this paper, we worked on comparative methodologies which are used to extract the unknown parameters by using known manufacturing data of various PV cells or the modules such as photocurrent (Iph), diode saturation current (Is), diode ideality factor (A), series resistance (Rs), shunt resistance (Rush). Along with all of this procedure, we also study about differentiae behavior of PV models that is Current-Voltage, Power-Voltage features as far as differentiae manners.","PeriodicalId":377501,"journal":{"name":"2022 International Conference for Advancement in Technology (ICONAT)","volume":"163 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114918103","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}
P. Pitre, Arya Gandhi, Vaishnavi Konde, Rahul B. Adhao, V. Pachghare
{"title":"An Intrusion Detection System for Zero-Day Attacks to Reduce False Positive Rates","authors":"P. Pitre, Arya Gandhi, Vaishnavi Konde, Rahul B. Adhao, V. Pachghare","doi":"10.1109/ICONAT53423.2022.9726105","DOIUrl":"https://doi.org/10.1109/ICONAT53423.2022.9726105","url":null,"abstract":"The Intrusion Detection System (IDS) - is one that monitors network traffic to issue alerts about any suspicious activity on the network. Conventionally, there are two types of IDSs - Signature-Based, which efficiently detect already known attacks, and Anomaly-Based, where models are trained to detect unknown attacks. The latter type of IDS plays a crucial role in detecting zero-day attacks- a type of attack where the vulnerability of the software is exploited before a developer can take action on it. However, it comes with a few problems, like its high false-positive rates that cause the network to slow down and require constant human intervention and its inability to detect attacks in real-time. This paper analyzes state-of-the-art models that deal with this problem, analyzing their benefits and shortcomings. Further, we propose a framework for addressing these zero-day attacks and reducing their false positive rate of detection using a combination of feature selection methods and fine-tuning of the dataset specifically for false-positive detection. These methods will be tried with various optimizers and models several times, and their results will be compared. We attach results from preliminary testing on the novel idea of a subset of the dataset, with promising results to be applied to find the model that works better than most existing.","PeriodicalId":377501,"journal":{"name":"2022 International Conference for Advancement in Technology (ICONAT)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133519977","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}
V. Kiranmayee, Srishti Ranjan, J. Shreyansh, Shylesh Suresh, K. Ranjini
{"title":"Stratification of Breast Cancer in it's Preliminary Stages","authors":"V. Kiranmayee, Srishti Ranjan, J. Shreyansh, Shylesh Suresh, K. Ranjini","doi":"10.1109/ICONAT53423.2022.9726123","DOIUrl":"https://doi.org/10.1109/ICONAT53423.2022.9726123","url":null,"abstract":"Classifying breast cancer in its preliminary stages is done with the help of machine learning and the concept of Transfer Learning Algorithm. Here, the classification is done by labeling the tumor as benign or malignant. The machine learning algorithms are implemented by using the scikit library in which transfer learning is also available. The algorithm completely depends upon the dataset that's run through it and the accuracy of the same. To get the best result, the usage of a pre-trained model approach will bolster the rate of accuracy. Once the algorithm is run, the desired result would be the algorithm predicting if the tumor is benign or malignant so the patient can get the most optimal care.","PeriodicalId":377501,"journal":{"name":"2022 International Conference for Advancement in Technology (ICONAT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130993264","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}