Pub Date : 2021-05-30DOI: 10.35940/IJITEE.G8895.0510721
Nagesh* A.
the growth in population and economics the global demand for energy is increased considerably. The large amount of energy demand comes from houses. Because of this the energy efficiency in houses in considered most important aspect towards the global sustainability. The machine learning algorithms contributed heavily in predicting the amount of energy consumed in household level. In this paper, a energy audit system using machine learning are developed to estimate the amount of energy consumed at household level in order to identify probable areas to plug wastage of energy in household. Each energy audit system is trained using one machine leaning algorithm with previous power consumption history of training data. By converting this data into knowledge, gratification of analysis of energy consumption is attained. The performance of energy audit Linear Regression system is 82%, Decision Tree system is 86% and Random Forest 91% are predicted energy consumption and the performance of learning methods were evaluated based on the heir predictive accuracy, ease of learning and user friendly characteristics. The Random Forest energy audit system is superior when compare to other energy audit system.
{"title":"Energy Audit System for Households using Machine Learning","authors":"Nagesh* A.","doi":"10.35940/IJITEE.G8895.0510721","DOIUrl":"https://doi.org/10.35940/IJITEE.G8895.0510721","url":null,"abstract":"the growth in population and economics the global\u0000demand for energy is increased considerably. The large amount\u0000of energy demand comes from houses. Because of this the\u0000energy efficiency in houses in considered most important aspect\u0000towards the global sustainability. The machine learning\u0000algorithms contributed heavily in predicting the amount of\u0000energy consumed in household level. In this paper, a energy\u0000audit system using machine learning are developed to estimate\u0000the amount of energy consumed at household level in order to\u0000identify probable areas to plug wastage of energy in household.\u0000Each energy audit system is trained using one machine leaning\u0000algorithm with previous power consumption history of training\u0000data. By converting this data into knowledge, gratification of\u0000analysis of energy consumption is attained. The performance of\u0000energy audit Linear Regression system is 82%, Decision Tree\u0000system is 86% and Random Forest 91% are predicted energy\u0000consumption and the performance of learning methods were\u0000evaluated based on the heir predictive accuracy, ease of learning\u0000and user friendly characteristics. The Random Forest energy\u0000audit system is superior when compare to other energy audit\u0000system.","PeriodicalId":23601,"journal":{"name":"VOLUME-8 ISSUE-10, AUGUST 2019, REGULAR ISSUE","volume":"30 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74874782","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}
Pub Date : 2021-05-30DOI: 10.35940/IJITEE.G8951.0510721
Kartik Khariwal, Rishabh Gupta, Jatin P. Singh, Anshul Arora
With the increasing fame of Android OS over the past few years, the quantity of malware assaults on Android has additionally expanded. In the year 2018, around 28 million malicious applications were found on the Android platform and these malicious apps were capable of causing huge financial losses and information leakage. Such threats, caused due to these malicious apps, call for a proper detection system for Android malware. There exist some research works that aim to study static manifest components for malware detection. However, to the best of our knowledge, none of the previous research works have aimed to find the best set amongst different manifest file components for malware detection. In this work, we focus on identifying the best feature set from manifest file components (Permissions, Intents, Hardware Components, Activities, Services, Broadcast Receivers, and Content Providers) that could give better detection accuracy. We apply Information Gain to rank the manifest file components intending to find the best set of components that can better classify between malware applications and benign applications. We put forward a novel algorithm to find the best feature set by using various machine learning classifiers like SVM, XGBoost, and Random Forest along with deep learning techniques like classification using Neural networks. The experimental results highlight that the best set obtained from the proposed algorithm consisted of 25 features, i.e., 5 Permissions, 2 Intents, 9 Activities, 3 Content Providers, 4 Hardware Components, 1 Service, and 1 Broadcast Receiver. The SVM classifier gave the highest classification accuracy of 96.93% and an F1-Score of 0.97 with this best set of 25 features.
{"title":"R-MFDroid: Android Malware Detection using Ranked Manifest File Components","authors":"Kartik Khariwal, Rishabh Gupta, Jatin P. Singh, Anshul Arora","doi":"10.35940/IJITEE.G8951.0510721","DOIUrl":"https://doi.org/10.35940/IJITEE.G8951.0510721","url":null,"abstract":"With the increasing fame of Android OS over the past\u0000few years, the quantity of malware assaults on Android has\u0000additionally expanded. In the year 2018, around 28 million\u0000malicious applications were found on the Android platform and\u0000these malicious apps were capable of causing huge financial\u0000losses and information leakage. Such threats, caused due to these\u0000malicious apps, call for a proper detection system for Android\u0000malware. There exist some research works that aim to study static\u0000manifest components for malware detection. However, to the best\u0000of our knowledge, none of the previous research works have\u0000aimed to find the best set amongst different manifest file\u0000components for malware detection. In this work, we focus on\u0000identifying the best feature set from manifest file components\u0000(Permissions, Intents, Hardware Components, Activities, Services,\u0000Broadcast Receivers, and Content Providers) that could give better\u0000detection accuracy. We apply Information Gain to rank the\u0000manifest file components intending to find the best set of\u0000components that can better classify between malware applications\u0000and benign applications. We put forward a novel algorithm to find\u0000the best feature set by using various machine learning classifiers\u0000like SVM, XGBoost, and Random Forest along with deep learning\u0000techniques like classification using Neural networks. The\u0000experimental results highlight that the best set obtained from the\u0000proposed algorithm consisted of 25 features, i.e., 5 Permissions, 2\u0000Intents, 9 Activities, 3 Content Providers, 4 Hardware\u0000Components, 1 Service, and 1 Broadcast Receiver. The SVM\u0000classifier gave the highest classification accuracy of 96.93% and\u0000an F1-Score of 0.97 with this best set of 25 features.","PeriodicalId":23601,"journal":{"name":"VOLUME-8 ISSUE-10, AUGUST 2019, REGULAR ISSUE","volume":"29 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83502097","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}
Pub Date : 2021-05-30DOI: 10.35940/IJITEE.G8877.0510721
M. Shireesha, Yasser Mirza Baig, C. Sarita, Syed Rashid Iqbal, C. Wesley, N. Vaishnavi
Biomass is an important source of energy and fuel worldwide after coal, oil and natural gas. These fossil fuels do substantially more harm than renewable energy sources like biomass energy. Oil extracted from biomass is considered as an attractive option. In our project, we have specifically selected coconut shells as our feed as they are carbon-neutral, easy to store and abundantly available. Coconut shell also known as Cocos Nucifera shell in biological terms, once a discarded outer hardcover is now a product of great demand. Coconut shell charcoal is used as domestic and industrial fuel. This is obtained by various techniques. Initially, the shells are burned at high temperature and condensed to extract bio-oil using a series of unit operations and processes such as distillation, gas chromatography. These samples are then sent for analysis to compare them with the conventional fuel sources and then antimicrobial activity is examined. The medium-chain fatty acids in coconut oil have antimicrobial properties that can help protect against harmful microorganisms. Lauric acid and capric acid are known to have potent antimicrobial properties. Different bacterial cultures have been introduced later to test the ability of the oil to resist the harmful microorganisms and fungal cultures. Various analysis such as Infrared Spectroscopy, Gas-Mass Spectroscopy and Ultimate analysis are performed on the retrieved samples of oil extracted from the coconut shells. It is to be observed that the carbon content in the Cocos nucifera derived oil is less than the conventional diesel oil which makes it best for environmental uses.
{"title":"Bio-Oil Extraction from the Shells of Cocos Nucifera – A Source of Generating Renewable\u0000Energy and Its Analysis","authors":"M. Shireesha, Yasser Mirza Baig, C. Sarita, Syed Rashid Iqbal, C. Wesley, N. Vaishnavi","doi":"10.35940/IJITEE.G8877.0510721","DOIUrl":"https://doi.org/10.35940/IJITEE.G8877.0510721","url":null,"abstract":"Biomass is an important source of energy and fuel\u0000worldwide after coal, oil and natural gas. These fossil fuels do\u0000substantially more harm than renewable energy sources like\u0000biomass energy. Oil extracted from biomass is considered as an\u0000attractive option. In our project, we have specifically selected\u0000coconut shells as our feed as they are carbon-neutral, easy to\u0000store and abundantly available. Coconut shell also known as\u0000Cocos Nucifera shell in biological terms, once a discarded outer\u0000hardcover is now a product of great demand. Coconut shell\u0000charcoal is used as domestic and industrial fuel. This is obtained\u0000by various techniques. Initially, the shells are burned at high\u0000temperature and condensed to extract bio-oil using a series of\u0000unit operations and processes such as distillation, gas\u0000chromatography. These samples are then sent for analysis to\u0000compare them with the conventional fuel sources and then\u0000antimicrobial activity is examined. The medium-chain fatty acids\u0000in coconut oil have antimicrobial properties that can help protect\u0000against harmful microorganisms. Lauric acid and capric acid are\u0000known to have potent antimicrobial properties. Different\u0000bacterial cultures have been introduced later to test the ability of\u0000the oil to resist the harmful microorganisms and fungal cultures.\u0000Various analysis such as Infrared Spectroscopy, Gas-Mass\u0000Spectroscopy and Ultimate analysis are performed on the\u0000retrieved samples of oil extracted from the coconut shells. It is to\u0000be observed that the carbon content in the Cocos nucifera derived\u0000oil is less than the conventional diesel oil which makes it best for\u0000environmental uses.","PeriodicalId":23601,"journal":{"name":"VOLUME-8 ISSUE-10, AUGUST 2019, REGULAR ISSUE","volume":"5 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77183743","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}