Pub Date : 2023-08-07DOI: 10.59544/uaae7050/ngcesi23p88
Brenda G., Franklin Jino R. E., Sherin Paul P
Fire detection using computer vision techniques and image processing mainly considered for rescuing operation. Indeed, good accuracy of computer vision techniques can outperform traditional models of fire detection. Computer vision techniques are being replaced by deep learning models such as Convolutional Neural Networks (CNN). Existing System has only been assessed on balanced datasets, which can lead to the unsatisfied results and mislead real-world performance as fire is a rare and abnormal real-life event. Also, the result of traditional CNN shows that its performance is very low, when evaluated on imbalanced datasets. Therefore, this proposed system use of transfer learning that is based on deep CNN approach to detect fire. It uses pre-trained deep CNN architecture namely VGG, and Mobile Net for development of fire detection system. These deep CNN models are tested on imbalanced datasets by considering real world scenarios. The results of deep CNNs models show that these models increase accuracy significantly and it is observed that deep CNNs models are completely outperforming traditional Convolutional Neural Networks model. The accuracy of Mobile Net is roughly the same as VGG Net, however, Mobile Net is smaller in size and faster than VGG
{"title":"An Efficient Technique for Fire Detection Using Deep Learning Algorithm","authors":"Brenda G., Franklin Jino R. E., Sherin Paul P","doi":"10.59544/uaae7050/ngcesi23p88","DOIUrl":"https://doi.org/10.59544/uaae7050/ngcesi23p88","url":null,"abstract":"Fire detection using computer vision techniques and image processing mainly considered for rescuing operation. Indeed, good accuracy of computer vision techniques can outperform traditional models of fire detection. Computer vision techniques are being replaced by deep learning models such as Convolutional Neural Networks (CNN). Existing System has only been assessed on balanced datasets, which can lead to the unsatisfied results and mislead real-world performance as fire is a rare and abnormal real-life event. Also, the result of traditional CNN shows that its performance is very low, when evaluated on imbalanced datasets. Therefore, this proposed system use of transfer learning that is based on deep CNN approach to detect fire. It uses pre-trained deep CNN architecture namely VGG, and Mobile Net for development of fire detection system. These deep CNN models are tested on imbalanced datasets by considering real world scenarios. The results of deep CNNs models show that these models increase accuracy significantly and it is observed that deep CNNs models are completely outperforming traditional Convolutional Neural Networks model. The accuracy of Mobile Net is roughly the same as VGG Net, however, Mobile Net is smaller in size and faster than VGG","PeriodicalId":315694,"journal":{"name":"The International Conference on scientific innovations in Science, Technology, and Management","volume":"197 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116108193","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 : 2023-08-07DOI: 10.59544/fnob9186/ngcesi23p91
Catherine Bimla J, Sindhuja S. N, Christina Jane .I
Having diseases is quite natural in crops due to changing climatic and environmental conditions. Diseases affect the growth and produce of the crops and often difficult to control. To ensure good quality and high production, it is necessary to have accurate disease diagnosis and control actions to prevent them in time. Grape which is widely grown crop in India and it may be affected by different types of diseases on leaf, stem and fruit. Leaf diseases which are the early symptoms caused due to fungi, bacteria and virus. So, there is a need to have an automatic system that can be used to detect the type of diseases and to take appropriate actions. This project proposes an automatic system for detecting the disease in the grape leaf using convolutional neural network. The CNN classified image is fed to the image processing operation. In image processing operation block Gaussian filter is used. The fuzzy inference system segments the processed image using Fuzzy c-means segmentation. A healthy leaf percentage are discovered using the fuzzy inference approach. This project is implemented with MATLAB simulation software and the output reveals the healthy percentage.
{"title":"Detection of Grape Leaf Diseases Using a Traditional Neural Network","authors":"Catherine Bimla J, Sindhuja S. N, Christina Jane .I","doi":"10.59544/fnob9186/ngcesi23p91","DOIUrl":"https://doi.org/10.59544/fnob9186/ngcesi23p91","url":null,"abstract":"Having diseases is quite natural in crops due to changing climatic and environmental conditions. Diseases affect the growth and produce of the crops and often difficult to control. To ensure good quality and high production, it is necessary to have accurate disease diagnosis and control actions to prevent them in time. Grape which is widely grown crop in India and it may be affected by different types of diseases on leaf, stem and fruit. Leaf diseases which are the early symptoms caused due to fungi, bacteria and virus. So, there is a need to have an automatic system that can be used to detect the type of diseases and to take appropriate actions. This project proposes an automatic system for detecting the disease in the grape leaf using convolutional neural network. The CNN classified image is fed to the image processing operation. In image processing operation block Gaussian filter is used. The fuzzy inference system segments the processed image using Fuzzy c-means segmentation. A healthy leaf percentage are discovered using the fuzzy inference approach. This project is implemented with MATLAB simulation software and the output reveals the healthy percentage.","PeriodicalId":315694,"journal":{"name":"The International Conference on scientific innovations in Science, Technology, and Management","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124118922","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 : 2023-08-07DOI: 10.59544/qvbw1742/ngcesi23p104
Thanvin. Mohammed, Subitha Mary
The paper aims to fill a void created by the absence of proper materials management on construction sites. Research has shown that construction materials accounts for 50-60% of the total cost in construction projects. For a productive and cost efficiency, material management is very essential. Material mismanagement decrease the contractor’s profit leading to huge losses, and leaving the project in big troubles, therefore the proper management of this single largest component can improve the productivity and cost efficiency of a project and help ensure its timely completion. The existing construction material management practices of contracting companies are investigated in this paper. The study was exclusively assessed through questionnaire survey, interviews, field visits and discussion with the concerned authorities. 26 factors were selected for the proper assessment of most critical factors. The population for this research was all ongoing building construction project sites in Trivandrum and purposive sampling techniques were used. To achieve these research objectives questionnaire survey and interviews were used to collect relevant data from contractors, consultants and client representatives on-site. A total of 45 valid questionnaire survey was returned 31(83.78%) from contractors, 9(81.82%) from consultants and 5(62.50%) from clients. So that, based on the respondent’s agreement the relative importance index (RII) value and percentage were used to rank and explain their agreement by using Microsoft excel.
{"title":"Assessment of Impact on Project Cost and Schedule Due to Material Mismanagement in Trivandrum","authors":"Thanvin. Mohammed, Subitha Mary","doi":"10.59544/qvbw1742/ngcesi23p104","DOIUrl":"https://doi.org/10.59544/qvbw1742/ngcesi23p104","url":null,"abstract":"The paper aims to fill a void created by the absence of proper materials management on construction sites. Research has shown that construction materials accounts for 50-60% of the total cost in construction projects. For a productive and cost efficiency, material management is very essential. Material mismanagement decrease the contractor’s profit leading to huge losses, and leaving the project in big troubles, therefore the proper management of this single largest component can improve the productivity and cost efficiency of a project and help ensure its timely completion. The existing construction material management practices of contracting companies are investigated in this paper. The study was exclusively assessed through questionnaire survey, interviews, field visits and discussion with the concerned authorities. 26 factors were selected for the proper assessment of most critical factors. The population for this research was all ongoing building construction project sites in Trivandrum and purposive sampling techniques were used. To achieve these research objectives questionnaire survey and interviews were used to collect relevant data from contractors, consultants and client representatives on-site. A total of 45 valid questionnaire survey was returned 31(83.78%) from contractors, 9(81.82%) from consultants and 5(62.50%) from clients. So that, based on the respondent’s agreement the relative importance index (RII) value and percentage were used to rank and explain their agreement by using Microsoft excel.","PeriodicalId":315694,"journal":{"name":"The International Conference on scientific innovations in Science, Technology, and Management","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134061952","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 : 2023-08-07DOI: 10.59544/bagd8150/ngcesi23p73
Saji Lekshman K. L
Concrete bleeding in bored pile scan cause substantial defects such as channelling or air pockets in pile shaft of diaphragm walls. The repair of such damage can be costly and time consuming. The mechanism of concrete bleeding in bored piles and diaphragm walls is well known among construction professionals, but there a sons how concrete bleeding occurs remain insufficiently understood to date. This paper introduces a potential model to explain the fundamental mechanism of concrete bleeding or channelling in deep foundations (e.g. concrete bored piles or diaphragm walls). The model is based on a well-established theory from the disciplines of soil mechanics and geotechnical engineering. The transfer of knowledge from the discipline of geotechnical engineering to another (concrete technology) assumes that fresh concrete is a three-phase system consisting of aggregate (gravel and sand), fluid (cement paste and excess design water) and air. The application of external pressure on to fresh concrete inside a deep foundation due to self-weight of the fresh concrete column causes the redistribution of pore-water pressure, resulting in a reduction of void space inside the aggregate matrix. This change in aggregate density is likely to cause concrete bleeding if potential drainage paths exist inside the fresh concrete matrix. Such drainage paths will provide ‘escape routes’ to release the excess pore-water pressure (water or cement paste) to the surface of the pile by forming bleeding channels or voids inside the hardened concrete. The existence of potential drainage paths, the lack of fines in the fresh concrete matrix in combination within sufficient aggregate grading and the addition of too much design water (above the optimal water content for a given aggregate combination) have been identified as key factors contributing to concrete bleeding and channelling in deep foundations (e.g. bored piles and diaphragm walls).
{"title":"Fundamental Mechanisms of Concrete Bleeding in Bored Piles","authors":"Saji Lekshman K. L","doi":"10.59544/bagd8150/ngcesi23p73","DOIUrl":"https://doi.org/10.59544/bagd8150/ngcesi23p73","url":null,"abstract":"Concrete bleeding in bored pile scan cause substantial defects such as channelling or air pockets in pile shaft of diaphragm walls. The repair of such damage can be costly and time consuming. The mechanism of concrete bleeding in bored piles and diaphragm walls is well known among construction professionals, but there a sons how concrete bleeding occurs remain insufficiently understood to date. This paper introduces a potential model to explain the fundamental mechanism of concrete bleeding or channelling in deep foundations (e.g. concrete bored piles or diaphragm walls). The model is based on a well-established theory from the disciplines of soil mechanics and geotechnical engineering. The transfer of knowledge from the discipline of geotechnical engineering to another (concrete technology) assumes that fresh concrete is a three-phase system consisting of aggregate (gravel and sand), fluid (cement paste and excess design water) and air. The application of external pressure on to fresh concrete inside a deep foundation due to self-weight of the fresh concrete column causes the redistribution of pore-water pressure, resulting in a reduction of void space inside the aggregate matrix. This change in aggregate density is likely to cause concrete bleeding if potential drainage paths exist inside the fresh concrete matrix. Such drainage paths will provide ‘escape routes’ to release the excess pore-water pressure (water or cement paste) to the surface of the pile by forming bleeding channels or voids inside the hardened concrete. The existence of potential drainage paths, the lack of fines in the fresh concrete matrix in combination within sufficient aggregate grading and the addition of too much design water (above the optimal water content for a given aggregate combination) have been identified as key factors contributing to concrete bleeding and channelling in deep foundations (e.g. bored piles and diaphragm walls).","PeriodicalId":315694,"journal":{"name":"The International Conference on scientific innovations in Science, Technology, and Management","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127749312","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 : 2023-08-07DOI: 10.59544/lfrz9442/ngcesi23p67
Nithya M. S
Concrete is an important construction material consisting of cement, sand and aggregate such as gravel or crushed rock, mixed with water. The most commonly used cement is Portland cement. The cement and water form a paste or gel which coast the sand and aggregate. When the cement has chemically reacted with the water, it hardens and binds the whole mix together; Fine and coarse aggregate make up the bulk of a concrete mixture. Manufactured sand is an alternative for river sand. Due to fast growing construction industry, the demand for sand has increased tremendously; causing deficiency of suitable river sand is most part of the word. Plain cement concrete is good at providing reasonable compressive strength but it tends to be brittle is nature and is weak in tensile strength and minimum resistance to cracking, poor toughness to overcome the concrete. In the present study of Hempfibre are used with conventional concrete. The combining of fibre s, often called hybridization. There is a growing awareness of the advantages of the advantages of fibre reinforcement techniques of construction all over the world. In the recent time there is a growing interest on the use of various type of fibre in structural applications. Experimental and analysis of results were conducted to study the compressive, tensile and flexural behavior of composite concrete with varying percentage of fibres added to it. The M20 grade of concrete is adopted with varying percentage of fibres ranging from 0.2%, 0.4%, 0.6%, and 0.8% on different characteristic of fibre are used in all construction.
{"title":"Experimental Investigation on Hempcrete","authors":"Nithya M. S","doi":"10.59544/lfrz9442/ngcesi23p67","DOIUrl":"https://doi.org/10.59544/lfrz9442/ngcesi23p67","url":null,"abstract":"Concrete is an important construction material consisting of cement, sand and aggregate such as gravel or crushed rock, mixed with water. The most commonly used cement is Portland cement. The cement and water form a paste or gel which coast the sand and aggregate. When the cement has chemically reacted with the water, it hardens and binds the whole mix together; Fine and coarse aggregate make up the bulk of a concrete mixture. Manufactured sand is an alternative for river sand. Due to fast growing construction industry, the demand for sand has increased tremendously; causing deficiency of suitable river sand is most part of the word. Plain cement concrete is good at providing reasonable compressive strength but it tends to be brittle is nature and is weak in tensile strength and minimum resistance to cracking, poor toughness to overcome the concrete. In the present study of Hempfibre are used with conventional concrete. The combining of fibre s, often called hybridization. There is a growing awareness of the advantages of the advantages of fibre reinforcement techniques of construction all over the world. In the recent time there is a growing interest on the use of various type of fibre in structural applications. Experimental and analysis of results were conducted to study the compressive, tensile and flexural behavior of composite concrete with varying percentage of fibres added to it. The M20 grade of concrete is adopted with varying percentage of fibres ranging from 0.2%, 0.4%, 0.6%, and 0.8% on different characteristic of fibre are used in all construction.","PeriodicalId":315694,"journal":{"name":"The International Conference on scientific innovations in Science, Technology, and Management","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133495605","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 : 2023-08-07DOI: 10.59544/wkyj3792/ngcesi23p105
Sreejith B., Sreeja V.
Agile methodology is a type of project management process, mainly used for software development, where demands and solutions evolve through the collaborative effort of self-functional teams and their customers. During the past few decades, fundamental changes have taken place in project development, planning, and execution. This has taken from with embracing new techniques such as various agile project management, instead of using the traditional waterfall project management. . It is mainly suitable for complex project, where there is delay in construction projects & final deliverable in advance. Construction delays are a common phenomenon in civil engineering projects. There are many reasons to delay in construction as pre-design, design and execution phase. It leads to time overrun in the construction work. Completion of construction projects on time seems to be challenging tasks in large-scale construction. It has been observed that about 90% of government infrastructure projects fail to achieve on time completion in India. Time is a major factor in construction and on time completion will bring about many benefits to the client, contractor and the society. This thesis paper will discuss and finding out the reasons for delay in two different construction project and apply agile management methodology where the delay is identified in this construction works. Also will prove the scope of agile management in construction industry in future.
{"title":"The Construction Agile Managements of Different Infrastructure Projects","authors":"Sreejith B., Sreeja V.","doi":"10.59544/wkyj3792/ngcesi23p105","DOIUrl":"https://doi.org/10.59544/wkyj3792/ngcesi23p105","url":null,"abstract":"Agile methodology is a type of project management process, mainly used for software development, where demands and solutions evolve through the collaborative effort of self-functional teams and their customers. During the past few decades, fundamental changes have taken place in project development, planning, and execution. This has taken from with embracing new techniques such as various agile project management, instead of using the traditional waterfall project management. . It is mainly suitable for complex project, where there is delay in construction projects & final deliverable in advance. Construction delays are a common phenomenon in civil engineering projects. There are many reasons to delay in construction as pre-design, design and execution phase. It leads to time overrun in the construction work. Completion of construction projects on time seems to be challenging tasks in large-scale construction. It has been observed that about 90% of government infrastructure projects fail to achieve on time completion in India. Time is a major factor in construction and on time completion will bring about many benefits to the client, contractor and the society. This thesis paper will discuss and finding out the reasons for delay in two different construction project and apply agile management methodology where the delay is identified in this construction works. Also will prove the scope of agile management in construction industry in future.","PeriodicalId":315694,"journal":{"name":"The International Conference on scientific innovations in Science, Technology, and Management","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133994595","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 : 2023-08-07DOI: 10.59544/ecfa6325/ngcesi23p90
Jasmin S, Benschwartz R
Fruit and vegetable identification and classification system is always necessary and advantageous for the agriculture business, the food processing sector, as well as the convenience shops and hypermarkets where these products are sold. Therefore, it is necessary to build an effective automated tool to meet the needs of the market by boosting the outcome, in order to improve economic efficiency. In this paper, a two-stage model is proposed to recognize fruits using camera images. Fruit disease recognition plays a crucial role in ensuring the quality and yield of fruits in agriculture. The framework for fruit disease recognition using a combination of VGG16 feature extraction, APGWO and CNN classification.VGG16 is a deep convolutional neural network known for its excellent feature extraction capabilities. APGWO adaptively adjusts the parameters to enhance the search efficiency and accuracy of feature selection. In this study, Adaptive particle – Grey Wolf Optimization (APGWO) has been applied for choosing the most pertinent features.
{"title":"Enhancing Fruit Disease Recognition Using Deep Learning Model","authors":"Jasmin S, Benschwartz R","doi":"10.59544/ecfa6325/ngcesi23p90","DOIUrl":"https://doi.org/10.59544/ecfa6325/ngcesi23p90","url":null,"abstract":"Fruit and vegetable identification and classification system is always necessary and advantageous for the agriculture business, the food processing sector, as well as the convenience shops and hypermarkets where these products are sold. Therefore, it is necessary to build an effective automated tool to meet the needs of the market by boosting the outcome, in order to improve economic efficiency. In this paper, a two-stage model is proposed to recognize fruits using camera images. Fruit disease recognition plays a crucial role in ensuring the quality and yield of fruits in agriculture. The framework for fruit disease recognition using a combination of VGG16 feature extraction, APGWO and CNN classification.VGG16 is a deep convolutional neural network known for its excellent feature extraction capabilities. APGWO adaptively adjusts the parameters to enhance the search efficiency and accuracy of feature selection. In this study, Adaptive particle – Grey Wolf Optimization (APGWO) has been applied for choosing the most pertinent features.","PeriodicalId":315694,"journal":{"name":"The International Conference on scientific innovations in Science, Technology, and Management","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116314378","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 : 2023-08-07DOI: 10.59544/gjmb2606/ngcesi23p95
Arun Kumar R. E, Amutha S.
Finite field arithmetic is becoming increasingly a very prominent solution for calculations in many applications. In this paper, complexity and delay of six different multipliers (Mastrovito multiplier, Paar-Roelse multiplier, Massey- Omura multiplier, Hasan-Masoleh multiplier, Berlekamp multiplier and Karatsuba multiplier) are compared. Also this paper presents a modified multiplier based on Karatsuba multiplication algorithm. To optimize the Karatsuba multiplication algorithm, the product terms are splited into two alternative forms and all the terms are expressed in the repeated fashion. This Modified architecture saves the 14.9% computation time and it consumes 45.5% less slices than existing Karatsuba multiplier. The proposed architecture has been simulated and synthesized by Xilinx ISE design suite for Spartan & Vertex device family. The new architecture is Simple & easy. The proposed Modified Karatsuba Multiplier (MKM) is also applied to compute the circular convolution for DSP application. In Spartan3E FPGA device family, computation of 8-bit circular convolution using Modified Karatsuba Algorithm (MKA) is 26.5% faster than Karatsuba Algorithm (KA). It also consumes 61.7% less slices than existing KA based Convolution.
{"title":"An Efficient of High-Speed and High precision Overlap-Free Karatsuba-Based Finite-Field Multiplier for FGPA Implementation","authors":"Arun Kumar R. E, Amutha S.","doi":"10.59544/gjmb2606/ngcesi23p95","DOIUrl":"https://doi.org/10.59544/gjmb2606/ngcesi23p95","url":null,"abstract":"Finite field arithmetic is becoming increasingly a very prominent solution for calculations in many applications. In this paper, complexity and delay of six different multipliers (Mastrovito multiplier, Paar-Roelse multiplier, Massey- Omura multiplier, Hasan-Masoleh multiplier, Berlekamp multiplier and Karatsuba multiplier) are compared. Also this paper presents a modified multiplier based on Karatsuba multiplication algorithm. To optimize the Karatsuba multiplication algorithm, the product terms are splited into two alternative forms and all the terms are expressed in the repeated fashion. This Modified architecture saves the 14.9% computation time and it consumes 45.5% less slices than existing Karatsuba multiplier. The proposed architecture has been simulated and synthesized by Xilinx ISE design suite for Spartan & Vertex device family. The new architecture is Simple & easy. The proposed Modified Karatsuba Multiplier (MKM) is also applied to compute the circular convolution for DSP application. In Spartan3E FPGA device family, computation of 8-bit circular convolution using Modified Karatsuba Algorithm (MKA) is 26.5% faster than Karatsuba Algorithm (KA). It also consumes 61.7% less slices than existing KA based Convolution.","PeriodicalId":315694,"journal":{"name":"The International Conference on scientific innovations in Science, Technology, and Management","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125577678","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 : 2023-08-07DOI: 10.59544/qkfn6548/ngcesi23p93
Sujini S. P, AnbuShamini G. N, Prija J. S
Early detection of network intrusions is a very important factor in network security. However, most studies of network intrusion detection systems utilize features for full sessions, making it difficult to detect intrusions before a session ends. To solve this problem, the proposed method uses packet data for features to determine if packets are malicious traffic. Such an approach inevitably increases the probability of falsely detecting normal packets as an intrusion or an intrusion as normal traffic for the initial session. As a solution, the proposed method learns the patterns of packets that are unhelpful in order to classify network intrusions and benign sessions. To this end, a new training dataset for Generative Adversarial Network (GAN) is created using misclassified data from an original training dataset by the LSTM-DNN model trained using the original one. The GAN trained with this dataset has ability to determine whether the currently received packet can be accurately classified in the LSTM-DNN. If the GAN determines that the packet cannot be classified correctly, the detection process is canceled and will be tried again when the next packet is received. Meticulously designed classification algorithm based on LSTM-DNN and validation model using GAN enable the proposed algorithm to accurately perform network intrusion detection in real time without session termination or delay time for collecting a certain number of packets. Additionally, a Deep Autoencoder neural network is utilized to automatically extract relevant features from the network traffic. This unsupervised learning approach enables the system to adapt to evolving attack patterns.
{"title":"Deep Intrusion Detection for DOS and DDOS Attacks Using LSTM and Deep Autoencoder Neural Network","authors":"Sujini S. P, AnbuShamini G. N, Prija J. S","doi":"10.59544/qkfn6548/ngcesi23p93","DOIUrl":"https://doi.org/10.59544/qkfn6548/ngcesi23p93","url":null,"abstract":"Early detection of network intrusions is a very important factor in network security. However, most studies of network intrusion detection systems utilize features for full sessions, making it difficult to detect intrusions before a session ends. To solve this problem, the proposed method uses packet data for features to determine if packets are malicious traffic. Such an approach inevitably increases the probability of falsely detecting normal packets as an intrusion or an intrusion as normal traffic for the initial session. As a solution, the proposed method learns the patterns of packets that are unhelpful in order to classify network intrusions and benign sessions. To this end, a new training dataset for Generative Adversarial Network (GAN) is created using misclassified data from an original training dataset by the LSTM-DNN model trained using the original one. The GAN trained with this dataset has ability to determine whether the currently received packet can be accurately classified in the LSTM-DNN. If the GAN determines that the packet cannot be classified correctly, the detection process is canceled and will be tried again when the next packet is received. Meticulously designed classification algorithm based on LSTM-DNN and validation model using GAN enable the proposed algorithm to accurately perform network intrusion detection in real time without session termination or delay time for collecting a certain number of packets. Additionally, a Deep Autoencoder neural network is utilized to automatically extract relevant features from the network traffic. This unsupervised learning approach enables the system to adapt to evolving attack patterns.","PeriodicalId":315694,"journal":{"name":"The International Conference on scientific innovations in Science, Technology, and Management","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123254573","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 : 2023-08-07DOI: 10.59544/arto9883/ngcesi23p86
Anna Palagan C., Praveen B. M.
Now a day by the initiative taken by the Government of India in the scheme of “Smart India”, all villages will soon transfer to Smart Villages. This will be achieved by the Information Technology Platforms. For converting the Villages to Smart Villages, the Internet of Things (IoT) plays a major Role in India. By using IoT everything in the village is connected to the Internet and it is controlled by the users anywhere by remotely. In our project we have taken the problems in Smart Garbage System and Smart Water Level Controller to distribute water from the common tank to all users. In Garbage System the wet and dry waste is identified separately and it regularly monitored whether the tank is full, then information given to municipality to clean that concern Garbage. In water level controller the utilization of water from common tank is controlled and managed by using the mobile application. Keep tracking of water level in the tank by float sensor and based on the water level it will be distributed to the users. The domestic public users also controlled by the user defined commands which is intercepted with the home of particular user.
{"title":"Smart Village – A Digital Transformation of Modern Village Using ESP32 Microcontroller","authors":"Anna Palagan C., Praveen B. M.","doi":"10.59544/arto9883/ngcesi23p86","DOIUrl":"https://doi.org/10.59544/arto9883/ngcesi23p86","url":null,"abstract":"Now a day by the initiative taken by the Government of India in the scheme of “Smart India”, all villages will soon transfer to Smart Villages. This will be achieved by the Information Technology Platforms. For converting the Villages to Smart Villages, the Internet of Things (IoT) plays a major Role in India. By using IoT everything in the village is connected to the Internet and it is controlled by the users anywhere by remotely. In our project we have taken the problems in Smart Garbage System and Smart Water Level Controller to distribute water from the common tank to all users. In Garbage System the wet and dry waste is identified separately and it regularly monitored whether the tank is full, then information given to municipality to clean that concern Garbage. In water level controller the utilization of water from common tank is controlled and managed by using the mobile application. Keep tracking of water level in the tank by float sensor and based on the water level it will be distributed to the users. The domestic public users also controlled by the user defined commands which is intercepted with the home of particular user.","PeriodicalId":315694,"journal":{"name":"The International Conference on scientific innovations in Science, Technology, and Management","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129563441","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：