Pub Date : 2023-03-31DOI: 10.47164/ijngc.v14i2.831
Tarun Kumar Ghosh, Krishna Gopal Dhal, Sanjoy Das
The cloud computing has emerged as a novel distributed computing system in past few years. It provides computation and resources over the Internet via dynamic provisioning of services. There are quite a few challenges and issues connected with implementation of cloud computing. This paper considers one of its major problems, i.e. task scheduling. The function of an efficient task scheduling algorithm is that it concentrates not only on attaining the requirements of the user but also in enhancing the efficiency of the cloud computing system. Cloud task scheduling is an NP-hard optimization problem, and many meta-heuristic algorithms have been proposed to solve it. This paper proposes a modified Penguins Search Optimization Algorithm (MPeSOA) for efficient cloud task scheduling. The main contribution of our work is to schedule all tasks to available virtual machines so that the makespan is minimized, resource utilization is increased and the degree of imbalance is reduced. The proposed scheduling algorithm was simulated using the CloudSim 4.0 simulator. Experimental results showed that the proposed MPeSOA outperformed three existing meta-heuristics, namely Penguins Search Optimization Algorithm (PeSOA), Genetic Algorithm (GA) and Particle Swarm Optimization (PSO).
{"title":"Cloud Task Scheduling Using Modified Penguins Search Optimization Algorithm","authors":"Tarun Kumar Ghosh, Krishna Gopal Dhal, Sanjoy Das","doi":"10.47164/ijngc.v14i2.831","DOIUrl":"https://doi.org/10.47164/ijngc.v14i2.831","url":null,"abstract":"The cloud computing has emerged as a novel distributed computing system in past few years. It provides computation and resources over the Internet via dynamic provisioning of services. There are quite a few challenges and issues connected with implementation of cloud computing. This paper considers one of its major problems, i.e. task scheduling. The function of an efficient task scheduling algorithm is that it concentrates not only on attaining the requirements of the user but also in enhancing the efficiency of the cloud computing system. Cloud task scheduling is an NP-hard optimization problem, and many meta-heuristic algorithms have been proposed to solve it. This paper proposes a modified Penguins Search Optimization Algorithm (MPeSOA) for efficient cloud task scheduling. The main contribution of our work is to schedule all tasks to available virtual machines so that the makespan is minimized, resource utilization is increased and the degree of imbalance is reduced. The proposed scheduling algorithm was simulated using the CloudSim 4.0 simulator. Experimental results showed that the proposed MPeSOA outperformed three existing meta-heuristics, namely Penguins Search Optimization Algorithm (PeSOA), Genetic Algorithm (GA) and Particle Swarm Optimization (PSO).","PeriodicalId":42021,"journal":{"name":"International Journal of Next-Generation Computing","volume":"104 1","pages":""},"PeriodicalIF":0.3,"publicationDate":"2023-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80470251","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 : 2023-03-31DOI: 10.47164/ijngc.v14i2.976
Nikita Singhal, Lalji Prasad
Numerous traffic-related problems arise as a result of the exponential growth in the number of vehicles on the road. Vehicle detection is important in many smart transportation applications, including transportation planning, transportation management, traffic signal automation, and autonomous driving. Many researchers have spent a lot of time and effort on it over the last few decades, and they have achieved a lot. In this paper, we compared the performances of major deep learning models: Faster RCNN, YOLOv3, YOLOv4, YOLOv5, and SSD for vehicle detection with variable image size using two different vehicle detection datasets: Highway dataset and MIOTCD. The datasets that are most commonly used in this domain are also analyzed and reviewed. Additionally, we haveemphasized the opportunities and challenges in this domain for the future.
{"title":"Comparative Analysis of Deep Learning based Vehicle Detection Approaches","authors":"Nikita Singhal, Lalji Prasad","doi":"10.47164/ijngc.v14i2.976","DOIUrl":"https://doi.org/10.47164/ijngc.v14i2.976","url":null,"abstract":"Numerous traffic-related problems arise as a result of the exponential growth in the number of vehicles on the road. Vehicle detection is important in many smart transportation applications, including transportation planning, transportation management, traffic signal automation, and autonomous driving. Many researchers have spent a lot of time and effort on it over the last few decades, and they have achieved a lot. In this paper, we compared the performances of major deep learning models: Faster RCNN, YOLOv3, YOLOv4, YOLOv5, and SSD for vehicle detection with variable image size using two different vehicle detection datasets: Highway dataset and MIOTCD. The datasets that are most commonly used in this domain are also analyzed and reviewed. Additionally, we haveemphasized the opportunities and challenges in this domain for the future.","PeriodicalId":42021,"journal":{"name":"International Journal of Next-Generation Computing","volume":"45 1","pages":""},"PeriodicalIF":0.3,"publicationDate":"2023-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87522992","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 : 2023-03-31DOI: 10.47164/ijngc.v14i2.691
Shashank Joshi, Falak Joshi
In human contact, emotion is very crucial. Attributes like words, voice intonation, facial expressions, and kinesics can all be used to portray one's feelings. However, brain-computer interface (BCI) devices have not yet reached the level required for emotion interpretation. With the rapid development of machine learning algorithms, dry electrode techniques, and different real-world applications of the brain-computer interface for normal individuals, emotion categorization from EEG data has recently gotten a lot of attention. Electroencephalogram (EEG) signals are a critical resource for these systems. The primary benefit of employing EEG signals is that they reflect true emotion and are easily resolved by computer systems. In this work, EEG signals associated with good, neutral, and negative emotions were identified using channel selection preprocessing. However, researchers had a limited grasp of the specifics of the link between various emotional states until now. To identify EEG signals, we used discrete wavelet transform and machine learning techniques such as recurrent neural network (RNN) and k-nearest neighbor (kNN) algorithm. Initially, the classifier methods were utilized for channel selection. As a result, final feature vectors were created by integrating the features of EEG segments from these channels. Using the RNN and kNN algorithms, the final feature vectors with connected positive, neutral, and negative emotions were categorized independently. The classification performance of both techniques is computed and compared. Using RNN and kNN, the average overall accuracies were 94.844 % and 93.438 %, respectively.
{"title":"Human Emotion Classification based on EEG Signals Using Recurrent Neural Network And KNN","authors":"Shashank Joshi, Falak Joshi","doi":"10.47164/ijngc.v14i2.691","DOIUrl":"https://doi.org/10.47164/ijngc.v14i2.691","url":null,"abstract":"In human contact, emotion is very crucial. Attributes like words, voice intonation, facial expressions, and kinesics can all be used to portray one's feelings. However, brain-computer interface (BCI) devices have not yet reached the level required for emotion interpretation. With the rapid development of machine learning algorithms, dry electrode techniques, and different real-world applications of the brain-computer interface for normal individuals, emotion categorization from EEG data has recently gotten a lot of attention. Electroencephalogram (EEG) signals are a critical resource for these systems. The primary benefit of employing EEG signals is that they reflect true emotion and are easily resolved by computer systems. In this work, EEG signals associated with good, neutral, and negative emotions were identified using channel selection preprocessing. However, researchers had a limited grasp of the specifics of the link between various emotional states until now. To identify EEG signals, we used discrete wavelet transform and machine learning techniques such as recurrent neural network (RNN) and k-nearest neighbor (kNN) algorithm. Initially, the classifier methods were utilized for channel selection. As a result, final feature vectors were created by integrating the features of EEG segments from these channels. Using the RNN and kNN algorithms, the final feature vectors with connected positive, neutral, and negative emotions were categorized independently. The classification performance of both techniques is computed and compared. Using RNN and kNN, the average overall accuracies were 94.844 % and 93.438 %, respectively.","PeriodicalId":42021,"journal":{"name":"International Journal of Next-Generation Computing","volume":"15 1","pages":""},"PeriodicalIF":0.3,"publicationDate":"2023-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85976806","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 : 2023-03-31DOI: 10.47164/ijngc.v14i2.566
Rakesh Singh, Radhika Kotecha, Karan Shethia
Automation is becoming more prevalent among manufacturing and eCommerce companies as a way to better serve their customers. One of the key problems in warehouse management is controlling the internal delivery/movement of goods/objects. It is labor-intensive, time-consuming, and needs additional care based on delicacy goods. Automated guided vehicles (AGVs) that are small in size can serve as a solution to the aforementioned problem of locomotion. For any robot to move autonomously, the initial and critical requirement is to understand the surrounding environment precisely. Simultaneous Localisation and Mapping (SLAM) is the preferred method to build an environment map at runtime. SLAM is designed to work in a static environment and faces a few challenges once it involves dynamic objects. This research proposes Deep Learning to enhance the SLAM technique. It aids the identification of static and dynamic objects and consequently updates the occupancy grid map. The proposed approach has been validated through a simulated environment and a Convolution Neural Network (CNN) for the classification of static and dynamic objects. The simulation results demonstrate the promising nature of the proposed approach.
{"title":"Enhancing Object Mapping in SLAM using CNN","authors":"Rakesh Singh, Radhika Kotecha, Karan Shethia","doi":"10.47164/ijngc.v14i2.566","DOIUrl":"https://doi.org/10.47164/ijngc.v14i2.566","url":null,"abstract":"Automation is becoming more prevalent among manufacturing and eCommerce companies as a way to better serve their customers. One of the key problems in warehouse management is controlling the internal delivery/movement of goods/objects. It is labor-intensive, time-consuming, and needs additional care based on delicacy goods. Automated guided vehicles (AGVs) that are small in size can serve as a solution to the aforementioned problem of locomotion. For any robot to move autonomously, the initial and critical requirement is to understand the surrounding environment precisely. Simultaneous Localisation and Mapping (SLAM) is the preferred method to build an environment map at runtime. SLAM is designed to work in a static environment and faces a few challenges once it involves dynamic objects. This research proposes Deep Learning to enhance the SLAM technique. It aids the identification of static and dynamic objects and consequently updates the occupancy grid map. The proposed approach has been validated through a simulated environment and a Convolution Neural Network (CNN) for the classification of static and dynamic objects. The simulation results demonstrate the promising nature of the proposed approach.","PeriodicalId":42021,"journal":{"name":"International Journal of Next-Generation Computing","volume":"22 1","pages":""},"PeriodicalIF":0.3,"publicationDate":"2023-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87451332","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 : 2023-03-31DOI: 10.47164/ijngc.v14i2.1137
Soma Mitra, Dr. Saikat Basu
Since the 1990s, remote sensing images have been used for land cover classification combined with MachineLearning algorithms. The traditional land surveying method only works well in places that are hard to get to, likehigh mountain regions, arid and semi-arid land, and densely forested areas. As the satellites and airborne sensorspass over a specific point of land surface periodically, it is possible to assess the change in land cover over a longtime. With the advent of ML methods, automated land cover classification has been at the center of researchfor the last few decades. From 2015 forward, a technical shift has been noticed with the emergence of severalbranches of Neural Networks (NN) and Deep Learning (DL). This paper examines current practices, problems,and trends in satellite image processing. This formal review focused on the summarization of major classificationapproaches from 1995. Two dominant research trends have been noticed in automated land cover classification,e.g., per pixel and subpixel analysis. Classical machine learning algorithms and deep learning methods are mainlyused for per-pixel analysis, whereas Fuzzy algorithms are used for sub-pixel analysis. The current article includesthe research gap in automated land cover classification to provide comprehensive guidance for subsequent researchdirection.
{"title":"Remote Sensing Based Land Cover Classification Using Machine Learning and Deep Learning: A Comprehensive Survey","authors":"Soma Mitra, Dr. Saikat Basu","doi":"10.47164/ijngc.v14i2.1137","DOIUrl":"https://doi.org/10.47164/ijngc.v14i2.1137","url":null,"abstract":"Since the 1990s, remote sensing images have been used for land cover classification combined with MachineLearning algorithms. The traditional land surveying method only works well in places that are hard to get to, likehigh mountain regions, arid and semi-arid land, and densely forested areas. As the satellites and airborne sensorspass over a specific point of land surface periodically, it is possible to assess the change in land cover over a longtime. With the advent of ML methods, automated land cover classification has been at the center of researchfor the last few decades. From 2015 forward, a technical shift has been noticed with the emergence of severalbranches of Neural Networks (NN) and Deep Learning (DL). This paper examines current practices, problems,and trends in satellite image processing. This formal review focused on the summarization of major classificationapproaches from 1995. Two dominant research trends have been noticed in automated land cover classification,e.g., per pixel and subpixel analysis. Classical machine learning algorithms and deep learning methods are mainlyused for per-pixel analysis, whereas Fuzzy algorithms are used for sub-pixel analysis. The current article includesthe research gap in automated land cover classification to provide comprehensive guidance for subsequent researchdirection.","PeriodicalId":42021,"journal":{"name":"International Journal of Next-Generation Computing","volume":"32 1","pages":""},"PeriodicalIF":0.3,"publicationDate":"2023-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81186119","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 : 2023-02-15DOI: 10.47164/ijngc.v14i1.1090
Ankita Gore, Vanshika Bajaj, Preeti Yadav, Vaishnavi Chouhan, Madhuri A. Tayal, M. S. Kumar
Natural Language Processing (NLP), is more specifically the branch of ”artificial intelligence” (AI) concerned with providing computers the ability to comprehend spoken and written language in a manner similar to that of humans. It is used for practical purposes to help connects us with everyday activities such as texting, emailing, and cross-language communication. The requirement for intelligent systems that can read a text and listen to voice memos and can converse with people in a natural language like English has substantially increased in recent years. In this paper, the random clausal sentence generator which is simple, compound, and complex sentences are described. This random sentence generation is beneficial for students studying on online platforms to learn clauses as they will get a variety of exercises to practice. Initially, simple sentences get generated and subsequently moved on to compound sentence and complex sentence generation. In this method, roughly hundredverbs are used to get varied randomness along with 3-4 conjunctions and objects which nearly fit with the verbs and give a syntactically and semantically meaningful sentence as the outcome.
{"title":"Sentence Generator for English Language using Formal Semantics","authors":"Ankita Gore, Vanshika Bajaj, Preeti Yadav, Vaishnavi Chouhan, Madhuri A. Tayal, M. S. Kumar","doi":"10.47164/ijngc.v14i1.1090","DOIUrl":"https://doi.org/10.47164/ijngc.v14i1.1090","url":null,"abstract":"Natural Language Processing (NLP), is more specifically the branch of ”artificial intelligence” (AI) concerned with providing computers the ability to comprehend spoken and written language in a manner similar to that of humans. It is used for practical purposes to help connects us with everyday activities such as texting, emailing, and cross-language communication. The requirement for intelligent systems that can read a text and listen to voice memos and can converse with people in a natural language like English has substantially increased in recent years. In this paper, the random clausal sentence generator which is simple, compound, and complex sentences are described. This random sentence generation is beneficial for students studying on online platforms to learn clauses as they will get a variety of exercises to practice. Initially, simple sentences get generated and subsequently moved on to compound sentence and complex sentence generation. In this method, roughly hundredverbs are used to get varied randomness along with 3-4 conjunctions and objects which nearly fit with the verbs and give a syntactically and semantically meaningful sentence as the outcome.","PeriodicalId":42021,"journal":{"name":"International Journal of Next-Generation Computing","volume":"68 1","pages":""},"PeriodicalIF":0.3,"publicationDate":"2023-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90365244","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 : 2023-02-15DOI: 10.47164/ijngc.v14i1.1017
P. Parkhi, Bhagyashree Hambarde Hambarde
The optic nerve damaging condition called Glaucoma. This disease is increment at an alarming rate. By the end of the 2044 there is possibility that across 111.8 million populations will be influenced by glaucoma. It is a neurodegenerative disease. If intravascular pressure is increases, optic nerve of the eye gets damage. This damage may cause permanent or total blindness in person. The Glaucoma is examined by an experienced ophthalmologist on the retinal part of the eye. This process required excessive equipment, experienced medical practitioners and also it take more time to work out manually. After considering this problem there is an extreme requirement of developing an automatic system which will effectively and automatically work properly in lack of any professional doctor and it should also take less time. Lots of different parameters are available to detect glaucoma but thebest parameter is to find out optical cup-to-disc-ratio. To increase or to enhance the precision and accuracy of the result, cup to disc value is needed to find CDR value. In order to detect glaucoma, automatic separation of the OC and DC is very essential to avoid any error. We use deeplabv3 architecture to perform segmentation of optic disc and cup and classification is done using ensemble machine learning. This proposes research achieve intersection over union (IOU) scores, 0.9423 for optic disc and 0.9310 for optic cup. We perform testing on globally accessible data-sets i.e. DRISHTI, ORIGA, and RIMONE with accuracy of 93%, 91% and 92% respectively
这种视神经损伤被称为青光眼。这种疾病正以惊人的速度增长。到本世纪末，有可能有1.118亿人口将受到青光眼的影响。这是一种神经退行性疾病。如果血管内压力升高，眼睛的视神经就会受到损伤。这种损害可能导致永久或完全失明。青光眼由经验丰富的眼科医生检查眼睛的视网膜部分。这一过程需要大量的设备和经验丰富的医生，而且需要更多的时间来手工完成。考虑到这一问题，迫切需要开发一种能够在没有专业医生的情况下有效、自动地正常工作的自动化系统，并且需要更少的时间。青光眼的检测参数有很多，但最好的参数是光学杯盘比。为了增加或提高结果的精度和准确性，需要用杯盘值来寻找CDR值。为了检测青光眼，自动分离OC和DC是非常必要的，以避免任何错误。我们使用deepplabv3架构进行视盘和视杯的分割，并使用集成机器学习完成分类。本文提出的研究实现了视盘和视杯的IOU (intersection over union)分数分别为0.9423和0.9310。我们在全球可访问的数据集(即DRISHTI, ORIGA和RIMONE)上进行测试，准确率分别为93%，91%和92%
{"title":"Optical Cup and Disc Segmentation using Deep Learning Technique for Glaucoma Detection","authors":"P. Parkhi, Bhagyashree Hambarde Hambarde","doi":"10.47164/ijngc.v14i1.1017","DOIUrl":"https://doi.org/10.47164/ijngc.v14i1.1017","url":null,"abstract":"The optic nerve damaging condition called Glaucoma. This disease is increment at an alarming rate. By the end of the 2044 there is possibility that across 111.8 million populations will be influenced by glaucoma. It is a neurodegenerative disease. If intravascular pressure is increases, optic nerve of the eye gets damage. This damage may cause permanent or total blindness in person. The Glaucoma is examined by an experienced ophthalmologist on the retinal part of the eye. This process required excessive equipment, experienced medical practitioners and also it take more time to work out manually. After considering this problem there is an extreme requirement of developing an automatic system which will effectively and automatically work properly in lack of any professional doctor and it should also take less time. Lots of different parameters are available to detect glaucoma but thebest parameter is to find out optical cup-to-disc-ratio. To increase or to enhance the precision and accuracy of the result, cup to disc value is needed to find CDR value. In order to detect glaucoma, automatic separation of the OC and DC is very essential to avoid any error. We use deeplabv3 architecture to perform segmentation of optic disc and cup and classification is done using ensemble machine learning. This proposes research achieve intersection over union (IOU) scores, 0.9423 for optic disc and 0.9310 for optic cup. We perform testing on globally accessible data-sets i.e. DRISHTI, ORIGA, and RIMONE with accuracy of 93%, 91% and 92% respectively","PeriodicalId":42021,"journal":{"name":"International Journal of Next-Generation Computing","volume":"50 1","pages":""},"PeriodicalIF":0.3,"publicationDate":"2023-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74781781","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 : 2023-02-15DOI: 10.47164/ijngc.v14i1.1000
Leena K. Gautam, V. Gulhane
Various nutrients are necessary for humans to remain healthy and active. Maintaining a high quality of life now depends on keeping track of everyday eating habits to prevent consuming too many calories and incorrect nutrients. Computerized applications can help Indian elderly people maintain and improve their overall health by providing pertinent information such as calories and nutritional details and following a strict diet plan suited to their ailments. In order to create optimized diet plans that take disease prevalence, food availability, and user preferences into account, the paper offers the Multi Constraint Metaheuristic integrated with the Knapsack approach. The solution's quality is attained by applying a dynamic, personalized set of food items. The average error percentage obtained by the suggested algorithm is 4.15.
{"title":"Diet Recommendation Model Using Multi Constraint Metaheuristic and Knapsack Optimization Algorithm.","authors":"Leena K. Gautam, V. Gulhane","doi":"10.47164/ijngc.v14i1.1000","DOIUrl":"https://doi.org/10.47164/ijngc.v14i1.1000","url":null,"abstract":"Various nutrients are necessary for humans to remain healthy and active. Maintaining a high quality of life now depends on keeping track of everyday eating habits to prevent consuming too many calories and incorrect nutrients. Computerized applications can help Indian elderly people maintain and improve their overall health by providing pertinent information such as calories and nutritional details and following a strict diet plan suited to their ailments. In order to create optimized diet plans that take disease prevalence, food availability, and user preferences into account, the paper offers the Multi Constraint Metaheuristic integrated with the Knapsack approach. The solution's quality is attained by applying a dynamic, personalized set of food items. The average error percentage obtained by the suggested algorithm is 4.15.","PeriodicalId":42021,"journal":{"name":"International Journal of Next-Generation Computing","volume":"50 1","pages":""},"PeriodicalIF":0.3,"publicationDate":"2023-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84769345","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 : 2023-02-15DOI: 10.47164/ijngc.v14i1.999
Shreya Tope, Sadnyani Gomkar, Pukhraj Rathkanthiwar, Aayushi Ganguli, P. Selokar
A genuine disability prevents a person from speaking. There are numerous ways for people with this condition to communicate with others, including sign language, which is one of the more widely used forms of communication. Human body language can be used to communicate with one another using sign language, where each word is represented by a specific sequence of gestures. The goal of the paper is to translate human sign language into speech that can interpret human gestures. Through a deep convolution neural network, we first construct the data-set, save the hand gestures in the database, and then use an appropriate model on these hand gesture visuals to test and train the system. When a user launches the application, it then detects the gestures that are saved inthe database and displays the corresponding results. By employing this system, it is possible to assist those who are hard of hearing while simultaneously making communication with them simpler for everyone else.
{"title":"Sign Language Gesture to Speech Conversion Using Convolutional Neural Network","authors":"Shreya Tope, Sadnyani Gomkar, Pukhraj Rathkanthiwar, Aayushi Ganguli, P. Selokar","doi":"10.47164/ijngc.v14i1.999","DOIUrl":"https://doi.org/10.47164/ijngc.v14i1.999","url":null,"abstract":"A genuine disability prevents a person from speaking. There are numerous ways for people with this condition to communicate with others, including sign language, which is one of the more widely used forms of communication. Human body language can be used to communicate with one another using sign language, where each word is represented by a specific sequence of gestures.\u0000The goal of the paper is to translate human sign language into speech that can interpret human gestures. Through a deep convolution neural network, we first construct the data-set, save the hand gestures in the database, and then use an appropriate model on these hand gesture visuals to test and train the system. When a user launches the application, it then detects the gestures that are saved inthe database and displays the corresponding results. By employing this system, it is possible to assist those who are hard of hearing while simultaneously making communication with them simpler for everyone else.","PeriodicalId":42021,"journal":{"name":"International Journal of Next-Generation Computing","volume":"42 1","pages":""},"PeriodicalIF":0.3,"publicationDate":"2023-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83290878","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 : 2023-02-15DOI: 10.47164/ijngc.v14i1.1098
Bhumika Neole
Noise determination and estimating a signal along with all its details proves a challenging task in signal processing. This issue has been addressed in the past using various discrete wavelet transform (DWT) based techniques. The signal is estimated as linear average of individual estimates derived from translated and wavelet-thresholded versions of a noisy signal by cycle spinning technique. In this paper, we propose a modified cycle zpinning algorithm with a new scaled down threshold of wavelet shrinkage for denoising images containing zero mean Gaussian noise using linear average of reconstructions obtained from shifted sequences’ DWT. This considerably improves the denoising performance of the conventional recursive cycle spinning algorithm and requires drasticallyless computations. Denoising performance of the proposed algorithm is benchmarked with published Recursive Cycle spinning, Buades NL means and Dual tree Complex Wavelet algorithms visually and quantitatively.
{"title":"Denoising Of Digital Images Using Cyclespinning Algorithm With Shifted DWT","authors":"Bhumika Neole","doi":"10.47164/ijngc.v14i1.1098","DOIUrl":"https://doi.org/10.47164/ijngc.v14i1.1098","url":null,"abstract":"Noise determination and estimating a signal along with all its details proves a challenging task in signal processing. This issue has been addressed in the past using various discrete wavelet transform (DWT) based techniques. The signal is estimated as linear average of individual estimates derived from translated and wavelet-thresholded versions of a noisy signal by cycle spinning technique. In this paper, we propose a modified cycle zpinning algorithm with a new scaled down threshold of wavelet shrinkage for denoising images containing zero mean Gaussian noise using linear average of reconstructions obtained from shifted sequences’ DWT. This considerably improves the denoising performance of the conventional recursive cycle spinning algorithm and requires drasticallyless computations. Denoising performance of the proposed algorithm is benchmarked with published Recursive Cycle spinning, Buades NL means and Dual tree Complex Wavelet algorithms visually and quantitatively.","PeriodicalId":42021,"journal":{"name":"International Journal of Next-Generation Computing","volume":"48 1","pages":""},"PeriodicalIF":0.3,"publicationDate":"2023-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88928685","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：