A face recognition system is a computer application proficient of verifying or identifying a person from a video frame or a digital image from a video source. The human face acts a significant role in the social communication, passing on people’s uniqueness. By means of the human face as a key to protection, biometric face recognition technology has attained noteworthy consideration in the precedent numerous years owing to its prospective for an extensive assortment of applications in both non-law enforcement and law enforcement activities. In this paper, the Speech Emotion Recognition (SER) is analyzed by adopting cepstral features for feature extraction and k-NN classifier for classification. Moreover, the implemented process is compared with k-means and C-means algorithms and the results are obtained.
{"title":"Impact of Supervised Classifier on Speech Emotion Recognition","authors":"Anitha J.S","doi":"10.46253/j.mr.v2i1.a2","DOIUrl":"https://doi.org/10.46253/j.mr.v2i1.a2","url":null,"abstract":"A face recognition system is a computer application proficient of verifying or identifying a person from a video frame or a digital image from a video source. The human face acts a significant role in the social communication, passing on people’s uniqueness. By means of the human face as a key to protection, biometric face recognition technology has attained noteworthy consideration in the precedent numerous years owing to its prospective for an extensive assortment of applications in both non-law enforcement and law enforcement activities. In this paper, the Speech Emotion Recognition (SER) is analyzed by adopting cepstral features for feature extraction and k-NN classifier for classification. Moreover, the implemented process is compared with k-means and C-means algorithms and the results are obtained.","PeriodicalId":167187,"journal":{"name":"Multimedia Research","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115416893","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}
: In various fields, image restoration has received huge interest and many researchers introduce several image restoration techniques to restore hidden clear images from degraded images. Moreover, aforesaid approaches performances are estimated impartially remnants the huge confront that might delay the furthermore improvement of developed image restoration techniques. Hence, an efficient noisy pixel prediction on the basis of the image restoration is introduced that uses the Deep Convolutional Neural Network (DCNN) classifier to restore the input image from several noises, such as random noise as well as impulse noise. An Improved Harmony Search Algorithm (IHSA) is adopted to train the DCNN optimally based on minimum error. After identifying the noisy pixels, by exploiting the neuro-fuzzy system the enhancement of pixel is performed. Finally, the experimental analysis is performed and the image restoration performance on the basis of IHSA is analyzed based on the SDME, PSNR, and SSIM. Ultimately, the adopted model attains the maximum PSNR SSIM for images with random noise, as well as maximum SDME with impulse noise, correspondingly.
{"title":"Improved Harmony Search Approach based DCNN for Image Restoration Model","authors":"Sathish Vuyyala","doi":"10.46253/j.mr.v5i2.a2","DOIUrl":"https://doi.org/10.46253/j.mr.v5i2.a2","url":null,"abstract":": In various fields, image restoration has received huge interest and many researchers introduce several image restoration techniques to restore hidden clear images from degraded images. Moreover, aforesaid approaches performances are estimated impartially remnants the huge confront that might delay the furthermore improvement of developed image restoration techniques. Hence, an efficient noisy pixel prediction on the basis of the image restoration is introduced that uses the Deep Convolutional Neural Network (DCNN) classifier to restore the input image from several noises, such as random noise as well as impulse noise. An Improved Harmony Search Algorithm (IHSA) is adopted to train the DCNN optimally based on minimum error. After identifying the noisy pixels, by exploiting the neuro-fuzzy system the enhancement of pixel is performed. Finally, the experimental analysis is performed and the image restoration performance on the basis of IHSA is analyzed based on the SDME, PSNR, and SSIM. Ultimately, the adopted model attains the maximum PSNR SSIM for images with random noise, as well as maximum SDME with impulse noise, correspondingly.","PeriodicalId":167187,"journal":{"name":"Multimedia Research","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123049636","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}
: In subsequent generation networks, to perform an improved communication the Orthogonal Frequency Division Multiple Access (OFDM), as well as Multiple Input-Multiple Output (MIMO) systems, are integrated which makes easy the spatial multiplexing on Resource Blocks (RBs) on the basis of time-frequency. A novel approach to interference alleviation was developed in this paper for 3D antenna array models in OFDMA as well as multi-cell MIMO wireless networks. Therefore, in the 3D MIMO-OFDM system, the Dynamic vertical beamforming is exploited to the cell degree separation user-specific down tilts user. The major contribution of this paper is to maximize the cell edge user’s throughput as well as cell center users. Here, the single objective function is the specified multi-objective model that is resolved using the adoption of a novel enhanced approach. This optimization issue is solved using the fine-tuning of particular parameters like RB allocation, allocated power for RB, and cell edge user. A hybrid Whale Optimization Algorithm (WOA) and Grey Wolf Optimization (GWO) algorithm referred to as the Hybrid WOA-GWO approach is used to attain the fine-tuned parameters. At last, the superiority of the adopted technique is examined with existing techniques on the basis of throughput, etc.
{"title":"Wireless Communication Network using Hybrid WOA and GWO Algorithm","authors":"Pavan Kumar Gajawada","doi":"10.46253/j.mr.v4i4.a3","DOIUrl":"https://doi.org/10.46253/j.mr.v4i4.a3","url":null,"abstract":": In subsequent generation networks, to perform an improved communication the Orthogonal Frequency Division Multiple Access (OFDM), as well as Multiple Input-Multiple Output (MIMO) systems, are integrated which makes easy the spatial multiplexing on Resource Blocks (RBs) on the basis of time-frequency. A novel approach to interference alleviation was developed in this paper for 3D antenna array models in OFDMA as well as multi-cell MIMO wireless networks. Therefore, in the 3D MIMO-OFDM system, the Dynamic vertical beamforming is exploited to the cell degree separation user-specific down tilts user. The major contribution of this paper is to maximize the cell edge user’s throughput as well as cell center users. Here, the single objective function is the specified multi-objective model that is resolved using the adoption of a novel enhanced approach. This optimization issue is solved using the fine-tuning of particular parameters like RB allocation, allocated power for RB, and cell edge user. A hybrid Whale Optimization Algorithm (WOA) and Grey Wolf Optimization (GWO) algorithm referred to as the Hybrid WOA-GWO approach is used to attain the fine-tuned parameters. At last, the superiority of the adopted technique is examined with existing techniques on the basis of throughput, etc.","PeriodicalId":167187,"journal":{"name":"Multimedia Research","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121944349","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}
: Cloud computing is vulnerable to accessible Information Technology (IT) attacks, as it expands as well as exploits conventional OS, IT infrastructure as well as applications. Nevertheless, the cloud computing environment occurs several security problems in recognizing the anomalous network behaviors with respect to the existing threats. An effectual Intrusion Detection System (IDS) called a hybrid Grasshopper Optimization (GSO) algorithm with Bat Algorithm (BA)-based DBN is developed to identify suspicious intrusions in cloud environments in order to solve security problems. By exploiting the fitness function the optimal solution to detect the intrusion is shown that recognizes the minimum error value as the optimal solution. Moreover, using adopted optimization approach is used to tune the weights optimally to produce an effective and best solution to detect the intruders. Nevertheless, the adopted optimization model-based Deep Belief Network (DBN) attained superior performance regarding the accuracy, sensitivity, as well as specificity by exploiting the BoT-IoT dataset.
{"title":"Hybrid Grasshopper Optimization and Bat Algorithm based DBN for Intrusion Detection in Cloud","authors":"Rama Krishna, Meher","doi":"10.46253/j.mr.v4i4.a5","DOIUrl":"https://doi.org/10.46253/j.mr.v4i4.a5","url":null,"abstract":": Cloud computing is vulnerable to accessible Information Technology (IT) attacks, as it expands as well as exploits conventional OS, IT infrastructure as well as applications. Nevertheless, the cloud computing environment occurs several security problems in recognizing the anomalous network behaviors with respect to the existing threats. An effectual Intrusion Detection System (IDS) called a hybrid Grasshopper Optimization (GSO) algorithm with Bat Algorithm (BA)-based DBN is developed to identify suspicious intrusions in cloud environments in order to solve security problems. By exploiting the fitness function the optimal solution to detect the intrusion is shown that recognizes the minimum error value as the optimal solution. Moreover, using adopted optimization approach is used to tune the weights optimally to produce an effective and best solution to detect the intruders. Nevertheless, the adopted optimization model-based Deep Belief Network (DBN) attained superior performance regarding the accuracy, sensitivity, as well as specificity by exploiting the BoT-IoT dataset.","PeriodicalId":167187,"journal":{"name":"Multimedia Research","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126409861","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}
: The current article aims to analyze student performance using some similarity measures. The analysis will result in a classification of the student based on how they usually take their lunch. Throughout the processes, we define some notions of similarity measures and finally select some measures to evaluate various data types of attributes. The Nearest-Neighbor approach is used for classification, with the K-Nearest-Neighbor (KNN) algorithm. At last we compare the performance on three data types: numerical, categorical and mixed data. Finally, the result is tested and validated using the Python programming language.
{"title":"Similarity Learning on Big Data: A Case Study","authors":"Albert Agisha Ntwali","doi":"10.46253/j.mr.v5i1.a1","DOIUrl":"https://doi.org/10.46253/j.mr.v5i1.a1","url":null,"abstract":": The current article aims to analyze student performance using some similarity measures. The analysis will result in a classification of the student based on how they usually take their lunch. Throughout the processes, we define some notions of similarity measures and finally select some measures to evaluate various data types of attributes. The Nearest-Neighbor approach is used for classification, with the K-Nearest-Neighbor (KNN) algorithm. At last we compare the performance on three data types: numerical, categorical and mixed data. Finally, the result is tested and validated using the Python programming language.","PeriodicalId":167187,"journal":{"name":"Multimedia Research","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121813642","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：