Multimedia Research最新文献

{"title":"To Improve the Insect Pests Images- A Comparative Analysis of Image Denoising Methods","authors":"","doi":"10.46253/j.mr.v6i4.a3","DOIUrl":"https://doi.org/10.46253/j.mr.v6i4.a3","url":null,"abstract":": Pest, Plant disease, climate change, and disaster are the major factor to determine the yeild of the plant. Pest inthe plants are identified in different methods. To process the images with machine vision models’ the quality of images isan important concern. Noise and unwanted artifacts integrated with the images at the time of acquisition and transmission. Noise is introduced in the images due to transmission, environment distortion, and sensor qualities. In this regard, some solutions related to the post-image-acquisition are required to enhance such issues. In this, image denoiser plays an important role to enhance the quality and minimize the noises in images. However, to preserve details of images a comparative analysis of related image denoising algorithms is conducted. In this study, the authors cover three types of filters to minimize the noise of insect pests’ images to find better ones. The experiment of the comparative study revealed that the Total Variation (TV) algorithm gives better results as compared to another denoising algorithm at different noise levels.","PeriodicalId":167187,"journal":{"name":"Multimedia Research","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135562819","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Application of Telemedicine for Healthcare Delivery in Nigeria","authors":"","doi":"10.46253/j.mr.v6i4.a2","DOIUrl":"https://doi.org/10.46253/j.mr.v6i4.a2","url":null,"abstract":": The study explores the application of telemedicine in healthcare delivery in Nigeria, the perception of medical practitioners, and its application in healthcare service delivery to the nation. An architectural framework was designed to depict the application of healthcare delivery via telemedicine. A questionnaire was set up to check the views of medical practitioners regarding the application of telemedicine in healthcare delivery. Over 100 questionnaires were given out to Medical practitioners, Patients, ICT providers, and Healthcare professionals who are policymakers. 95 questionnaires were returned and the remaining 5 could not be accounted for by the respondents. An evaluation was conducted on the collated data to check the ease of usage, Degree of relevance, and Reliability index of the application of telemedicine to evaluation performance metrics. 87.37% of the respondents preferred the application of telemedicine in healthcare delivery in terms of patient health management and satisfaction improvement. 12.63% of others preferred face-to-face opinions in terms of practice satisfaction to patients, Ease of use, Equipment setup expenses, Technical reliability, Time duration, Trust among the professionals, Diagnostic accuracy, and Patient convenience. The SRI, SDR, and SEU results obtained from the responses are 3.33, 3.02, and 2.65 respectively. The hypothesis derivative crouch coefficient ranges between 0.71 and 0.80 based on the validity and reliability of the application of telemedicine in healthcare delivery. Most medical practitioners were overwhelmed and supported the application of telemedicine and its application in healthcare practice. This study shows that medical practitioners are ready and prepared to accept telemedicine applications to improve healthcare delivery in Nigeria.","PeriodicalId":167187,"journal":{"name":"Multimedia Research","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135562486","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Android-Based Examination Questions Reader Application for Visually Impaired Students","authors":"","doi":"10.46253/j.mr.v6i4.a1","DOIUrl":"https://doi.org/10.46253/j.mr.v6i4.a1","url":null,"abstract":": Education is part and parcel of every human being. Education empowers an induvial, concocts a community, and protrudes a nation. To be educated, a person must gain knowledge through reading, listening, speaking, and writing. These processes are carried out through our body parts. Body parts such as the brain, heart, eyes, ears, mouth, hands, etc., play an important role in education. When any such body parts get affected, it will affect the entire system. Those people need extra guidance and support. As such, visually impaired students cannot read question papers during the examination as their sense of vision is deformed which can cause a lot of difficulties during their exam period including diverting the attention of the examiner to get special consideration or attention. However, a screen reading application can help impaired students to be independent in writing the exam. This project aims to address this problem by developing an Android application that has the capability of reading out questions to visually impaired students during examinations. To make the students independent in the examination hall in terms of perceiving questions. Moreover, the application can only work on mobile devices supported by the Android operating system. The Application`s reading capability is limited to questions written inEnglishlanguageonlyanditcannotreadtablesnordescribefigures.Inthecourseofthesoftwaredevelopment, this project has adhered to software Engineering principles where an iterative model was chosen as the SDLC approach to be used for the system development. After the system was fully implemented, a Beta version of the application was subjected to testing where informative feedback was obtained from testers and necessary changes were affected.","PeriodicalId":167187,"journal":{"name":"Multimedia Research","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135562816","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing An Image Blood Staining Malaria Diagnosis Using Convolution Neural Network On Raspberry Pi","authors":"","doi":"10.46253/j.mr.v6i4.a5","DOIUrl":"https://doi.org/10.46253/j.mr.v6i4.a5","url":null,"abstract":": Malaria is a common disease in Sub-Saharan Africa, the disease is caused by a class of parasites called protozoan, and it is transmitted by female Anopheles mosquitoes to humans. Plasmodium ovale, plasmodium vivax, plasmodium knowlesi, plasmodium falciparum, and plasmodiummalariae. T he five known plasmodium species that cause malaria in humans. The microscopic diagnosis has always been a gold standard but today, computational tools like deep learning are used in malaria prediction. The deep learning model use images to diagnose infection. The model was trained using the Kaggle dataset with 27,560 images with equal instances of primary images,used to validate primary images from the microscope were annotated using Roboflow. A total of 27 primary images were collected. The model gave accuracy and precision of 85% and Recall of 96% both on the personal computer and Raspberry Pi 4. This research provides a prototype for enhancing malaria diagnosis from images by deploying a deep learning model - a convolution neural network, on a Raspberry Pi. This research has proven the possibility of classifying malaria images as parasitized or unparasitized by deploying a deep-learning model on the Raspberry Pi. This study demonstrates that Raspberry Pi can be utilized for diagnosis and overcome the constraint of requiring high computer hardware specifications to operate a deep learning model. The result obtained 90% accuracy in the detection of parasites in the Red Blood Smear.","PeriodicalId":167187,"journal":{"name":"Multimedia Research","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135562496","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Role of Agricultural Input Credit on Production of Maize: A Case Study in Shebedneo District, Sidama Region, Ethiopia","authors":"","doi":"10.46253/j.mr.v6i4.a4","DOIUrl":"https://doi.org/10.46253/j.mr.v6i4.a4","url":null,"abstract":": Smallholder farmers’ inability to procure agricultural input is one of the main causes of low agricultural productivity and production. But in recent years, the government and NGOs have tried their level best to access credits to farmers both in cash and agricultural inputs, especially fertilizers. In this study, an attempt is made to examine the role of agricultural input credit on the production of maize from a single-visit survey of the case study in Shebedino District, Sidama Region, Ethiopia. More than ever, the study tried to find out the sources of input credit for rural farmers. The major problems that hinder the use, repayment, provision, and collection of input credit for farmers and from farmers. The importance of input credit on maize production and the trends in input credit provision and repayment in Shebedino District. Hence, primary data was collected from 91 farm households drawn from three kebeles using purposive and simple random sampling. Secondary data was collected from the Shebedino District agricultural and OMO microfinance offices and different written documents. The data was analyzed using both the descriptive and econometric analysis methods. OLS models were employed to examine the role of agricultural input credit in the production of maize. The survey findings showed that there is a direct relationship between agricultural input credit and maize output performance. Loan provision in Shebedino District was increasing but the rate was not regular through the years and the repayment rate in the district was decreasing through the years. The finding also showed that educational level and savings have a positive or direct relationship with the usage and repayment of input credit among the farmers. As the findings revealed, the problems that can affect the provision and collection of agricultural inputs credit or taking and repaying the loan are low agricultural productivity, low infrastructural faculties, and low extension service. low saving and attitude of rural farmers towards the input credit service for these, providing more extensional services and infrastructural facilities side by side with credit service to rural farmers is better for increasing their productivity and it is also better if more educated people invest in agricultural activity and increase saving behavior among rural farmers to increase their income and country development.","PeriodicalId":167187,"journal":{"name":"Multimedia Research","volume":"258 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135562492","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Adaptive Filter using Improved Pigeon Inspired Optimization Algorithm for Satellite Image Denoising","authors":"T. Thangam","doi":"10.46253/J.MR.V3I3.A4","DOIUrl":"https://doi.org/10.46253/J.MR.V3I3.A4","url":null,"abstract":"Satellite imaging is a current development in image processing; however, it faces a lot of challenges because of the environmental factors. For denoising, state-of-the-art method has developed some filters like the hyperspectral satellite images, which is not effectual. Moreover, this paper proposed an adaptive filter using the assist of an optimization approach for the satellite image denoising. The developed adaptive filter performs the image denoising via noise correction, noise identification, and image enhancement. In the satellite image by transforming the image to a binary image, the type-2 fuzzy filter recognizes the noisy pixels which are passed via the adaptive non-local mean filter for the noise correction. Subsequently, the kernel-based interpolation scheme performs the image enhancement, which is performed through the developed improved Pigeon optimization algorithm (IPOA). The whole experimentation of the developed denoising system is performed taking into consideration by satellite images from standard databases. It is obvious that the developed adaptive filter with the developed improved Pigeon optimization algorithm has enhanced performance with the PSNR values from the outcomes.","PeriodicalId":167187,"journal":{"name":"Multimedia Research","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114387543","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Crowd Behaviour Recognition using Enhanced Butterfly Optimization Algorithm based Recurrent Neural Network","authors":"Yuying Chen","doi":"10.46253/J.MR.V3I3.A3","DOIUrl":"https://doi.org/10.46253/J.MR.V3I3.A3","url":null,"abstract":"The crowd emotion recognition is a motivating research area that helps the security personals by means of the public emotions to interpret the crowd activity in a region. Approximately several conventional techniques exploit the lowlevel visual features to comprehend the behaviors of a crowd which widen the gap between the high as well as the low-level features. The objective model is used to expand the automatic algorithm for emotion recognition; hence this work uses the Recurrent Neural Network (RNN). The Bhattacharya distance is used for effectual emotion recognition, which is necessary to choose video keyframes. The keyframes are subjected to the Space-Time Interest Points (STI) descriptor which extracts features that structure input vector to the classifier. RNN is trained by exploiting the enhanced Butterfly Optimization Algorithm (Enhanced-BOA). The developed classifier identifies the crowd emotions, like Escape, Angry, Happy, Fight, Running/Walking, Normal, as well as Violence. The experimentation of the developed technique revealed that developed technique obtained a maximum accuracy, sensitivity as well as specificity, correspondingly.","PeriodicalId":167187,"journal":{"name":"Multimedia Research","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134433377","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Image Steganography for Pixel Prediction using K-nearest Neighbor","authors":"Fatima-ezzahra Lagrari","doi":"10.46253/J.MR.V3I2.A2","DOIUrl":"https://doi.org/10.46253/J.MR.V3I2.A2","url":null,"abstract":": Nowadays to secure the privacy of the patient has increased more research interest during the Image steganography process. Least Significant Bit (LSB) substitute approach was widely exploited to hide the sensitive information in the conventional works. Here, each pixel was reinstated to achieve advanced privacy, other than it increased the complexity. This paper develops a new pixel prediction model-based image steganography to surmount the complication problems widespread in the conventional works. In the proposed pixel prediction model, the K-Nearest Neighbour (KNN) classifier is used to construct the prediction map that recognizes the appropriate pixels for the embedding process. Subsequently, from the medical image to extract the wavelet coefficients based on the Discrete Wavelet Transform (DWT) and embedding power and the undisclosed message is embedded into the HL wavelet band in the embedding phase. At last, from the medical image, the concealed message is extracted by using the DWT. The simulation of the proposed pixel prediction model is carried out by exploiting medical images from the BRATS database. The proposed pixel prediction model has attained maximum performance for the Peak Signal to Noise Ratio (PSNR), Structural Similarity Index (SSIM), and correlation factor, correspondingly.","PeriodicalId":167187,"journal":{"name":"Multimedia Research","volume":"218 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116164228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hybrid classifier: Brain Tumor Classification and Segmentation using Genetic-based Grey Wolf optimization","authors":"Avinash Gopal","doi":"10.46253/J.MR.V3I2.A1","DOIUrl":"https://doi.org/10.46253/J.MR.V3I2.A1","url":null,"abstract":"This work uses a novel brain tumor classification technique which comprises 5 steps like “(i) denoising, (ii) skull stripping, (iii) segmentation, (iv) feature extraction and (v) classification”. At first, the image is given in the denoising procedure, whereas the amputation of the noise process is performed by using an entropy-oriented trilateral filter. Subsequently, noise removed image is used to skull stripping procedure through morphology segmentation and Otsu thresholding. Then, the segmentation takes place using the adaptive CLFAHE method. GLCM features are extracted after finishing segmentation. Here, hybrid classification represents the hybridization of 2 classifiers such as FNN and “Bayesian regularization classifier”. The very important involvement lies in the best selecting of hidden neurons in FNN. In this paper, a novel genetic algorithm based GWO (GA-GWO) method is proposed that hybrids the conception. At last, the proposed method performance is evaluated with conventional techniques to show the supremacy of the proposed method.","PeriodicalId":167187,"journal":{"name":"Multimedia Research","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131844699","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimal Container Resource Allocation Using Hybrid SA-MFO Algorithm in Cloud Architecture","authors":"","doi":"10.46253/j.mr.v3i1.a2","DOIUrl":"https://doi.org/10.46253/j.mr.v3i1.a2","url":null,"abstract":": Owing to the merits of container practice such as easier and more rapid consumption, superior portability, and limited overheads, it can be extensively installed over the cloud architecture. Then, a suitable architecture solution is proposed to develop the applications, which are produced using the microservice expansion model. Thus far, numerous research works have determined on resolving the open problems in container management and automation. In reality, for cloud providers, container resource allocation is considered as the main knothole as it directly influences the system performance and resource utilization. In this way, this work initiates a novel optimized container resource allocation framework by developing a novel optimization theory. Here, a novel hybrid approach is proposed such as, SA and MFO that is the hybridization of Simulated Annealing (SA) and Moth Flame Optimization Algorithm (MFOA) to create the prospect of optimal container resource allocation. In addition, the solution of optimized resource allocation is inclined with the modeling of a novel objective model which contemplates system failure, threshold distance, total network distance, and balanced cluster use, correspondingly. At last, the performance of the proposed approach is evaluated over other existing approaches and exhibits the performance of the proposed model.","PeriodicalId":167187,"journal":{"name":"Multimedia Research","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125391749","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}