https://reunir.unir.net/handle/123456789/12993 2024-11-05T05:59:27Z https://reunir.unir.net/handle/123456789/13005 Editor's Note Chun-Wei Lin, Jerry; Srivastava, Gautam; Tseng, Vicent S. In today’s world, we have witnessed an onset of multimedia content being uploaded/downloaded and shared through a multitude of platforms both online and offline. In support of this trend, multimedia processing and analyzing has become very popular in all kinds of information extraction and attracts research interest from both academia and industry. This is to be expected as the multimedia digital world is worth trillions of dollars worldwide. However, multimedia information is hard to encode, interpret and recognize because it is combined with many complex components. Recently, there are many research areas related to the overall notion of intelligent multimedia processing. Therefore, the collected papers in this special issue provide a systematic overview and state-of-the-art research in the field of intelligent multimedia processing and analyzing system and outline new developments in fundamental, theorems, approaches, methodologies, software systems, recommendations, and real-world applications in this area. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-05-03T12:30:24Z No. of bitstreams: 1 ijimai6_7_0.pdf: 85925 bytes, checksum: ba27e470d7b795be7800324d985cad96 (MD5); Made available in DSpace on 2022-05-03T12:30:24Z (GMT). No. of bitstreams: 1 ijimai6_7_0.pdf: 85925 bytes, checksum: ba27e470d7b795be7800324d985cad96 (MD5) https://reunir.unir.net/handle/123456789/13004 Imputation of Rainfall Data Using the Sine Cosine Function Fitting Neural Network Chan Chiu, Po; Selamat, Ali; Krejcar, Ondrej; Kuok Kuok, King; Herrera-Viedma, Enrique; Fenza, Giuseppe Missing rainfall data have reduced the quality of hydrological data analysis because they are the essential input for hydrological modeling. Much research has focused on rainfall data imputation. However, the compatibility of precipitation (rainfall) and non-precipitation (meteorology) as input data has received less attention. First, we propose a novel pre-processing mechanism for non-precipitation data by using principal component analysis (PCA). Before the imputation, PCA is used to extract the most relevant features from the meteorological data. The final output of the PCA is combined with the rainfall data from the nearest neighbor gauging stations and then used as the input to the neural network for missing data imputation. Second, a sine cosine algorithm is presented to optimize neural network for infilling the missing rainfall data. The proposed sine cosine function fitting neural network (SC-FITNET) was compared with the sine cosine feedforward neural network (SCFFNN), feedforward neural network (FFNN) and long short-term memory (LSTM) approaches. The results showed that the proposed SC-FITNET outperformed LSTM, SC-FFNN and FFNN imputation in terms of mean absolute error (MAE), root mean square error (RMSE) and correlation coefficient (R), with an average accuracy of 90.9%. This study revealed that as the percentage of missingness increased, the precision of the four imputation methods reduced. In addition, this study also revealed that PCA has potential in pre-processing meteorological data into an understandable format for the missing data imputation. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-05-03T12:26:22Z No. of bitstreams: 1 ijimai6_7_4.pdf: 2067955 bytes, checksum: 2af2444d93e5c0c255b6cad33152c6a1 (MD5); Made available in DSpace on 2022-05-03T12:26:22Z (GMT). No. of bitstreams: 1 ijimai6_7_4.pdf: 2067955 bytes, checksum: 2af2444d93e5c0c255b6cad33152c6a1 (MD5) https://reunir.unir.net/handle/123456789/13003 Integration of Genetic Programming and TABU Search Mechanism for Automatic Detection of Magnetic Resonance Imaging in Cervical Spondylosis Juan, Chun-Jung; Wang, Chen-Shu; Lee, Bo-Yi; Chiang, Shang-Yu; Yeh, Chun-Chang; Cho, Der-Yang; Shen, Wu-Chung Cervical spondylosis is a kind of degenerative disease which not only occurs in elder patients. The age distribution of patients is unfortunately decreasing gradually. Magnetic Resonance Imaging (MRI) is the best tool to confirm the cervical spondylosis severity but it requires radiologist to spend a lot of time for image check and interpretation. In this study, we proposed a prediction model to evaluate the cervical spine condition of patients by using MRI data. Furthermore, to ensure the computing efficiency of the proposed model, we adopted a heuristic programming, genetic programming (GP), to build the core of refereeing engine by combining the TABU search (TS) with the evolutionary GP. Finally, to validate the accuracy of the proposed model, we implemented experiments and compared our prediction results with radiologist’s diagnosis to the same MRI image. The experiment found that using clinical indicators to optimize the TABU list in GP+TABU got better fitness than the other two methods and the accuracy rate of our proposed model can achieve 88% on average. We expected the proposed model can help radiologists reduce the interpretation effort and improve the relationship between doctors and patients. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-05-03T12:05:15Z No. of bitstreams: 1 ijimai6_7_11.pdf: 2984088 bytes, checksum: 9d394359a3de2e44d7cbf1bac731ef61 (MD5); Made available in DSpace on 2022-05-03T12:05:15Z (GMT). No. of bitstreams: 1 ijimai6_7_11.pdf: 2984088 bytes, checksum: 9d394359a3de2e44d7cbf1bac731ef61 (MD5) https://reunir.unir.net/handle/123456789/13002 Modeling of Performance Creative Evaluation Driven by Multimodal Affective Data Wu, Yufeng; Zhang, Longfei; Ding, Gangyi; Xue, Tong; Zhang, Fuquan Performance creative evaluation can be achieved through affective data, and the use of affective featuresto evaluate performance creative is a new research trend. This paper proposes a “Performance Creative—Multimodal Affective (PC-MulAff)” model based on the multimodal affective features for performance creative evaluation. The multimedia data acquisition equipment is used to collect the physiological data of the audience, including the multimodal affective data such as the facial expression, heart rate and eye movement. Calculate affective features of multimodal data combined with director annotation, and defined “Performance Creative—Affective Acceptance (PC-Acc)” based on multimodal affective features to evaluate the quality of performance creative. This paper verifies the PC-MulAff model on different performance data sets. The experimental results show that the PC-MulAff model shows high evaluation quality in different performance forms. In the creative evaluation of dance performance, the accuracy of the model is 7.44% and 13.95% higher than that of the single textual and single video evaluation. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-05-03T11:58:51Z No. of bitstreams: 1 ijimai6_7_9.pdf: 4988076 bytes, checksum: 9c5e1818386608466023e1d750104196 (MD5); Made available in DSpace on 2022-05-03T11:58:51Z (GMT). No. of bitstreams: 1 ijimai6_7_9.pdf: 4988076 bytes, checksum: 9c5e1818386608466023e1d750104196 (MD5) https://reunir.unir.net/handle/123456789/13001 Optimal QoE Scheduling in MPEG-DASH Video Streaming Chang, Shin-Hung; Tsai, Min-Lun; Lee, Meng-Huang; Ho, Jan-Ming DASH is a popular technology for video streaming over the Internet. However, the quality of experience (QoE), a measure of humans’ perceived satisfaction of the quality of these streamed videos, is their subjective opinion, which is difficult to evaluate. Previous studies only considered network-based indices and focused on them to provide smooth video playback instead of improving the true QoE experienced by humans. In this study, we designed a series of click density experiments to verify whether different resolutions could affect the QoE for different video scenes. We observed that, in a single video segment, different scenes with the same resolution could affect the viewer’s QoE differently. It is true that the user’s satisfaction as a result of watching high-resolution video segments is always greater than that when watching low-resolution video segments of the same scenes. However, the most important observation is that low-resolution video segments yield higher viewing QoE gain in slow motion scenes than in fast motion scenes. Thus, the inclusion of more high-resolution segments in the fast motion scenes and more low-resolution segments in the slow motion scenes would be expected to maximize the user’s viewing QoE. In this study, to evaluate the user’s true experience, we convert the viewing QoE into a satisfaction quality score, termed the Q-score, for scenes with different resolutions in each video segment. Additionally, we developed an optimal segment assignment (OSA) algorithm for Q-score optimization in environments characterized by a constrained network bandwidth. Our experimental results show that application of the OSA algorithm to the playback schedule significantly improved users’ viewing satisfaction. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-05-03T11:40:28Z No. of bitstreams: 1 ijimai6_7_7.pdf: 5765364 bytes, checksum: 48622abe49860609c898f21c6f7b9269 (MD5); Made available in DSpace on 2022-05-03T11:40:28Z (GMT). No. of bitstreams: 1 ijimai6_7_7.pdf: 5765364 bytes, checksum: 48622abe49860609c898f21c6f7b9269 (MD5) https://reunir.unir.net/handle/123456789/13000 Modified YOLOv4-DenseNet Algorithm for Detection of Ventricular Septal Defects in Ultrasound Images Chen, Shih-Hsin; Wang, Chun-Wei; Tai, I-Hsin; Weng, Ken-Pen; Chen, Yi-Hui; Hsieh, Kai-Sheng Doctors conventionally analyzed echocardiographic images for diagnosing congenital heart diseases (CHDs). However, this process is laborious and depends on the experience of the doctors. This study investigated the use of deep learning algorithms for the image detection of the ventricular septal defect (VSD), the most common type. Color Doppler echocardiographic images containing three types of VSDs were tested with color doppler ultrasound medical images. To the best of our knowledge, this study is the first one to solve this object detection problem by using a modified YOLOv4–DenseNet framework. Because some techniques of YOLOv4 are not suitable for echocardiographic object detection, we revised the algorithm for this problem. The results revealed that the YOLOv4–DenseNet outperformed YOLOv4, YOLOv3, YOLOv3–SPP, and YOLOv3–DenseNet in terms of metric mAP-50. The F1-score of YOLOv4-DenseNet and YOLOv3-DenseNet were better than those of others. Hence, the contribution of this study establishes the feasibility of using deep learning for echocardiographic image detection of VSD investigation and a better YOLOv4-DenseNet framework could be employed for the VSD detection. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-05-03T11:09:38Z No. of bitstreams: 1 ijimai6_7_10.pdf: 2345492 bytes, checksum: 2425a3a4bbc97ba66c00fefb13bfe324 (MD5); Made available in DSpace on 2022-05-03T11:09:38Z (GMT). No. of bitstreams: 1 ijimai6_7_10.pdf: 2345492 bytes, checksum: 2425a3a4bbc97ba66c00fefb13bfe324 (MD5) https://reunir.unir.net/handle/123456789/12999 Pulmonary Nodule Classification in Lung Cancer from 3D Thoracic CT Scans Using fastai and MONAI Kaliyugarasan, Satheshkumar; Lundervold, Arvid; Lundervold, Alexander Selvikvåg We construct a convolutional neural network to classify pulmonary nodules as malignant or benign in the context of lung cancer. To construct and train our model, we use our novel extension of the fastai deep learning framework to 3D medical imaging tasks, combined with the MONAI deep learning library. We train and evaluate the model using a large, openly available data set of annotated thoracic CT scans. Our model achieves a nodule classification accuracy of 92.4% and a ROC AUC of 97% when compared to a “ground truth” based on multiple human raters subjective assessment of malignancy. We further evaluate our approach by predicting patient-level diagnoses of cancer, achieving a test set accuracy of 75%. This is higher than the 70% obtained by aggregating the human raters assessments. Class activation maps are applied to investigate the features used by our classifier, enabling a rudimentary level of explainability for what is otherwise close to “black box” predictions. As the classification of structures in chest CT scans is useful across a variety of diagnostic and prognostic tasks in radiology, our approach has broad applicability. As we aimed to construct a fully reproducible system that can be compared to new proposed methods and easily be adapted and extended, the full source code of our work is available at https://github.com/MMIV-ML/Lung-CT-fastai-2020. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-05-03T11:00:30Z No. of bitstreams: 1 ijimai6_7_8.pdf: 4159041 bytes, checksum: 2d9ab0ea8671e64fe47a484809bd380d (MD5); Made available in DSpace on 2022-05-03T11:00:30Z (GMT). No. of bitstreams: 1 ijimai6_7_8.pdf: 4159041 bytes, checksum: 2d9ab0ea8671e64fe47a484809bd380d (MD5) https://reunir.unir.net/handle/123456789/12998 A Generalized Wine Quality Prediction Framework by Evolutionary Algorithms Hui-Ye Chiu, Terry; Wu, Chienwen; Chen, Chun-Hao Wine is an exciting and complex product with distinctive qualities that makes it different from other manufactured products. Therefore, the testing approach to determine the quality of wine is complex and diverse. Several elements influence wine quality, but the views of experts can cause the most considerable influence on how people view the quality of wine. The views of experts on quality is very subjective, and may not match the taste of consumer. In addition, the experts may not always be available for the wine testing. To overcome this issue, many approaches based on machine learning techniques that get the attention of the wine industry have been proposed to solve it. However, they focused only on using a particular classifier with a specific set of wine dataset. In this paper, we thus firstly propose the generalized wine quality prediction framework to provide a mechanism for finding a useful hybrid model for wine quality prediction. Secondly, based on the framework, the generalized wine quality prediction algorithm using the genetic algorithms is proposed. It first encodes the classifiers as well as their hyperparameters into a chromosome. The fitness of a chromosome is then evaluated by the average accuracy of the employed classifiers. The genetic operations are performed to generate new offspring. The evolution process is continuing until reaching the stop criteria. As a result, the proposed approach can automatically find an appropriate hybrid set of classifiers and their hyperparameters for optimizing the prediction result and independent on the dataset. At last, experiments on the wine datasets were made to show the merits and effectiveness of the proposed approach. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-05-03T10:36:21Z No. of bitstreams: 1 ijimai6_7_6.pdf: 2091621 bytes, checksum: 8181aed690d44bb4cf32cd015ab0582d (MD5); Made available in DSpace on 2022-05-03T10:36:21Z (GMT). No. of bitstreams: 1 ijimai6_7_6.pdf: 2091621 bytes, checksum: 8181aed690d44bb4cf32cd015ab0582d (MD5) https://reunir.unir.net/handle/123456789/12997 Alzheimer Disease Detection Techniques and Methods: A Review Afzal, Sitara; Maqsood, Muazzam; Khan, Umair; Mehmood, Irfan; Nawaz, Hina; Aadil, Farhan; Song, Oh-Young; Yunyoung, Nam Brain pathological changes linked with Alzheimer's disease (AD) can be measured with Neuroimaging. In the past few years, these measures are rapidly integrated into the signatures of Alzheimer disease (AD) with the help of classification frameworks which are offering tools for diagnosis and prognosis. Here is the review study of Alzheimer's disease based on Neuroimaging and cognitive impairment classification. This work is a systematic review for the published work in the field of AD especially the computer-aided diagnosis. The imaging modalities include 1) Magnetic resonance imaging (MRI) 2) Functional MRI (fMRI) 3) Diffusion tensor imaging 4) Positron emission tomography (PET) and 5) amyloid-PET. The study revealed that the classification criterion based on the features shows promising results to diagnose the disease and helps in clinical progression. The most widely used machine learning classifiers for AD diagnosis include Support Vector Machine, Bayesian Classifiers, Linear Discriminant Analysis, and K-Nearest Neighbor along with Deep learning. The study revealed that the deep learning techniques and support vector machine give higher accuracies in the identification of Alzheimer’s disease. The possible challenges along with future directions are also discussed in the paper. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-05-03T10:29:48Z No. of bitstreams: 1 ijimai6_7_3.pdf: 1256360 bytes, checksum: c7087c8a9916347c36d1dbc9f1985568 (MD5); Made available in DSpace on 2022-05-03T10:29:48Z (GMT). No. of bitstreams: 1 ijimai6_7_3.pdf: 1256360 bytes, checksum: c7087c8a9916347c36d1dbc9f1985568 (MD5) https://reunir.unir.net/handle/123456789/12996 Design and Development of an Energy Efficient Multimedia Cloud Data Center with Minimal SLA Violation Biswas, Nirmal Kr.; Banerjee, Sourav; Biswas, Utpal Multimedia computing (MC) is rising as a nascent computing paradigm to process multimedia applications and provide efficient multimedia cloud services with optimal Quality of Service (QoS) to the multimedia cloud users. But, the growing popularity of MC is affecting the climate. Because multimedia cloud data centers consume an enormous amount of energy to provide services, it harms the environment due to carbon dioxide emissions. Virtual machine (VM) migration can effectively address this issue; it reduces the energy consumption of multimedia cloud data centers. Due to the reduction of Energy Consumption (EC), the Service Level Agreement violation (SLAV) may increase. An efficient VM selection plays a crucial role in maintaining the stability between EC and SLAV. This work highlights a novel VM selection policy based on identifying the Maximum value among the differences of the Sum of Squares Utilization Rate (MdSSUR) parameter to reduce the EC of multimedia cloud data centers with minimal SLAV. The proposed MdSSUR VM selection policy has been evaluated using real workload traces in CloudSim. The simulation result of the proposed MdSSUR VM selection policy demonstrates the rate of improvements of the EC, the number of VM migrations, and the SLAV by 28.37%, 89.47%, and 79.14%, respectively. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-05-03T09:50:01Z No. of bitstreams: 1 ijimai6_7_5.pdf: 1978034 bytes, checksum: d3cbcf721b71de8db1dddea4644721f4 (MD5); Made available in DSpace on 2022-05-03T09:50:01Z (GMT). No. of bitstreams: 1 ijimai6_7_5.pdf: 1978034 bytes, checksum: d3cbcf721b71de8db1dddea4644721f4 (MD5) https://reunir.unir.net/handle/123456789/12995 A Novel Fog Computing Approach for Minimization of Latency in Healthcare using Machine Learning Kishor, Amit; Chakraborty, Chinmay; Jeberson, Wilson In the recent scenario, the most challenging requirements are to handle the massive generation of multimedia data from the Internet of Things (IoT) devices which becomes very difficult to handle only through the cloud. Fog computing technology emerges as an intelligent solution and uses a distributed environment to operate. The objective of the paper is latency minimization in e-healthcare through fog computing. Therefore, in IoT multimedia data transmission, the parameters such as transmission delay, network delay, and computation delay must be reduced as there is a high demand for healthcare multimedia analytics. Fog computing provides processing, storage, and analyze the data nearer to IoT and end-users to overcome the latency. In this paper, the novel Intelligent Multimedia Data Segregation (IMDS) scheme using Machine learning (k-fold random forest) is proposed in the fog computing environment that segregates the multimedia data and the model used to calculate total latency (transmission, computation, and network). With the simulated results, we achieved 92% as the classification accuracy of the model, an approximately 95% reduction in latency as compared with the pre-existing model, and improved the quality of services in e-healthcare. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-05-03T09:22:41Z No. of bitstreams: 1 ijimai6_7_1.pdf: 2233977 bytes, checksum: 28018ceafc10d13be7a3337606e0dd14 (MD5); Made available in DSpace on 2022-05-03T09:22:41Z (GMT). No. of bitstreams: 1 ijimai6_7_1.pdf: 2233977 bytes, checksum: 28018ceafc10d13be7a3337606e0dd14 (MD5) https://reunir.unir.net/handle/123456789/12994 An Enhanced Texture-Based Feature Extraction Approach for Classification of Biomedical Images of CT-Scan of Lungs Srivastava, Varun; Gupta, Shilp; Chaudhary, Gopal; Balodi, Arun; Khari, Manju; García-Díaz, Vicente Content Based Image Retrieval (CBIR) techniques based on texture have gained a lot of popularity in recent times. In the proposed work, a feature vector is obtained by concatenation of features extracted from local mesh peak valley edge pattern (LMePVEP) technique; a dynamic threshold based local mesh ternary pattern technique and texture of the image in five different directions. The concatenated feature vector is then used to classify images of two datasets viz. Emphysema dataset and Early Lung Cancer Action Program (ELCAP) lung database. The proposed framework has improved the accuracy by 12.56%, 9.71% and 7.01% in average for data set 1 and 9.37%, 8.99% and 7.63% in average for dataset 2 over three popular algorithms used for image retrieval. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2022-05-03T09:07:16Z No. of bitstreams: 1 ijimai6_7_2.pdf: 1271084 bytes, checksum: 0aa7a702bd7f3d0dcc56163946b02a5a (MD5); Made available in DSpace on 2022-05-03T09:07:16Z (GMT). No. of bitstreams: 1 ijimai6_7_2.pdf: 1271084 bytes, checksum: 0aa7a702bd7f3d0dcc56163946b02a5a (MD5)