Pub Date : 2018-07-31DOI: 10.1109/ICTC.2017.8191001
Aslina Baharum, S. A. Pitchay, Rozita Ismail, Noor Fazlinda Fabeil, Nordaliela Mohd. Rusli, I. A. A. Bahar
It can be seen that, conflicts, negative revolution, suicides, and other crimes becoming more common worldwide. Several studies and investigations have been conducted due to this case. Thus, it has been found that one of the root cause is stress, especially among the youth. Although stress can improve work performance and awareness for those who can manage it properly, however if someone is unable to cope with the stressful situation when it becomes excessive, the reaction might be disastrous. In tackling this unfavourable situation, several lifestyle changes have been prescribed such as listening to music, physical activities, doing desired activities, surfing, and others. This study uses the power of music to reduce stress. A mobile application named as “DeMuse” was developed and in its development, Mobile-D step-by-step methodology was applied. At explore phase, a number of existing applications have been compared. At the second phase, the initialize stage, a quantitative analysis was carried out to study the music and mood categories respectively. During the third and fourth phases, which were Productionize and Stabilise, the completion of Data Flow Diagram and Entity Relationship Diagram were established based on the quantitative analysis done. In the final phase, the System Test and Fix, the prototype were reviewed by 148 potential users. DeMuse showed to be one of the alternative ways to relieve stress. From this finding, DeMuse highlight the main feature which is the music and mood categories. In conclusion, DeMuse is a valid mobile apps that could be used to help reduce stress of its user. With this app, it hopes greatly to help in decreasing and eliminating the tension, dissatisfaction, and others negative feelings of users in their daily life.
{"title":"Demuse: Releasing stress using music mobile application","authors":"Aslina Baharum, S. A. Pitchay, Rozita Ismail, Noor Fazlinda Fabeil, Nordaliela Mohd. Rusli, I. A. A. Bahar","doi":"10.1109/ICTC.2017.8191001","DOIUrl":"https://doi.org/10.1109/ICTC.2017.8191001","url":null,"abstract":"It can be seen that, conflicts, negative revolution, suicides, and other crimes becoming more common worldwide. Several studies and investigations have been conducted due to this case. Thus, it has been found that one of the root cause is stress, especially among the youth. Although stress can improve work performance and awareness for those who can manage it properly, however if someone is unable to cope with the stressful situation when it becomes excessive, the reaction might be disastrous. In tackling this unfavourable situation, several lifestyle changes have been prescribed such as listening to music, physical activities, doing desired activities, surfing, and others. This study uses the power of music to reduce stress. A mobile application named as “DeMuse” was developed and in its development, Mobile-D step-by-step methodology was applied. At explore phase, a number of existing applications have been compared. At the second phase, the initialize stage, a quantitative analysis was carried out to study the music and mood categories respectively. During the third and fourth phases, which were Productionize and Stabilise, the completion of Data Flow Diagram and Entity Relationship Diagram were established based on the quantitative analysis done. In the final phase, the System Test and Fix, the prototype were reviewed by 148 potential users. DeMuse showed to be one of the alternative ways to relieve stress. From this finding, DeMuse highlight the main feature which is the music and mood categories. In conclusion, DeMuse is a valid mobile apps that could be used to help reduce stress of its user. With this app, it hopes greatly to help in decreasing and eliminating the tension, dissatisfaction, and others negative feelings of users in their daily life.","PeriodicalId":53606,"journal":{"name":"Journal of Theoretical and Applied Information Technology","volume":"4 1","pages":"4624-4648"},"PeriodicalIF":0.0,"publicationDate":"2018-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76359687","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}
We present a modified Temporal Deep Belief Networks (TDBN) for human motion analysis and synthesis by incorporating Sparse Encoding Symmetric Machines (SESM) improvement on its pre-training. SESM consisted of two important terms: regularization and sparsity. In this paper, we measure the effect of these two terms on the smoothness of synthesized (or generated) motion. The smoothness is measured as the standard deviation of five bones movements with three motion transitions. We also address how these two terms influence the free energy and reconstruction error profiles during pre-training of the Restricted Boltzmann Machines (RBM) layers and the Conditional RBM (CRBM) layers. For this purpose, we compare gait transitions by bifurcation experiments using four different TDBN settings: original TDBN; modified-TDBN(R): a TDBN with only regularization constraint; modified-TDBN(S): a TDBN with only sparsity constraint; and modified-TDBN(R+S): a TDBN with regularization plus sparsity constraints. These experiments shows that the modified-TDBN(R+S) reaches lower energy faster in RBM pre-training and reach lower reconstruction error in the CRBM training. Even though the smoothness of the synthesized motion from the modified-TDBN approaches is slightly less smooth than the original TDBN, they are more responsive to the action command to change a motion (from run to walk or vice versa) while preserving the smoothness during motion transitions without incurring much overhead computation time.
{"title":"A SPARSE ENCODING SYMMETRIC MACHINES PRE-TRAINING FOR TEMPORAL DEEP BELIEF NETWORKS FOR MOTION ANALYSIS AND SYNTHESIS","authors":"M. N. Shoumi, M. I. Fanany","doi":"10.5281/ZENODO.34149","DOIUrl":"https://doi.org/10.5281/ZENODO.34149","url":null,"abstract":"We present a modified Temporal Deep Belief Networks (TDBN) for human motion analysis and synthesis by incorporating Sparse Encoding Symmetric Machines (SESM) improvement on its pre-training. SESM consisted of two important terms: regularization and sparsity. In this paper, we measure the effect of these two terms on the smoothness of synthesized (or generated) motion. The smoothness is measured as the standard deviation of five bones movements with three motion transitions. We also address how these two terms influence the free energy and reconstruction error profiles during pre-training of the Restricted Boltzmann Machines (RBM) layers and the Conditional RBM (CRBM) layers. For this purpose, we compare gait transitions by bifurcation experiments using four different TDBN settings: original TDBN; modified-TDBN(R): a TDBN with only regularization constraint; modified-TDBN(S): a TDBN with only sparsity constraint; and modified-TDBN(R+S): a TDBN with regularization plus sparsity constraints. These experiments shows that the modified-TDBN(R+S) reaches lower energy faster in RBM pre-training and reach lower reconstruction error in the CRBM training. Even though the smoothness of the synthesized motion from the modified-TDBN approaches is slightly less smooth than the original TDBN, they are more responsive to the action command to change a motion (from run to walk or vice versa) while preserving the smoothness during motion transitions without incurring much overhead computation time.","PeriodicalId":53606,"journal":{"name":"Journal of Theoretical and Applied Information Technology","volume":"1 1","pages":"86-93"},"PeriodicalIF":0.0,"publicationDate":"2015-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88944922","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}
Visual tracking in mobile robots have to track various target objects in fast processing, but existing state-of-the-art methods only use specific image feature which only suitable for certain target objects. In this paper, we proposed new approach without depend on specific feature. By using deep learning, we can learn essential features of many of the objects and scenes found in the real world. Furthermore, fast visual tracking can be achieved by using Extreme Learning Machine (ELM). The developed tracking algorithm is based on bootstrap particle filter. Thus the observation model of particle filter is enhanced into two steps: offline training step and online tracking step. The offline training stage is carried out by training one kind of deep learning techniques: Stacked Denoising Autoencoder (SDAE) with auxiliary image data. During the online tracking process, an additional classification layer based on ELM is added to the encoder part of the trained. Using experiments, we found (i) the specific feature is only suitable for certain target objects (ii) the running time of the tracking algorithm can be improved by using ELM with regularization and intensity adjustment in online step, (iii) dynamic model is crucial for object tracking, especially when adjusting the diagonal covariance matrix values. Preliminary experimental results are provided. The algorithm is still restricted to track single object and will extend to track multiple object and will enhance by creating the advanced dynamic model. These are remaining for our future works.
{"title":"DEEP EXTREME TRACKER BASED ON BOOTSTRAP PARTICLE FILTER","authors":"A. A. Gunawan, M. I. Fanany, W. Jatmiko","doi":"10.5281/ZENODO.18603","DOIUrl":"https://doi.org/10.5281/ZENODO.18603","url":null,"abstract":"Visual tracking in mobile robots have to track various target objects in fast processing, but existing state-of-the-art methods only use specific image feature which only suitable for certain target objects. In this paper, we proposed new approach without depend on specific feature. By using deep learning, we can learn essential features of many of the objects and scenes found in the real world. Furthermore, fast visual tracking can be achieved by using Extreme Learning Machine (ELM). The developed tracking algorithm is based on bootstrap particle filter. Thus the observation model of particle filter is enhanced into two steps: offline training step and online tracking step. The offline training stage is carried out by training one kind of deep learning techniques: Stacked Denoising Autoencoder (SDAE) with auxiliary image data. During the online tracking process, an additional classification layer based on ELM is added to the encoder part of the trained. Using experiments, we found (i) the specific feature is only suitable for certain target objects (ii) the running time of the tracking algorithm can be improved by using ELM with regularization and intensity adjustment in online step, (iii) dynamic model is crucial for object tracking, especially when adjusting the diagonal covariance matrix values. Preliminary experimental results are provided. The algorithm is still restricted to track single object and will extend to track multiple object and will enhance by creating the advanced dynamic model. These are remaining for our future works.","PeriodicalId":53606,"journal":{"name":"Journal of Theoretical and Applied Information Technology","volume":"9 1","pages":"857-863"},"PeriodicalIF":0.0,"publicationDate":"2014-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82784563","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}
Visual tracking is the problem of using visual sensor measurements to determine location and path of target object. One of big challenges for visual tracking is full occlusion. When full occlusions are present, image data alone can be unreliable, and is not sufficient to detect the target object. The developed tracking algorithm is based on bootstrap particle filter and using color feature target. Furthermore the algorithm is modified using nonretinotopic concept, inspired from the way of human visual cortex handles occlusion by constructing nonretinotopic layers. We interpreted the concept by using past tracking memory about motion dynamics rather than current measurement when quality level of tracking reliability below a threshold. Using experiments, we found (i) the performance of the object tracking algorithm in handling occlusion can be improved using nonretinotopic concept, (ii) dynamic model is crucial for object tracking, especially when the target object experienced occlusion and maneuver motions, (iii) the dependency of the tracker performance on the accuracy of tracking quality threshold when facing illumination challenge. Preliminary experimental results are provided.
{"title":"Nonretinotopic Particle Filter for Visual Tracking","authors":"A. A. Gunawan, Ito Wasito","doi":"10.5281/ZENODO.18601","DOIUrl":"https://doi.org/10.5281/ZENODO.18601","url":null,"abstract":"Visual tracking is the problem of using visual sensor measurements to determine location and path of target object. One of big challenges for visual tracking is full occlusion. When full occlusions are present, image data alone can be unreliable, and is not sufficient to detect the target object. The developed tracking algorithm is based on bootstrap particle filter and using color feature target. Furthermore the algorithm is modified using nonretinotopic concept, inspired from the way of human visual cortex handles occlusion by constructing nonretinotopic layers. We interpreted the concept by using past tracking memory about motion dynamics rather than current measurement when quality level of tracking reliability below a threshold. Using experiments, we found (i) the performance of the object tracking algorithm in handling occlusion can be improved using nonretinotopic concept, (ii) dynamic model is crucial for object tracking, especially when the target object experienced occlusion and maneuver motions, (iii) the dependency of the tracker performance on the accuracy of tracking quality threshold when facing illumination challenge. Preliminary experimental results are provided.","PeriodicalId":53606,"journal":{"name":"Journal of Theoretical and Applied Information Technology","volume":"14 1","pages":"104-111"},"PeriodicalIF":0.0,"publicationDate":"2014-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87263065","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 : 2011-11-01DOI: 10.14257/ijgdc.2016.9.7.16
A. Yousif, A. Abdullah, S. Nor, A. Abdelaziz
Scheduling jobs on computational grids is identified as NP-complete problem due to the heterogeneity of resources; the resources belong to different administrative domains and apply different management policies. This paper presents a novel metaheuristics method based on Firefly Algorithm (FA) for scheduling jobs on grid computing. The proposed method is to dynamically create an optimal schedule to complete the jobs within minimum makespan. The proposed method is compared with other heuristic methods using simple and different simulation scenarios. Each firefly represents a candidate solution of the grid scheduling problem in a vector form, with n elements; where n is the number of jobs to be scheduled. Firefly[i] specifies the resource to which the job number i is allocated. Therefore, the vector values are natural numbers. Also we note that the vector values are the resource IDs and hence the resource ID may appear more than one time in the firefly vector. This comes about because more than one job may be allocated to the same resource. To evaluate the effectiveness and the efficiency of job scheduling algorithms on computational grid, it is difficult and impractical to achieve performance assessment experimentally in such large scale heterogeneous system and to repeat and control the experiments to perform different scenarios. To encounter this limitation this research used mathematical modeling and simulation to model and evaluate the proposed mechanism. The results demonstrated that, the firefly scheduling mechanism achieved less makespan time than Min-Min and Max- Min heuristics in several scheduling scenarios. The results in this paper showed that the FA is promising method that can be used to optimize scheduling jobs on grid computing.
{"title":"Scheduling jobs on grid computing using firefly algorithm","authors":"A. Yousif, A. Abdullah, S. Nor, A. Abdelaziz","doi":"10.14257/ijgdc.2016.9.7.16","DOIUrl":"https://doi.org/10.14257/ijgdc.2016.9.7.16","url":null,"abstract":"Scheduling jobs on computational grids is identified as NP-complete problem due to the heterogeneity of resources; the resources belong to different administrative domains and apply different management policies. This paper presents a novel metaheuristics method based on Firefly Algorithm (FA) for scheduling jobs on grid computing. The proposed method is to dynamically create an optimal schedule to complete the jobs within minimum makespan. The proposed method is compared with other heuristic methods using simple and different simulation scenarios. Each firefly represents a candidate solution of the grid scheduling problem in a vector form, with n elements; where n is the number of jobs to be scheduled. Firefly[i] specifies the resource to which the job number i is allocated. Therefore, the vector values are natural numbers. Also we note that the vector values are the resource IDs and hence the resource ID may appear more than one time in the firefly vector. This comes about because more than one job may be allocated to the same resource. To evaluate the effectiveness and the efficiency of job scheduling algorithms on computational grid, it is difficult and impractical to achieve performance assessment experimentally in such large scale heterogeneous system and to repeat and control the experiments to perform different scenarios. To encounter this limitation this research used mathematical modeling and simulation to model and evaluate the proposed mechanism. The results demonstrated that, the firefly scheduling mechanism achieved less makespan time than Min-Min and Max- Min heuristics in several scheduling scenarios. The results in this paper showed that the FA is promising method that can be used to optimize scheduling jobs on grid computing.","PeriodicalId":53606,"journal":{"name":"Journal of Theoretical and Applied Information Technology","volume":"21 1","pages":"155-164"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84350551","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：