2021 IEEE 17th International Colloquium on Signal Processing & Its Applications (CSPA)最新文献_第2页

Reinforcement Learning for Robotic Applications with Vision Feedback 基于视觉反馈的机器人强化学习应用

2021 IEEE 17th International Colloquium on Signal Processing & Its Applications (CSPA) Pub Date : 2021-03-05 DOI: 10.1109/CSPA52141.2021.9377292

Hatem Fahd Al-Selwi, A. Aziz, F. S. Abas, Z. Zyada

{"title":"Reinforcement Learning for Robotic Applications with Vision Feedback","authors":"Hatem Fahd Al-Selwi, A. Aziz, F. S. Abas, Z. Zyada","doi":"10.1109/CSPA52141.2021.9377292","DOIUrl":"https://doi.org/10.1109/CSPA52141.2021.9377292","url":null,"abstract":"The presence of robots in our daily life is becoming more common, where robots start carrying out more complex tasks. This increase in the complexity of tasks makes conventional control system insufficient. Therefore, a plausible approach is required for robots to learn how to perform these tasks. Reinforcement learning enables robots to perform complex tasks without highly engineered control systems. However, using reinforcement learning in robotic applications is challenged by several problems such as high dimensionality. Thus, in this paper, we study the performance of the Hindsight Experience Replay (HER) algorithm which addresses the high dimensionality problem. In this paper, we analyze the algorithm performance using a simulated robotic arm to pick and place different objects. Then, we propose the use of vision feedback which is used to control the gripper of the robotic arm. The results and analysis highlights some of HER limitations when dealing with objects that have limited grasping points. Our proposed method allows the robotic arm to pick objects using the same trained policy without the need to retrain the agent for new objects. Finally, we prove that using our method the robotic arm can pick the objects with higher success rate compared to the one without vision feedback.","PeriodicalId":194655,"journal":{"name":"2021 IEEE 17th International Colloquium on Signal Processing & Its Applications (CSPA)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125035493","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}

引用次数: 1

Fuzzy PD and Fuzzy $text{PD}+mathrm{I}$ Controllers Design for Attitude Control of Innovative Nano-Satellite 新型纳米卫星姿态控制的模糊PD和模糊$text{PD}+ mathm {I}$控制器设计

2021 IEEE 17th International Colloquium on Signal Processing & Its Applications (CSPA) Pub Date : 2021-03-05 DOI: 10.1109/CSPA52141.2021.9377271

Ali H. Hazza, M. Y. Mashor, M. Mahdi

引用次数: 0

BDNF (Brain-Derived Neurotrophic Factor) Mediated Presynaptic Neuronal Signal from the Inhibitory Setting of Cortical Pyramidal Neurons Recorded from Brain Slices 脑源性神经营养因子介导的皮层锥体神经元抑制性突触前信号的脑切片记录

2021 IEEE 17th International Colloquium on Signal Processing & Its Applications (CSPA) Pub Date : 2021-03-05 DOI: 10.1109/CSPA52141.2021.9377273

T. Begum, H. Alzahrani, F. Reza, N. Shafin, Mohd Harizal Senik Nawi, Y. Yoshimura

{"title":"BDNF (Brain-Derived Neurotrophic Factor) Mediated Presynaptic Neuronal Signal from the Inhibitory Setting of Cortical Pyramidal Neurons Recorded from Brain Slices","authors":"T. Begum, H. Alzahrani, F. Reza, N. Shafin, Mohd Harizal Senik Nawi, Y. Yoshimura","doi":"10.1109/CSPA52141.2021.9377273","DOIUrl":"https://doi.org/10.1109/CSPA52141.2021.9377273","url":null,"abstract":"BDNF (brain-derived neurotrophic factor) has a tremendous effect on GABAergic synaptic transmission in the developing and adult central nervous system. Paired pulse stimuli are the common way to observe the paired-pulse ratio (PPR) that is the indicator of presynaptic transmission. During paired-pulse stimuli, the second response might be larger or smaller than the first one. To investigate BDFN induced presynaptic signal in the inhibitory neuron of the visual cortex, we used whole-cell patch-clamp recordings from the pyramidal neurons of mice visual cortex and studied signals evoked by paired-pulse stimuli. A total of seven mice brain slices were prepared for this study. AP5 and NBQX were added in artificial cerebrospinal fluid (aCSF) to block NMDA and non-NMDA receptors, respectively. Three levels of BDNF concentrations were used to see the effect of BDNF on GABAergic synaptic release; 0 ng/ml, 20 ng/ml, and 100 ng/ml of BDNF concentrations. Inhibitory postsynaptic currents as IPSC1 and IPSC2 were recorded after paired-pulse stimuli in the pyramidal neurons during all three conditions. PPR was measured as IPSC2/IPSC1. PPRs were compared among groups to see the significant differences. There were no significant differences between 0 ng/ml vs 20 ng/ml, 0 ng/ml vs 100 ng/ml and 20 ng/ml vs 100 ng/ml of BDNF concentrations. However, there was a tendency of reducing PPR during 20 & 100 ng/ml of BDNF concentration compare to 0 ng/ml might indicate diminished presynaptic transmitter releases. These results may suggest that BDNF has no activity-independent effect on the PPR of transmitter release at visual cortical inhibitory synapses.","PeriodicalId":194655,"journal":{"name":"2021 IEEE 17th International Colloquium on Signal Processing & Its Applications (CSPA)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126030375","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}

引用次数: 0

Evaluating the Masked and Unmasked Face with LeNet Algorithm 用LeNet算法评估被屏蔽面和未被屏蔽面

2021 IEEE 17th International Colloquium on Signal Processing & Its Applications (CSPA) Pub Date : 2021-03-05 DOI: 10.1109/CSPA52141.2021.9377283

Muhammad Haziq Rusli, N. N. A. Sjarif, S. Yuhaniz, Steven Kok, Muhammad Solihin Kadir

{"title":"Evaluating the Masked and Unmasked Face with LeNet Algorithm","authors":"Muhammad Haziq Rusli, N. N. A. Sjarif, S. Yuhaniz, Steven Kok, Muhammad Solihin Kadir","doi":"10.1109/CSPA52141.2021.9377283","DOIUrl":"https://doi.org/10.1109/CSPA52141.2021.9377283","url":null,"abstract":"Face recognition is a biometric technique that has been widely used in many fields. Most of the face recognition applications are used in the security and surveillance system. However, due to current pandemic, wearing facemasks is an obligation for everybody in public places. Hence, face recognition will encounter a problem such as extracting the facial features due to blockage caused by the facemasks. Thus, it will lower down the recognition rate level. The collected dataset consists of two categories which is masked face and unmasked face. This dataset called FaceMask Dataset was obtained from kaggle website. The Multi-Task Cascaded Neural Network (MTCNN) was used to find the face region in the dataset, and it will undergo image feature extraction and remove the undetected face as to prepare a proper training dataset before it can be trained by using LeNet algorithm. As the result, the categories in this work are fall into two classes, which masked face and unmasked face. The training accuracy was 98.21% and it will focus on the features on each result and will justify the difference between the accuracy for both classes. The proposed method was able to achieve 98.21% accuracy with LeNet algorithm as the face image was mainly focused on the face area without taking full size of the image.","PeriodicalId":194655,"journal":{"name":"2021 IEEE 17th International Colloquium on Signal Processing & Its Applications (CSPA)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127857277","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}

引用次数: 6

Technical and Organizational Facilitating Conditions — The Antecedent Factors and Impact on the Intention to Use ERP System in Libyan Universities 技术和组织便利条件——利比亚大学使用ERP系统意愿的先行因素和影响

2021 IEEE 17th International Colloquium on Signal Processing & Its Applications (CSPA) Pub Date : 2021-03-05 DOI: 10.1109/CSPA52141.2021.9377305

Slem Emhmed, Omar Ismael Al-Sanjary, Adam Amril Jaharadak, S. Aldulaimi, Mohammed HazimAlkawaz

{"title":"Technical and Organizational Facilitating Conditions — The Antecedent Factors and Impact on the Intention to Use ERP System in Libyan Universities","authors":"Slem Emhmed, Omar Ismael Al-Sanjary, Adam Amril Jaharadak, S. Aldulaimi, Mohammed HazimAlkawaz","doi":"10.1109/CSPA52141.2021.9377305","DOIUrl":"https://doi.org/10.1109/CSPA52141.2021.9377305","url":null,"abstract":"The aim of this paper is to investigate the precedence factors of technical facilitating conditions and organizational facilitating conditions and their antecedent impact on the intention to use the enterprise resource planning (ERP) system in the Libyan Universities. Many HEIs have turned to Enterprise Resource Planning (ERP) systems in the hope of helping them to improve their performance. The proposed model is partly dependent upon the third version UTAUT model of Venkatesh (2016). The dependent variable – intention to use ERP – is added besides splitting facilitating conditions into two variables, technical facilitating conditions, and organizational facilitating conditions. The precedence factors of technical facilitating conditions are IT infrastructure, IT unit professionalism, and IT vendors' professionalism, and the precedence factors of organizational facilitating conditions are HR-IT capacity, financial capacity, and managerial support. The target population is the staff of universities in Tripoli, Libya; and the sample size is 382. The results show that the three precedencies of technical facilitating conditions have significant relationships where IT infrastructure have the highest impact; the three precedencies of organizational facilitating conditions have significant relationships where managerial support have the highest impact, and both the two facilitating condition variables have a significant influence on the intention to use ERP.","PeriodicalId":194655,"journal":{"name":"2021 IEEE 17th International Colloquium on Signal Processing & Its Applications (CSPA)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114512929","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}

引用次数: 7

Intervention Support Program for Students at Risk of Dropping Out Using Fuzzy Logic-Based Prescriptive Analytics 基于模糊逻辑的规范分析对有辍学风险学生的干预支持计划

2021 IEEE 17th International Colloquium on Signal Processing & Its Applications (CSPA) Pub Date : 2021-03-05 DOI: 10.1109/CSPA52141.2021.9377304

Cindy G. de Jesus, Mark Kristian C. Ledda

{"title":"Intervention Support Program for Students at Risk of Dropping Out Using Fuzzy Logic-Based Prescriptive Analytics","authors":"Cindy G. de Jesus, Mark Kristian C. Ledda","doi":"10.1109/CSPA52141.2021.9377304","DOIUrl":"https://doi.org/10.1109/CSPA52141.2021.9377304","url":null,"abstract":"Education is perceived to be an inevitable impact in building one's nation and presumed to be a significant factor of one's success. However, the issue with increasing school dropouts in secondary schools continue to persist worldwide. This study aimed to design and develop an intervention support program for students at risk of dropping using prescriptive analytics for the Department of Education. Factors affecting students to drop include family, individual, community and school related factors were identified. Based from these factors, appropriate types of intervention programs were determined through focus group discussions with secondary school teachers and guidance counselors. A web-based intervention support program system was developed with the use of Fuzzy Logic-Based prescriptive analytics. First, the system predicts students at risk of dropping out through the identified factors as inputs. Second, based from the results of the prediction, the system's fuzzy inference mechanism determines both the intervention applicability and effectivity to provide suitable intervention prescription as the system's final output. Results show that students who are at risk of dropping out can be identified earlier with the correct inputs in the developed system and appropriate interventions vary from one student to another. Thus, making the study useful in addressing the issue with increasing school dropouts by prescribing suitable intervention programs.","PeriodicalId":194655,"journal":{"name":"2021 IEEE 17th International Colloquium on Signal Processing & Its Applications (CSPA)","volume":"28 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128335315","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}

引用次数: 0

Enhanced Ensemble Models for Predictive Modeling: A Conceptual Framework 用于预测建模的增强集成模型:一个概念框架

2021 IEEE 17th International Colloquium on Signal Processing & Its Applications (CSPA) Pub Date : 2021-03-05 DOI: 10.1109/CSPA52141.2021.9377299

Janson Luke Ong Wai Kit, V. Asirvadam, M. Hassan

引用次数: 2

Early Detection of Single-Phase Induction Motor Failure through the use of Accelerometer and Temperature Sensor via Arduino 通过Arduino使用加速度计和温度传感器对单相感应电机故障进行早期检测

2021 IEEE 17th International Colloquium on Signal Processing & Its Applications (CSPA) Pub Date : 2021-03-05 DOI: 10.1109/CSPA52141.2021.9377285

Erick V. Alviento, Jeferson B. Cabais, Juan Miguel M. Fajardo, Ramon G. Garcia, A. Ballado

引用次数: 0

Determination of the Separability Criterion of the Singular Spectrum Analysis Based Sinusoidal Components Extraction Technique 基于奇异谱分析的正弦分量提取技术可分离性准则的确定

2021 IEEE 17th International Colloquium on Signal Processing & Its Applications (CSPA) Pub Date : 2021-03-05 DOI: 10.1109/CSPA52141.2021.9377280

Shuvashis Banerjee, M. Hasan

{"title":"Determination of the Separability Criterion of the Singular Spectrum Analysis Based Sinusoidal Components Extraction Technique","authors":"Shuvashis Banerjee, M. Hasan","doi":"10.1109/CSPA52141.2021.9377280","DOIUrl":"https://doi.org/10.1109/CSPA52141.2021.9377280","url":null,"abstract":"In singular spectrum analysis based sinusoidal component extraction of the sensor signal, the separability criterion for the elementary component indicates the quality of estimation. In this article, the effects of window length of singular spectrum analysis have been investigated on the separability of the components. The separability has been evaluated numerically based on the correlations of these elementary components. For the illustration of the effects of variation window length on the separability, Bangla vowel (/a/) stimulated EEG signals have been captured from forty persons. The elementary components are estimated from the eigenvectors and eigenvalues of the singular spectrum components. For the window length 100, 110, ….250 samples, these are calculated from the experimentally captured signals. From the group of eigenvalue distributions, the mean and variance distributions are also determined for the abovementioned window lengths. The ranges of first, second, and third eigenvalues are 10.939% −10.059%, 7.819%-6.853%, and 6.864%-6.069% respectively. The variation of first eigenvalue increases with window length but variations of second and third eigenvalues have opposite tendencies. The minimum value of the mean correlation coefficient is obtained at window length of 210 samples which refers the optimal length for the proper sinusoidal component extraction.","PeriodicalId":194655,"journal":{"name":"2021 IEEE 17th International Colloquium on Signal Processing & Its Applications (CSPA)","volume":"9 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116788762","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}

引用次数: 0

Image Copy-Move Forgery Detection Algorithms Based on Spatial Feature Domain 基于空间特征域的图像复制-移动伪造检测算法

2021 IEEE 17th International Colloquium on Signal Processing & Its Applications (CSPA) Pub Date : 2021-03-05 DOI: 10.1109/CSPA52141.2021.9377272

I. T. Ahmed, B. T. Hammad, N. Jamil

{"title":"Image Copy-Move Forgery Detection Algorithms Based on Spatial Feature Domain","authors":"I. T. Ahmed, B. T. Hammad, N. Jamil","doi":"10.1109/CSPA52141.2021.9377272","DOIUrl":"https://doi.org/10.1109/CSPA52141.2021.9377272","url":null,"abstract":"Currently, digital image forgery (DIF) become more active due to the advent of powerful image processing tools. On a daily, many images are exchanged through the internet, which makes them susceptible to such effects. One of the most popular of the passive image forgery techniques is copy-move forgery. In the Copy-move forgery, the basic process is copy/paste from one area to another in the same image. In this paper, the proposed image copy-move forgery detection (IC-MFDs) involves five stages: image preprocessing, dividing the image into overlapping blocks, calculating the mean and standard deviation of each block, feature vectors are then sorted lexicographically, then feeding the feature vector to the Support Vector Machine (SVM) classifier to identify the image as authentic or forged. Experiments are performed on a standard dataset of copy move forged images MICC-F220 to evaluate the proposed technique. The findings indicate that the proposed IC-MFDs can be extremely accurate in terms of Detection Accuracy (98.44). We also compare some state-of-the-art approaches with our proposed IC-MFDs. It's noted that the findings obtained are better than these approaches.","PeriodicalId":194655,"journal":{"name":"2021 IEEE 17th International Colloquium on Signal Processing & Its Applications (CSPA)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129121284","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}

引用次数: 10