2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS)最新文献_第3页

A security aware scheduling in fog computing by hyper heuristic algorithm 基于超启发式算法的雾计算安全感知调度

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-12-01 DOI: 10.1109/ICSPIS.2017.8311595

Dadmehr Rahbari, Sabihe Kabirzadeh, M. Nickray

{"title":"A security aware scheduling in fog computing by hyper heuristic algorithm","authors":"Dadmehr Rahbari, Sabihe Kabirzadeh, M. Nickray","doi":"10.1109/ICSPIS.2017.8311595","DOIUrl":"https://doi.org/10.1109/ICSPIS.2017.8311595","url":null,"abstract":"Fog computing provides a new architecture for the implementation of the Internet of Things (IoT), which can connect sensor nodes to the cloud using the edge of the network. This structure has improved the latency and energy consumption in the cloud. In this heterogeneous and distributed environment, resource allocation is very important. Hence, scheduling will be a challenge to increase productivity and allocate resources appropriately to the tasks. Programs that run in this environment should be protected from intruders. We consider three parameters as authentication, integrity, and confidentiality to maintain security in fog devices. These parameters have time and computational overhead. In the proposed approach, we schedule the modules for the run in fog devices by heuristic algorithms based on data mining technique. The objective function is included CPU utilization, bandwidth, and security overhead. We compare the proposed algorithm with several heuristic algorithms. The results show that our proposed algorithm improved the average energy consumption of 63.27%, cost 44.71% relative to the PSO, ACO, SA algorithms.","PeriodicalId":380266,"journal":{"name":"2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116186212","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: 23

A weighted denoising auto-encoder applied to Mel sub-bands for robust speech recognition 一种应用于Mel子带的加权去噪自编码器用于鲁棒语音识别

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-12-01 DOI: 10.1109/ICSPIS.2017.8311586

Faezeh Baniardalan, A. Akbari, B. Nasersharif

引用次数: 2

Sparse representation and convolutional neural networks for 3D human pose estimation 基于稀疏表示和卷积神经网络的三维人体姿态估计

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-12-01 DOI: 10.1109/ICSPIS.2017.8311614

H. Alikarami, F. Yaghmaee, Mohammad Javad Fadaeieslam

引用次数: 1

Seizure prediction using EEG segmentation change points 基于脑电分割变化点的癫痫发作预测

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-12-01 DOI: 10.1109/ICSPIS.2017.8311582

N. Ghasemi, M. Mosavi

引用次数: 3

A content-based movie recommender system based on temporal user preferences 基于时间用户偏好的基于内容的电影推荐系统

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-12-01 DOI: 10.1109/ICSPIS.2017.8311601

B. R. Cami, H. Hassanpour, H. Mashayekhi

引用次数: 31

Speed up biological inspired object recognition, HMAX 加速生物启发的物体识别，HMAX

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-12-01 DOI: 10.1109/ICSPIS.2017.8311613

H. Sufikarimi, K. Mohammadi

{"title":"Speed up biological inspired object recognition, HMAX","authors":"H. Sufikarimi, K. Mohammadi","doi":"10.1109/ICSPIS.2017.8311613","DOIUrl":"https://doi.org/10.1109/ICSPIS.2017.8311613","url":null,"abstract":"In this paper, a new approach is proposed to accelerate the process of a biologically inspired object recognition method called HMAX. The HMAX is an effective object recognition method which is inspired by mammalian visual systems. Despite achieving a relatively good classification rate, this model needs many computing resources and a rather high volume of temporary memory during its process. High computational load and low processing speed is a big challenge in this algorithm. Due to randomly feature extraction, many redundant features might be extracted which causes an extremely increment in calculations and processing time. To tackle this problem, a feature selection strategy based on filter method is added to the standard HMAX. By eliminating redundant and selecting distinctive features, the new proposed HMAX achieves the same accuracy rate as the previous HMAX resulted whereas it is faster more than three times than the standard HMAX. Suggested approach plays an elegant role in processing speed, especially when the number of extracted features is relatively high. The standard HMAX and the proposed one are evaluated on the Caltech5 dataset. The experiments show that the proposed manner reaches the same accuracy rate as the standard HMAX, even though near 79% of the extracted patches were removed. Although feature selection stage imposes a little computational load on the algorithm, it provides us to accelerate process up to 3.3X times higher than the speed of standard HMAX. This method is very suitable for implementation especially on limited resources such as FPGA platform and DSP processors.","PeriodicalId":380266,"journal":{"name":"2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS)","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134426724","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

Content base image retrieval design & optimization for MRI brain tumor images 基于内容的MRI脑肿瘤图像检索设计与优化

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-12-01 DOI: 10.1109/ICSPIS.2017.8311607

Zahra Chinsari Mehneh, Reza Shamsaee

{"title":"Content base image retrieval design & optimization for MRI brain tumor images","authors":"Zahra Chinsari Mehneh, Reza Shamsaee","doi":"10.1109/ICSPIS.2017.8311607","DOIUrl":"https://doi.org/10.1109/ICSPIS.2017.8311607","url":null,"abstract":"In the current years, advancements in medical imaging have prompted the rise of some massive databases, including the pictures from a different scope of modalities. Content based image retrieval (CBIR) is a kind of search that selects examples from an image set that have a similar content to an input query image. Each CBIR system consists of two substantial factors, feature extraction and similarity measure. Based on the type of these parts, many CBIR systems are proposed. In this paper we present not only how to design a CBIR system for MRI brain Tumor images, but also a comparison between the different implemented CBIR systems and ours. Furthermore, in this research, using a DML (Distance Metric Learning) instead of the rigid distance metric such as Euclidean distance as the Similarity measure has helped the researchers to obtain a better mAP (mean Average Precision) as the result. The experimental results of our CBIR system show that it has a better performance than other rivals in the field. The obtained mean average precision of our CBIR system is 92.41 that is significant in MRI brain tumor.","PeriodicalId":380266,"journal":{"name":"2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129864828","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: 2

An experimental study on vision based controlling of a spherical rolling robot 球面滚动机器人视觉控制的实验研究

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-12-01 DOI: 10.1109/ICSPIS.2017.8311583

Rasoul Sadeghian, Shahrooz Shahin, M. T. Masouleh

{"title":"An experimental study on vision based controlling of a spherical rolling robot","authors":"Rasoul Sadeghian, Shahrooz Shahin, M. T. Masouleh","doi":"10.1109/ICSPIS.2017.8311583","DOIUrl":"https://doi.org/10.1109/ICSPIS.2017.8311583","url":null,"abstract":"In this paper, three path planning algorithms and the comparison between them are described in terms of processing time and path distance values. The algorithms which are used in this paper are, Genetic Algorithm (GA), Bidirectional Rapidly-Exploring Random Tree (BRRT) algorithm and Potential Field algorithm. According to the simulation results which are obtained based on MATLAB simulation, the performance of the designed potential field algorithm is better than the other ones in terms of processing time and the path distance values. Indeed, the designed potential field algorithm is considered as the one that is chosen to be used in vision based control process. The proposed process is used to path finding for a spherical rolling robot, which is named TSR. A fixed camera on top of the proposed robot's workspace is connected to a laptop, which is used as the main core of vision based control processor unit. The experimental results based on implementing the potential field approach as path planning algorithm, verified the desirable performance of it in terms of finding a short and accurate path in an acceptable time. Finally, the effect of using the proposed vision based control method is assessed. The experimental results based on combining the aforementioned control methods verified the significant performance of the propounded spherical rolling robot in terms of path finding and following.","PeriodicalId":380266,"journal":{"name":"2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128268824","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: 4

Singular value thresholding for multi-dimensional data: Application to fMRI and terahertz imaging 多维数据的奇异值阈值:在功能磁共振成像和太赫兹成像中的应用

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-12-01 DOI: 10.1109/ICSPIS.2017.8311592

V. Abolghasemi, S. Ferdowsi

引用次数: 1

An efficient voice activity detector in non-stationary noises incorporating evidence theory to combine multiple statistical models 将证据理论与多种统计模型相结合，提出了一种有效的非平稳噪声声活动检测方法

2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS) Pub Date : 2017-12-01 DOI: 10.1109/ICSPIS.2017.8311608

Mohammad Amin Navakpour, N. Faraji

{"title":"An efficient voice activity detector in non-stationary noises incorporating evidence theory to combine multiple statistical models","authors":"Mohammad Amin Navakpour, N. Faraji","doi":"10.1109/ICSPIS.2017.8311608","DOIUrl":"https://doi.org/10.1109/ICSPIS.2017.8311608","url":null,"abstract":"This paper presents a voice activity detector (VAD) by selecting the most appropriate statistical model of noisy speech spectral components. In the previous researches, it is shown that the power spectral flatness measure (PSFM) value implies which statistical model fits the best to the Discrete Cosine Transform (DCT) coefficients of noisy speech. We utilize the similar trend to evaluate the relation between the real/imaginary valued DFT coefficients of noisy speech in different stationary and non-stationary noise signals and SNRs. In the conducted experiments, the Kolmogorov-Smirnov (KS) test is employed to quantify the Goodness-of-Fit (GOF) of each parametric statistical model, which is Gaussian, Gamma and Laplacian probability density functions (PDFs). The likelihood ratio (LR) concluded from the selected statistical model is employed to calculate the smoothed LR (SLR) and multiple observation LR (MOLR). The final decision is made by utilizing Dempster-Shafer Theory (DST) to combine the three LR tests that are basic LRT, MO-LRT and SLRT. The usage of the proposed VAD is developed for non-stationary noise signals employing Gerkmann's noise power spectral density estimator. The experiments demonstrate that our proposed method outperforms the conventional VADs in various adverse conditions.","PeriodicalId":380266,"journal":{"name":"2017 3rd Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133075108","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