• فهرست مقالات Signal processing

      • دسترسی آزاد مقاله

        1 - کاربرد معادلات دیفرانسیل جزئی کسری فازی در کاهش اختلال سیگنال صدای قلب
        فرنوش کریمی توفیق الهویرانلو سعید عباسبندی
        سیستم قلبی و عروقی یک منبع از داده‌ها برای پیش بینی و تمییز دادن بین بیماریهای قلبی است .بخش اساسی مطالعات علمی به میزان دسترسی به داده‌های معتبر بستگی دارد . امروزه در زمینه‌های مربوط به تحقیقات حیاتی بشر، نه ‌تنها به دلیل خطاهای اندازه‌گیری بلکه به دلیل ابهام در مفهوم چکیده کامل
        سیستم قلبی و عروقی یک منبع از داده‌ها برای پیش بینی و تمییز دادن بین بیماریهای قلبی است .بخش اساسی مطالعات علمی به میزان دسترسی به داده‌های معتبر بستگی دارد . امروزه در زمینه‌های مربوط به تحقیقات حیاتی بشر، نه ‌تنها به دلیل خطاهای اندازه‌گیری بلکه به دلیل ابهام در مفهوم اندازه‌گیری، داده‌های تجربی همیشه توسط اطلاعات نادرست آلوده می‌شوند. به ‌عنوان یک نمونه واقعی می‌توان به ادغام سیگنالهای حیاتی ازجمله سیگنال قلب با نویز اشاره کرد که در آن ابهام موجود مانع از پردازش صحیح سیگنال با روشهای کلاسیک شده است. در این مقاله سعی ما بر آن است که در مرحله پیش‌پردازش سیگنال، الگوریتمی برای کاهش نویز سیگنال صدای قلب طراحی کنیم. روش جدید حذف نویز از سیگنال‌های صدای قلب با استفاده از معادلات دیفرانسیل جزئی فازی از مرتبه کسری(FFPDE) جهت دستیابی به‌دقت بالا ارائه می‌شود. فازی سازی برای از بین بردن مرزهای مطلق انجام شده است. الگوریتم بر روی سیگنال صدای قلب نرمال بدون نویز با افزودن نویز سفید گاوسی مورد آزمایش قرار می‌گیرد. پس از معرفی و ارائه مدل، حذف نویز مبتنی بر روش انجام می‌گیرد. تحقق فیلتر FFPDE از مرتبه کسری به‌طور کلی مراحل زیر را شامل می‌شود؛ ابتدا با استفاده ازجمله پسرو اویلر و گسسته سازی، معادله دیفرانسیل فازی به دست می-آید. سپس ماتریس فیلتر معرفی می‌شود. نتایج حاصل حاکی از آن است که معادلات دیفرانسیل جزئی فازی از مرتبه کسری در تشخیص و کاهش نویز بسیار کارا است. پرونده مقاله
      • دسترسی آزاد مقاله

        2 - Presenting a New Model of Optimal Coordinated beam former Vector Selection in DRFM for Radar Jamming
        Hasan Mohammadi khodadad Halili Vahidreza Soltaninia Meysam Bayat Saeed Talati
        Digital Radio Frequency Memory (DRFM) is a technique that uses high-speed sampling and digital memory to store radio frequency and microwave signals. DRFM is a popular technique for implementing false-target ECM systems. DRFM is a technique that stores and reproduces ra چکیده کامل
        Digital Radio Frequency Memory (DRFM) is a technique that uses high-speed sampling and digital memory to store radio frequency and microwave signals. DRFM is a popular technique for implementing false-target ECM systems. DRFM is a technique that stores and reproduces radio frequency (RF) and microwave signals. Input an RF signal that has been converted to a frequency sufficient for sampling by a high-speed A/D converter (ADC). The sampled signal is stored in a high-speed memory and can be retrieved and converted to the original signal using a D/A converter (DAC). In this article, the principles and architecture of DRFM have been reviewed and to improve the performance of this system, the method of interference matching has been proposed using a coordinated beam shaper to improve the performance of this system in creating interference. This article, it is presented to evaluate the proposed method in improving the interference values and BER in the method based on the improvement of the coordinated beam former. For this purpose, a DRFM was considered for disruption. Then the proposed method was implemented with the help of signal processing and in MATLAB software on this DRFM. In the proposed method, an objective function is considered by considering the increase in the number of objectives in proportion to the fulfillment of the acceptable rate. Based on this objective function, the amount of interference and BER has been reduced. The effect of increasing targets on interference and BER has been investigated in evaluating the proposed method. For this purpose, the SINR value was changed, and based on the change of the SINR value and the change in the number of targets, the evaluation was done. The obtained results show that with the increase in the number of targets, the amount of interference and also the amount of BER have increased. The increase in the number of targets in the proposed optimal and quasi-optimal coordinated beam former method with the increase in the number of targets is much less than that of the coordinated beam former. It is also the reason for this superiority. Also, the desired optimization function in the stated situations has caused this importance to be taken into account. The proposed method has been evaluated in terms of bit error rate and interference. The evaluation results show a reduction in bit error rate up to 6%, and interference up to 5% compared to the coordinated beam former as the number of targets increases. پرونده مقاله
      • دسترسی آزاد مقاله

        3 - Monitoring Pipe-Wall Corrosion Rate by Ultrasonic Technique
        Behzad Esmaeili Aghdam Hossein Nasir Aghdam
        thickness and corrosion/erosion rate. In this thesis, a combination of signal processing techniques are used to estimate the corrosion rate estimates based on MBE. Corrosion rate is estimated based on ultrasonic pipe wall thickness data is collected over a short period چکیده کامل
        thickness and corrosion/erosion rate. In this thesis, a combination of signal processing techniques are used to estimate the corrosion rate estimates based on MBE. Corrosion rate is estimated based on ultrasonic pipe wall thickness data is collected over a short period of time using MBE model. This technique is based on data collected from the speedometer applied for thinning and both indicate that they were able to estimate the rate of corrosion in short periods of time and with good accuracy. پرونده مقاله
      • دسترسی آزاد مقاله

        4 - Influence of Converter and inverter on dynamic behavior of the GMAW process
        Alireza Doodman Tipi Seyed Kamal Hosseini Sani Naser Pariz
        This paper investigates the dynamic behavior of Gas Metal Arc Welding (GMAW) process for two types of power supplies –inverter and rectifier- for short circuit transfer mode. The large ripples on the rectifier power source are able to perturb the metal transfer mo چکیده کامل
        This paper investigates the dynamic behavior of Gas Metal Arc Welding (GMAW) process for two types of power supplies –inverter and rectifier- for short circuit transfer mode. The large ripples on the rectifier power source are able to perturb the metal transfer mode. In this experimental work some operating points in the short circuit mode have been selected using an automatic pipeline welding system -, and then both rectifier and inverter effects (as the power supplies) on the process are illustrated. For the small voltage and currents, the two power supplies effects are similar in the short circuit transfer mode. On the other hand, for larger voltage and current values, the responses will be different as the rectifier power supply produces more perturbations on the metal transfer. However the process with the inverter has a more regular behavior and more stable detachment. finally, the results have been evaluated by implementing on the real industrial GMAW system. پرونده مقاله
      • دسترسی آزاد مقاله

        5 - بازشناسی احساسات از روی گفتار با استفاده از ترکیب شبکه‌های عصبی ترنسفورمر و کانولوشنی
        یوسف پورابراهیم فربد رزازی حسین صامتی
        بازشناسی احساسات از روی گفتار با توجه به کاربردهای متنوع آن امروزه مورد توجه بسیاری از محققان قرار گرفته است. با پیشرفت روش‌های آموزش شبکه‌های عصبی عمیق وگسترش استفاده از آن در کاربردهای مختلف، در این مقاله کاربرد شبکه‌های کانولوشنی و ترنسفورمر در یک ترکیب جدید در بازشن چکیده کامل
        بازشناسی احساسات از روی گفتار با توجه به کاربردهای متنوع آن امروزه مورد توجه بسیاری از محققان قرار گرفته است. با پیشرفت روش‌های آموزش شبکه‌های عصبی عمیق وگسترش استفاده از آن در کاربردهای مختلف، در این مقاله کاربرد شبکه‌های کانولوشنی و ترنسفورمر در یک ترکیب جدید در بازشناسی احساسات گفتاری مورد بررسی قرار گرفته که از لحاظ پیاده‌سازی نسبت به روش‌های موجود ساده‌تر بوده و عملکرد مطلوبی نیز دارد. برای این منظور شبکه‌های عصبی کانولوشنی و ترنسفورمر پایه معرفی شده و سپس مبتنی بر آنها یک مدل جدید حاصل از ترکیب شبکه‌های کانولوشنی و ترنسفورمر ارایه شده که در آن خروجی مدل کانولوشنی پایه ورودی مدل ترنسفورمر پایه است. نتایج حاصل نشان می‌دهد که استفاده از شبکه‌های عصبی ترنسفورمر در بازشناسی بعضی از حالت‌های احساسی عملکرد بهتری نسبت به روش کانولوشنی دارد. همچنین در این مقاله نشان داده شده ‌که استفاده از شبکه‌های عصبی ساده به صورت ترکیبی عملکرد بهتری در بازشناسی احساسات از روی گفتار می‌تواند داشته باشد. در این رابطه بازشناسی احساسات گفتاری با استفاده از ترکیب شبکه‌های عصبی کانولوشنی و ترنسفورمر با نام کانولوشنال-ترنسفورمر (CTF) برای دادگان راودس دقتی برابر 94/80 درصد به دست آورد؛ در حالی که یک شبکه عصبی کانولوشنی ساده دقتی در حدود 7/72 درصد به دست آورد. همچنین ترکیب شبکه‌های عصبی ساده علاوه بر اینکه می‌تواند دقت بازشناسی را افزایش دهد، می‌تواند زمان آموزش و نیاز به نمونه‌های آموزشی برچسب دار را نیز کاهش دهد. پرونده مقاله
      • دسترسی آزاد مقاله

        6 - A Review of Notable Studies on Using Empirical Mode Decomposition for Biomedical Signal and Image Processing
        Fereshteh Yousefi Rizi
        The data-driven empirical mode decomposition (EMD) method is designed to analyze the non-stationary signals like biomedical signals originating from nonlinear biological systems. EMD analysis produces a local complete separation of the input signal in fast and slow osci چکیده کامل
        The data-driven empirical mode decomposition (EMD) method is designed to analyze the non-stationary signals like biomedical signals originating from nonlinear biological systems. EMD analysis produces a local complete separation of the input signal in fast and slow oscillations along with the time-frequency localization. EMD extracts the amplitude and frequency modulated (AM–FM) functions, i.e. the intrinsic mode functions (IMFs), that have been widely used for biomedical signal de-noising, de-trending, feature extraction, compression, and identification. To overcome the problems of EMD, like mode mixing, new generations of EMD have been proposed and applied for biomedical signal analysis. Besides, the bidimensional EMD (BEMD) was introduced and improved for image processing. BEMD and its modified versions have been widely used for medical image de-noising, de-speckling, segmentation, registration, fusion, compression, and classification. In this paper, a review of notable studies in the biomedical signal and image processing based on EMD or BEMD method and their modified versions were considered. The studies on using EMD and its modified versions for mono-dimensional and bidimensional(image) signal processing showed the capabilities of the improved EMD and BEMD methods on biomedical signal and image processing. پرونده مقاله
      • دسترسی آزاد مقاله

        7 - Determination of the Type of The Imagined Movement of Organs in People with Mobility Disabilities Using Corrected Common Spatial Patterns
        Alireza Pirasteh Manouchehr Shamseini Ghiyasvand Majid Pouladian
        In order to help people with disabilities, understanding presence of the coronavirus (covid-19) pandemic increasingly highlights the need for emerging technologies. As we know, brain computer interface (BCI) systems were hired to resolve the important challenges on the چکیده کامل
        In order to help people with disabilities, understanding presence of the coronavirus (covid-19) pandemic increasingly highlights the need for emerging technologies. As we know, brain computer interface (BCI) systems were hired to resolve the important challenges on the quality of life of people with disabilities and improve disabled person independent in performing daily activities. Therefore, in this work, BCI systems were furnished to study the type of movement of a person imagines from EEG signals. Before starting to analyze data, frequency bands and brain regions were first associated with motion imaging. Then, various types of spatial and frequency filters were applied to reduce signal noise, after that features were extracted by improving CSP algorithms like CSSP. Because the appropriate frequency band is not selected, the CSP results, which depend on frequency filtering, will not have the desired results, therefore CSSP method based on FIR filters is used. It means that we apply a frequency filter and frequency optimization occurred. The used data is standard data provided on bbci.de. In this database, 9 people have undergone EEG registration. Signal recording was performed in four visual classes including left-hand movement, right-hand movement, both feet, and language. To select the feature, we used the SFS feature algorithm. This algorithm achieved high accuracy by selecting six features together and using SVM classifier. In total, while the accuracy in the CSP method was 87.5%, in the CSSP method it reached 93.6 %. پرونده مقاله
      • دسترسی آزاد مقاله

        8 - A Denoising Autoencoder Stacked Deep Learning Method for Clinical Trial Enrichment and Design Applied to Alzheimer’s Disease
        Aref Safari
        In this research, we first present some background on the sample size estimation for conducting clinical trials, discussing the necessity of a computational enrichment criterion. The Denoising Autoencoder Stacked Deep Learning (DASDL) design and development are directly چکیده کامل
        In this research, we first present some background on the sample size estimation for conducting clinical trials, discussing the necessity of a computational enrichment criterion. The Denoising Autoencoder Stacked Deep Learning (DASDL) design and development are directly motivated by the optimal enrichment design. Although there are many types of deep architectures in the literature, we focus our presentation using two of the most widely used models stacked denoising autoencoders and fully-supervised dropout. The ideas presented here are applied to any such architectures used for learning problems in the small-sample regime. In this work, we propose a novel, scalable, deep learning method that is applicable for learning problems in the small sample regime and obtains reliable performance. The results show via extensive analyses using imaging, cognitive, and other clinical data alongside a ROC curve analysis. When used as trial inclusion criteria, the new computational markers result in cost-efficient clinical Alzheimer’s disease trials with moderate sample sizes. پرونده مقاله