Articles

Permanent URI for this collection

https://testres.nu.edu.kz/handle/123456789/1165

Browse

Browsing Articles by Author "Alizadeh, Tohid"

Now showing 1 - 2 of 2
  • No Thumbnail Available
    ItemUnknown
    Cluster-head based feedback for simplified time reversal prefiltering in ultra-wideband systems
    (Physical Communication, 2017-12-01) Soleimani, Hossein; Tomasin, Stefano; Alizadeh, Tohid; Shojafar, Mohammad; Hossein, Soleimani
    Abstract Time-reversal prefiltering (TRP) technique for impulse radio (IR) ultra wide-band (UWB) systems requires a large amount of feedback to transmit the channel impulse response from the receiver to the transmitter. In this paper, we propose a new feedback design based on vector quantization. We use a machine learning algorithm to cluster the estimated channels into several groups and to select the channel cluster heads (CCHs) for feedback. In particular, CCHs and their labels are recorded at both side of the UWB transceivers and the label of the most similar CCH to the estimated channel is fed back to the transmitter. Finally, the TRP is applied using the feedback CCH. The proposed digital feedback provides three main advantages: (1) it significantly reduces the dedicated bandwidth required for feedback; (2) it considerably improves the speed of transceivers; and, (3) it is robust to noise in the feedback channel since few bytes are required to send the codes that can be heavily error protected. Numerical results on standard UWB channel models are discussed, showing the advantage of the proposed solution.
  • No Thumbnail Available
    ItemUnknown
    An intelligent system for quality measurement of Golden Bleached raisins using two comparative machine learning algorithms
    (Measurement, 2017-09-01) Karimi, Navab; Ranjbarzadeh Kondrood, Ramin; Alizadeh, Tohid; Navab, Karimi
    Abstract In this research, an expert system is provided for measuring and recognizing the quality and purity of mixed (pure-impure) raisins using bulk raisins’ images. For this purpose, by utilizing a machine vision setup 1400 images of the raisins were captured in the several ranges of mixture (from 5 to 50%). Then, totally 146 textural features were obtained using four methods of gray-level histograms, gray level co-occurrence matrix (GLCM), gray level run-length (GLRM) matrix, and local binary pattern (LBP). Principal Components Analysis (PCA) was used in order to find the optimum features from the extracted features. Accordingly, Artificial Neural Network (ANN) and Support Vector Machine (SVM) were used for classifying the mixtures. In comparison to ANN, using top 50 features, SVM classifier had more efficient and accurate classification results (averagely 92.71%). The results of the proposed approach can be used in designing a system for purity and quality measuring of raisins.