Iranian Journal of Electrical and Electronic Engineering

---

In this paper we present a new accurate steganalysis method for the LSB

replacement steganography. The suggested method is based on the changes that occur in the

histogram of an image after the embedding of data. Every pair of neighboring bins of a

histogram are either inter-related or unrelated depending on whether embedding of a bit of

data in the image could affect both bins or not. We show that the overall behavior of all

inter-related bins, when compared with that of the unrelated ones, could give an accurate

measure for the amount of the embedded data. Both analytical analysis and simulation

results show the accuracy of the proposed method. The suggested method has been

implemented and tested for over 2000 samples and compared with the RS Steganalysis

method. Mean and variance of error were 0.0025 and 0.0037 for the suggested method

where these quantities were 0.0070 and 0.0182 for the RS Steganalysis. Using 4800

samples, we showed that the performance of the suggested method is comparable with

those of the RS steganalysis for JPEG filtered images. The new approach is applicable for

the detection of both random and sequential LSB embedding.

---

This paper presents a new approach for estimating and improving voltage stability margin from phase and magnitude profile of bus voltages using sensitivity analysis of Voltage Stability Assessment Neural Network (VSANN). Bus voltage profile contains useful information about system stability margin including the effect of load-generation, line outage and reactive power compensation so, it is adopted as input pattern for VSANN. In fact, VSANN establishes a functionality for VSM with respect to voltage profile. Sensitivity analysis of VSM with respect to voltage profile and reactive power compensation extracted from information stored in the weighting factor of VSANN, is the most dominant feature of the proposed approach. Sensitivity of VSM helps one to select most effective buses for reactive power compensation aimed enhancing VSM. The proposed approach has been applied on IEEE 39-bus test system which demonstrated applicability of the proposed approach.

---

Abstract: Voltage instability is a major threat for security of power systems. Preserving voltage security margin at a certain limit is a vital requirement for today’s power systems. Assessment of voltage security margin is a challenging task demanding sophisticated indices. In this paper, for the purpose of on line voltage security assessment a new index based on the correlation characteristic of network voltage profile is proposed. Voltage profile comprising all bus voltages contains the effect of network structure, load-generation patterns and reactive power compensation on the system behaviour and voltage security margin. Therefore, the proposed index is capable to clearly reveal the effect of system characteristics and events on the voltage security margin. The most attractive feature for this index is its fast and easy calculation from synchronously measured voltage profile without any need to system modelling and simulation and without any dependency on network size. At any instant of system operation by merely measuring network voltage profile and no further simulation calculation this index could be evaluated with respect to a specific reference profile. The results show that the behaviour of this index with respect to the change in system security is independent of the selected reference profile. The simplicity and easy calculation make this index very suitable for on line application. The proposed approach has been demonstrated on IEEE 39 bus test system with promising results showing its effectiveness and applicability.

---

---

The Nonparametric Speech Kernel (NSK), a nonparametric kernel technique, is presented in this study as a novel way to improve Speech Emotion Recognition (SER). The method aims to effectively reduce the size of speech features to improve recognition accuracy. The proposed approach addresses the need for efficient and compact low-dimensional features for speech emotion recognition. Having acknowledged the intrinsic distinctions between speech and picture data, we have refined the Kernel Nonparametric Weighted Feature Extraction (KNWFE) formulation to suggest NSK, which is especially intended for speech emotion identification. The output of NSK can be used as input features for deep learning models such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), or hybrid architectures. In deep learning, NSK can also be used as a kernel function for kernel-based methods such as kernelized support vector machines (SVM) or kernelized neural networks. Our tests demonstrate that NSK outperforms current techniques, outperforming the best-tested approach by 5.02% and 3.05%, respectively, with an average accuracy of 96.568% for the Persian speech emotion dataset and 82.56% for the Berlin speech emotion dataset.