Recognizing speech emotions is an important subject in pattern recognition. This work is about studying the effect of extracting the minimum possible number of features on the speech emotion recognition (SER) system. In this paper, three experiments performed to reach the best way that gives good accuracy. The first one extracting only three features: zero crossing rate (ZCR), mean, and standard deviation (SD) from emotional speech samples, the second one extracting only the first 12 Mel frequency cepstral coefficient (MFCC) features, and the last experiment applying feature fusion between the mentioned features. In all experiments, the features are classified using five types of classification techniques, which are the Random Forest (RF), k-Nearest Neighbor (k-NN), Sequential Minimal Optimization (SMO), Naïve Bayes (NB), and Decision Tree (DT). The performance of the system validated over Surrey Audio-Visual Expressed Emotion (SAVEE) dataset for seven emotions. The results of the experiments showed given good accuracy compared with the previous studies using a fusion of a few numbers of features with the RF classifier.
Fraxinus ornus L. is considered as a special species that is frequently planted as a decorative tree in most of the country. The cross-sections of the root and stem are circular in shape and in the secondary growth stage, the vascular tissue in the root and stem consists of secondary xylem in radial rows and the type of vessels in the xylem are ring pours wood. Epidermal cells of leaves undulate on the upper and lower side, hairs are uniseriate and unicellular and the stomata appeared in the abaxial surface only is anomocytic type. The vertical-section of blade leaf includes upper epidermis and lower epidermis followed by the palisade layer and spongy layers. The cross-section of petiole horseshoe shape and the vascular bundles are cover
... Show MoreThe current study aimed to identify the morphological description of the domestic cat tongue; thus for this purpose, five domestic cats of both sexes were collected from the local markets of Baghdad governorate, and then the animals were anesthetized and the tongue was removed from them. Fresh tongue samples were fixed using formalin (10%), and the preserved samples were dyed with methyl blue. The results showed that the tongue is an elongated organ divided into three regions: a somewhat flat rounded apex, this region contains a central depression called the middle groove. The second region is the lingual body region represents the largest region of the tongue, whereas its last region, called the root which has a lingual prominence on it
... Show MoreBackground: For many decades, the ECG was the
workhorse of non-invasive cardiac test and today although
other techniques provide more details about the structural
anomalies in congenital heart diseases, ECG is likely to be
part of clinical evaluation of patients with such diseases
because it is inexpensive, easy to perform and in certain
situations may be both sensitive and specific.
Objective: this study carried out to identify the pattern of
ECG study in patients with TOF.
Methods: this is a retrospective study of 200 patients
with TOF, referred to Ibn Al-Bitar cardiac center from
April 1993 to May 1999. The diagnosis of TOF established
by echocrdiographic, catheterization and angiographic
study.
To translate sustainable concepts into sustainable structure, there is a require a collaborative work and technology to be innovated, such as BIM, to connect and organize different levels of industry e.g. decision-makers, contractors, economists, architects, urban planners, construction supplies and a series of urban planning and strategic infrastructure for operate, manage and maintain the facilities. This paper will investigate the BIM benefits as a project management tool, its effectiveness in sustainable decision making, also the benefit for the local industry key stakeholders by encouraging the BIM use as a project management tool to produce a sustainable building project. This p
The convolutional neural networks (CNN) are among the most utilized neural networks in various applications, including deep learning. In recent years, the continuing extension of CNN into increasingly complicated domains has made its training process more difficult. Thus, researchers adopted optimized hybrid algorithms to address this problem. In this work, a novel chaotic black hole algorithm-based approach was created for the training of CNN to optimize its performance via avoidance of entrapment in the local minima. The logistic chaotic map was used to initialize the population instead of using the uniform distribution. The proposed training algorithm was developed based on a specific benchmark problem for optical character recog
... Show MoreFace recognition is required in various applications, and major progress has been witnessed in this area. Many face recognition algorithms have been proposed thus far; however, achieving high recognition accuracy and low execution time remains a challenge. In this work, a new scheme for face recognition is presented using hybrid orthogonal polynomials to extract features. The embedded image kernel technique is used to decrease the complexity of feature extraction, then a support vector machine is adopted to classify these features. Moreover, a fast-overlapping block processing algorithm for feature extraction is used to reduce the computation time. Extensive evaluation of the proposed method was carried out on two different face ima
... Show MoreHM Al-Dabbas, RA Azeez, AE Ali, IRAQI JOURNAL OF COMPUTERS, COMMUNICATIONS, CONTROL AND SYSTEMS ENGINEERING, 2023