Emotion recognition has important applications in human-computer interaction. Various sources such as facial expressions and speech have been considered for interpreting human emotions. The aim of this paper is to develop an emotion recognition system from facial expressions and speech using a hybrid of machine-learning algorithms in order to enhance the overall performance of human computer communication. For facial emotion recognition, a deep convolutional neural network is used for feature extraction and classification, whereas for speech emotion recognition, the zero-crossing rate, mean, standard deviation and mel frequency cepstral coefficient features are extracted. The extracted features are then fed to a random forest classifier. In addition, a bi-modal system for recognising emotions from facial expressions and speech signals is presented. This is important since one modality may not provide sufficient information or may not be available for any reason beyond operator control. To perform this, decision-level fusion is performed using a novel way for weighting according to the proportions of facial and speech impressions. The results show an average accuracy of 93.22 %.
The organization and coordination of any communication is based on the system of turn-taking which refers to the process by which a participant in a conversation takes the role of speaker. The progression of any conversation is achieved by the change of roles between speaker and hearer which, in its turn, represents the heart of the turn-taking system. The turn-taking system is not a random process but it is a highly organized process governed by a set of rules. Thus, this system has certain features and rules which exist in any English communicative process. These rules, if applied by speakers, help to achieve successful exchange of turns in any conversation. This paper attempts to present full exposition of the concepts of conversation
... Show MoreAfter the outbreak of COVID-19, immediately it converted from epidemic to pandemic. Radiologic images of CT and X-ray have been widely used to detect COVID-19 disease through observing infrahilar opacity in the lungs. Deep learning has gained popularity in diagnosing many health diseases including COVID-19 and its rapid spreading necessitates the adoption of deep learning in identifying COVID-19 cases. In this study, a deep learning model, based on some principles has been proposed for automatic detection of COVID-19 from X-ray images. The SimpNet architecture has been adopted in our study and trained with X-ray images. The model was evaluated on both binary (COVID-19 and No-findings) classification and multi-class (COVID-19, No-findings
... Show MoreThis study investigated the effect of applying an external magnetic field on the characteristics of laser-induced plasma, such as its parameters plasma, magnetization properties, emission line intensities, and plasma coefficients, for plasma induced from zinc oxide: aluminum composite (ZO:AL) at an atomic ratio of 0.3 %. Plasma properties include magnetization and emission line intensities. The excitation was done by a pulsed laser of Nd:YAG with 400 mJ energy at atmospheric pressure. Both the electron temperature and number density were determined with the help of the Stark effect principle and the Boltzmann-Plot method. There was a rise in the amount of (ne) and (Te) that was produced
... Show MorePV connected systems are worldwide installed because it allows consumer to reduce energy consumption from the electricity grid. This paper presents the results obtained from monitoring a 1.1 kWp. The system was monitored for nine months and all the electricity generated was fed to the fifth floor for physics and renewable energy building 220 V, 50 Hz. Monthly, and daily performance parameters of the PV system are evaluated which include: average generated of system Ah per day, average system efficiency, solar irradiation around these months. The average generated kWh per day was 8 kWh/day, the average solar irradiation per day was 5.6 kWh/m2/day, the average inverter efficiency was 95%, the average modules efficien
... Show MoreBeen Antkhav three isolates of soil classified as follows: Bacillus G3 consists of spores, G12, G27 led Pal NTG treatment to kill part of the cells of the three isolates varying degrees treatment also led to mutations urged resistance to streptomycin and rifampicin and double mutations
Low incoming discharge upstream of Samarra-Al Tharthar System leads to sediment accumulation and forming islands, especially an island upstream of Al Tharthar Regulator. This island and the sedimentation threaten the stability of the structure and reduce the efficiency of the system. This study aims to hydraulically identify the sedimentation problem mentioned above, to find solutions of how to control the sediment problems, and to develop the capacity of
the system for 500 years return period flood of 15060 m3/s. Surface Water Modeling System (SMS10.1) with two dimensional depth average models (RMA-2) software were used to simulate and analyze the system. The results of analysis showed that the maximum permissible discharge through t
This study aims to preparation a standards code for sustainability requirements to contribute in a better understanding to the concept of sustainability assessment systems in the dimensions of Iraqi projects in general and in the high-rise building. Iraq is one of the developing countries that faced significant challenges in sustainability aspects environmental, economic and social, it became necessary to develop an effective sustainability building assessment system in respect of the local context in Iraq. This study presented a proposal for a system of assessing the sustainability requirements of Iraqi high rise buildings (ISHTAR), which has been developed through several integrated
HM Al-Dabbas, RA Azeez, AE Ali, Iraqi Journal of Science, 2023