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

In cyber security, the most crucial subject in information security is user authentication. Robust text-based password methods may offer a certain level of protection. Strong passwords are hard to remember, though, so people who use them frequently write them on paper or store them in file for computer .Numerous of computer systems, networks, and Internet-based environments have experimented with using graphical authentication techniques for user authentication in recent years. The two main characteristics of all graphical passwords are their security and usability. Regretfully, none of these methods could adequately address both of these factors concurrently. The ISO usability standards and associated characteristics for graphical

For businesses that provide delivery services, the efficiency of the delivery process in terms of punctuality is very important. In addition to increasing customer trust, efficient route management, and selection are required to reduce vehicle fuel costs and expedite delivery. Some small and medium businesses still use conventional methods to manage delivery routes. Decisions to manage delivery schedules and routes do not use any specific methods to expedite the delivery settlement process. This process is inefficient, takes a long time, increases costs and is prone to errors. Therefore, the Dijkstra algorithm has been used to improve the delivery management process. A delivery management system was developed to help managers and drivers

Dust is a frequent contributor to health risks and changes in the climate, one of the most dangerous issues facing people today. Desertification, drought, agricultural practices, and sand and dust storms from neighboring regions bring on this issue. Deep learning (DL) long short-term memory (LSTM) based regression was a proposed solution to increase the forecasting accuracy of dust and monitoring. The proposed system has two parts to detect and monitor the dust; at the first step, the LSTM and dense layers are used to build a system using to detect the dust, while at the second step, the proposed Wireless Sensor Networks (WSN) and Internet of Things (IoT) model is used as a forecasting and monitoring model. The experiment DL system

         In the present work, the magnetic dipole and electric quadrupole moments for some sodium isotopes have been calculated using the shell model, considering the effect of the two-body effective interactions and the single-particle potentials. These isotopes are; ²¹Na (3/2+), ²³Na (3/2+), ²⁵Na (5/2+), ²⁶Na (3+), ²⁷Na (5/2+), ²⁸Na (1+) and, ²⁹Na (3/2+). The one-body transition density matrix elements (OBDM) have been calculated using the (USDA, USDB, HBUMSD and W) two-body effective interactions carried out in the sd-shell model space. The sd shell model space consists of the active 2s_1/2, 1d_5/2,

The background subtraction is a leading technique adopted for detecting the moving objects in video surveillance systems. Various background subtraction models have been applied to tackle different challenges in many surveillance environments. In this paper, we propose a model of pixel-based color-histogram and Fuzzy C-means (FCM) to obtain the background model using cosine similarity (CS) to measure the closeness between the current pixel and the background model and eventually determine the background and foreground pixel according to a tuned threshold. The performance of this model is benchmarked on CDnet2014 dynamic scenes dataset using statistical metrics. The results show a better performance against the state-of the art

Encryption of data is translating data to another shape or symbol which enables people only with an access to the secret key or a password that can read it. The data which are encrypted are generally referred to as cipher text, while data which are unencrypted are known plain text. Entropy can be used as a measure which gives the number of bits that are needed for coding the data of an image. As the values of pixel within an image are dispensed through further gray-levels, the entropy increases. The aim of this research is to compare between CAST-128 with proposed adaptive key and RSA encryption methods for video frames to determine the more accurate method with highest entropy. The first method is achieved by applying the "CAST-128" and