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 %.
Estimating the semantic similarity between short texts plays an increasingly prominent role in many fields related to text mining and natural language processing applications, especially with the large increase in the volume of textual data that is produced daily. Traditional approaches for calculating the degree of similarity between two texts, based on the words they share, do not perform well with short texts because two similar texts may be written in different terms by employing synonyms. As a result, short texts should be semantically compared. In this paper, a semantic similarity measurement method between texts is presented which combines knowledge-based and corpus-based semantic information to build a semantic network that repre
... Show MoreThis paper focuses on the optimization of drilling parameters by utilizing “Taguchi method” to obtain the minimum surface roughness. Nine drilling experiments were performed on Al 5050 alloy using high speed steel twist drills. Three drilling parameters (feed rates, cutting speeds, and cutting tools) were used as control factors, and L9 (33) “orthogonal array” was specified for the experimental trials. Signal to Noise (S/N) Ratio and “Analysis of Variance” (ANOVA) were utilized to set the optimum control factors which minimized the surface roughness. The results were tested with the aid of statistical software package MINITAB-17. After the experimental trails, the tool diameter was found as the most important facto
... Show MoreImage databases are increasing exponentially because of rapid developments in social networking and digital technologies. To search these databases, an efficient search technique is required. CBIR is considered one of these techniques. This paper presents a multistage CBIR to address the computational cost issues while reasonably preserving accuracy. In the presented work, the first stage acts as a filter that passes images to the next stage based on SKTP, which is the first time used in the CBIR domain. While in the second stage, LBP and Canny edge detectors are employed for extracting texture and shape features from the query image and images in the newly constructed database. The p
Chaotic systems have been proved to be useful and effective for cryptography. Through this work, a new Feistel cipher depend upon chaos systems and Feistel network structure with dynamic secret key size according to the message size have been proposed. Compared with the classical traditional ciphers like Feistel-based structure ciphers, Data Encryption Standards (DES), is the common example of Feistel-based ciphers, the process of confusion and diffusion, will contains the dynamical permutation choice boxes, dynamical substitution choice boxes, which will be generated once and hence, considered static,
While using chaotic maps, in the suggested system, called
In recent years, the performance of Spatial Data Infrastructures for governments and companies is a task that has gained ample attention. Different categories of geospatial data such as digital maps, coordinates, web maps, aerial and satellite images, etc., are required to realize the geospatial data components of Spatial Data Infrastructures. In general, there are two distinct types of geospatial data sources exist over the Internet: formal and informal data sources. Despite the growth of informal geospatial data sources, the integration between different free sources is not being achieved effectively. The adoption of this task can be considered the main advantage of this research. This article addresses the research question of how the
... Show MoreAbstract
Pneumatic processes sequence (PPS) is used widely in industrial applications. It is common to do a predetermined PPS to achieve a specific larger task within the industrial application like the PPS achieved by the pick and place industrial robot arm. This sequence may require change depending on changing the required task and usually this requires the programmer intervention to change the sequence’ sprogram, which is costly and may take long time. In this research a PLC-based PPS control system is designed and implemented, in which the PPS is programmed by demonstration. The PPS could be changed by demonstrating the new required sequence via the user by following simple series of manual steps without h
... Show MoreAny software application can be divided into four distinct interconnected domains namely, problem domain, usage domain, development domain and system domain. A methodology for assistive technology software development is presented here that seeks to provide a framework for requirements elicitation studies together with their subsequent mapping implementing use-case driven object-oriented analysis for component based software architectures. Early feedback on user interface components effectiveness is adopted through process usability evaluation. A model is suggested that consists of the three environments; problem, conceptual, and representational environments or worlds. This model aims to emphasize on the relationship between the objects
... Show MoreThe cuneiform images need many processes in order to know their contents
and by using image enhancement to clarify the objects (symbols) founded in the
image. The Vector used for classifying the symbol called symbol structural vector
(SSV) it which is build from the information wedges in the symbol.
The experimental tests show insome numbersand various relevancy including
various drawings in online method. The results are high accuracy in this research,
and methods and algorithms programmed using a visual basic 6.0. In this research
more than one method was applied to extract information from the digital images
of cuneiform tablets, in order to identify most of signs of Sumerian cuneiform.