Abstract:The textile industry is one of the most important industries in Sri Lanka. In most of the textile garment factories the defects of the fabrics are detected manually. The manual textile quality control usually depends on eye inspection. Famously, human visual assessment is drawn-out, tiring, and an exhausting errand, including perception, consideration and experience to recognize the fault occurrence. The precision of human visual assessment declines with dull positions and vast schedules. Some of the time slow, costly, and sporadic review is the outcome. In this manner, the programmed automatic visual review safeguards both the fabric quality inspector and the quality. This examination has exhibited that Textile Defect Recognition System is fit for distinguishing fabrics' imperfections with endorsed exactness with viability. With some products 100% inspection is important to ensure the stipulated quality or standard. The classifications for the automated fabric inspection approaches are expanding as the work is vast and complex. According to the algorithm used, the texture analysis problem is classified into different approaches. They are Structural, spectral, model-based methods, Unfortunately, the optimal plan does not yet exist for these vast numbers of applied methods, as each of them has some advantages and disadvantages.

Abstract:Cymatics is a visual representation of sound and vibrations, on surfaces of plates, diaphragms, and membranes in the forms of auditory-images. The surfaces that are exposed to these vibrations are sprinkled with fine particles that ac-cumulate at nodes, to create visualizations of specific geometry unique to the particular frequency. This paper dis-cusses the designing of an experimental platform, dedicated towards observing the behavior of cymatics, through analysis of such visualizations (Chladni patterns). This is further investigated by performing a numerical modelling using finite element simulation. Two millimeter thickness Aluminum (Al) plates of three shapes consisting of sur-faces with equal areas were used for both experimental and finite element analysis (FEA). FEA was performed using ANSYS simulation software and patterns were derived for different vibrational frequencies. The results demon-strated that the 60% of the experimental imagery conforms with the visualization generated by ANSYS software. Additionally, the lowest average frequency differences with respect to the simulation results an average deviation for similar images was found to be 9.2% and 2.8mm for the triangular shape plate, validating that the shape of the plate plays a paramount role in cymatics analysis. An image processing technique was used to determine the deviation between the images created by experimental platform and FEA for all the three shapes. The results demonstrate that Chladni patterns are best represented by a triangular shaped plate.

Abstract:The interaction between humans and machines has become an issue of concern in recent years. Besides facial ex-pressions or gestures, speech has been evidenced as one of the foremost promising modalities for automatic emotion recognition. Effective computing means to support HCI (Human-Computer Interaction) at a psychological level, al-lowing PCs to adjust their reactions as per human requirements. Therefore, the recognition of emotion is pivotal in High-level interactions. Each Emotion has distinctive properties that form us to recognize them. The acoustic signal produced for identical expression or sentence changes is essentially a direct result of biophysical changes, (for example, the stress instigated narrowing of the larynx) set off by emotions. This connection between acoustic cues and emotions made Speech Emotion Recognition one of the moving subjects of the emotive computing area. The most motivation behind a Speech Emotion Recognition algorithm is to observe the emotional condition of a speaker from recorded Speech signals. The results from the application of k-NN and OVA-SVM for MFCC features without and with a feature selection approach are presented in this research. The MFCC features from the audio signal were initially extracted to characterize the properties of emotional speech. Secondly, nine basic statistical measures were calculated from MFCC and 117-dimensional features were consequently obtained to train the classifiers for seven different classes (Anger, Happiness, Disgust, Fear, Sadness, Disgust, Boredom and Neutral) of emotions. Next, Classification was done in four steps. First, all the 117-features are classified using both classifiers. Second, the best classifier was found and then features were scaled to [-1, 1] and classified. In the third step, the with or without feature scaling which gives better performance was derived from the results of the second step and the classification was done for each of the basic sta-tistical measures separately. Finally, in the fourth step, the combination of statistical measures which gives better per-formance was derived using the forward feature selection method Experiments were carried out using k-NN with different k values and a linear OVA-based SVM classifier with different optimal values. Berlin emotional speech da-tabase for the German language was utilized for testing the planned methodology and recognition rates as high as 60% accomplished for the recognition of emotion from voice signal for the set of statistical measures (median, maximum, mean, Inter-quartile range, skewness). OVA-SVM performs better than k-NN and the use of the feature selection technique gives a high rate.

Abstract:A log-periodic antenna can provide directivity and gain when operating in a wide band. The log-periodic antenna is used in many applications where wide bandwidth is required along with direct and medium gain. This research implements a sequential approach to the design and simulation of the performance of a printed log-periodic dipole antenna (LPDA) capable of operating in the 1800 MHz frequency range. The advantage of this antenna is the compactness and easy integration into planar circuits suitable for applications requiring wide bandwidth and high gain. The dimension of the designed antenna was originally calculated taking high frequency as 1885 MHz and low frequency as 1805 MHz, then modeled using HFSS-13 electromagnetic simulation to determine the effect of substrate dielectric properties on dipole width and length for element optimization. The design was verified by creating and measuring S11 and radiation dia-grams. The designed antenna has a total gain of 7.9dB and a wide bandwidth.

Abstract:Gas metal arc welding (GMAW) is also referred as the metal inert gas (MIG) welding which is a process of welding done by the formation of an electric arc between the consumable wire electrode and the workpiece. Through the welding process, a continuous flow of inert gas is supplied, and it avoids the weld being subjected to react with at-mospheric air. The process can be automatic or semi-automatic where the main input parameters like current and the voltage can be direct and constant, respectively. Not only the current and voltage the welding quality depends on some more input parameters such as arc gap, velocity, and temperature. In this paper, we explain about a setup which is capable of real-time monitoring of input parameters mentioned above and selecting the best MIG welding parame-ters for the mild steel. The setup is composed of several sensors and microcontrollers for the collection and the measurement of the input parameters. The samples were categorized according to the federate and the voltage ad-justment of the selected welding machine. Then the final objective was to identify the samples of the weld with dif-ferent parameter changes which are monitored through the system. For the analysis, the samples were subjected to tensile and hardness tests, and microstructure tests to find the dependence of the input parameters which effect for the weld quality. Finally, the experimental results verified the effectiveness of the system for the selection of the quality weld.