No abstract

No abstract

Smart manufacturing enables an efficient manufacturing process by optimizing production and product transaction. The optimization is performed through data analytics that requires reliable and informative data as input. Therefore, in this paper, an accurate data capture approach based on a vision sensor is proposed. Three image recognition methods are studied to determine the best vision-based classification technique, namely Bag of Words (BOW), Spatial Pyramid Matching (SPM) and Convolutional Neural Network (CNN). The vision-based classifiers categorize the apple as defective and non-defective that can be used for automatic inspection, sorting and further analytics. A total of 550 apple images are collected to test the classifiers. The images consist of 275 non-defective and 275 defective apples. The defective category includes various types of defect and severity. The vision-based classifiers are trained and evaluated according to the K-fold cross-validation. The performances of the classifiers from 2-fold, 3-fold, 4-fold, 5-fold and 10-fold are compared. From the evaluation, SPM with SVM classifier attained 98.15% classification accuracy for 10-fold and outperformed the others. In terms of computational time, CNN with SVM classifier is the fastest. However, minimal time difference is observed between the computational time of CNN and SPM, which were separated by only 0.05 s.

No abstract

Antenna is a vital component in wireless application systems. The microstrip antenna can be used for wireless applications as it has features such as light weight, easily mounted and it is easy to mass produce. Although there are many features that suits well for microstrip antenna to be deployed for wireless applications, there is a very serious limitation where it has a very narrow bandwidth. The typical bandwidth of the microstrip antennas is between 1 -3%. If this limitation is eliminated, the microstrip antenna can be used to its full potential. An alternative bandwidth enhancement technique is studied and then proposed in order to broaden the bandwidth of the microstrip antenna. The wireless application that is selected to be studied is the Wireless Local Area Network (WLAN) based on the IEEE 802.11b standard. In Malaysia, this WLAN band spans from 2.4GHz to 2.48GHz. The bandwidth enhancement technique which is selected is the Identical Dual-Patch Microstrip Antenna with Air-Gap (IDMA). By using this technique, a bandwidth enhancement of about 11% has been achieved. This bandwidth very well covers the required WLAN band with an operating frequency of 2.45GHz.