No abstract

The computer vision (CV) is an emerging area with sundry promises. This communication encompasses the past development, recent trends and future directions of the CV in the context of deep learning (DL) algorithms-based object detections and localizations techniques. To identify the object location inside an image and recognize it by a computer program as fast as the human brain the machine learning and DL techniques have been evolved. However, the main limitations of the machine are related to the prolonged time consumption to handle vast amount of data to perform the same task as the human brain. To overcome these shortcomings, the convolution neural networks (NNs)-based deep NN has been developed, which detects and classifies the object with high precision. To train the deep NNs, massive amount of data (in the form of images and videos) and time is needed, making the computational cost of the CV very high. Thus, transfer learning techniques have been proposed wherein a model trained on one task can be reused on another linked task, thereby producing excellent outcomes. In this spirit, diverse DL-based algorithms have been introduced to detect and classify the object. These algorithms include the region-based convolutional NN (R-CNN), fast R-CNN, Faster R-CNN, mask E-CNN and You Only Look Once. A comparative evaluation among these techniques has been made to reveal their merits and demerits in the CV.

In the modernized era, the air conditioners are an integrated part of comfort living especially in hot climates. They are used to control the interior spatial temperature, relative humidity, degree of cleanliness, and speed of air streaming. The automatic controllers are the key elements of the modern air conditioning systems that ensure the reliable operation, improved quality, low operation cost, and better security. Thus, the realization, design, and application of the controller systems require the exact specifications of the involved processes. In this regard, controllers based on the fuzzy logic (FL) are prospective for air conditioners due to the easy accessibility of different output levels. Furthermore, using the FL it is possible to scale and control the users’ air processing demand depending on the temperature and relative humidity of the space. Based on these factors, this paper reports the design and performance evaluation of a FL based controller useful for air conditioners when implemented in the classroom setting. This FL based control system can reduce the complexity of programming thereby can be executed on general microcontrollers utilized in the control panels of classroom air conditioner. The results revealed the outperforming nature of the FL based controllers over other traditional controllers used to adjust the indoor temperature and relative humidity by air conditioners.

Malaysia, just like its neighbouring countries in the region, has a rich and diverse culture and heritage treasures. What makes Malaysia more unique is its diversity as a multi-racial and multicultural country. These cultural heritages might become lost and extinct without any efforts in preserving and safeguarding due to modernization, assimilation, and globalization. We present an overview of different cultural heritage in Malaysia and available efforts to preserve these treasures found from literature. Digital preservation efforts that computer graphics, media scientists and practitioners could offer as alternatives in preservation of culture and heritage preservation will also be included in this paper.

Performing and detecting object interference or collision detection in urban environment simulation is always challenging problem for researchers to come out with fast and efficient collision detection algorithm. Most of previous method seems trying to tackle the problems of involving specific geometric models colliding pairs with restricted rules and guidelines. For example, convex hull bounding-volume tends to solve the collision detection problems by make the collision more accurate. However, its limitation of performing fast collision detection method must be left behind. Hence, in this paper we introduce new traversal algorithm using BoundingVolume Hierarchies (BVH) for collision detection in urban environment simulation. By using hierarchical approach, the efficiency of detecting object interference in urban simulation is increase. We believe that BVH method can be useful in urban simulation for collision detection between static rigid models and dynamic rigid models. Thus it should be able to overcome the equipment of urban environment simulation. Our result shows that bounding-volume hierarchies achieve favorable frame-rates in real time simulation using top-down binary tree. In practice, the construction of bounding-volume hierarchies in urban environment simulation are not just useful for collision detection but they also useful for others detecting object interference technique such culling and raytracing.