Search

Precision agriculture is gaining attention as it employs modern technologies and intelligence for automation in agricultural practices. In the area of weed management, automation is advantageous to select the appropriate herbicide and manage the amount used, which consequently reduced the cost and minimizes the environmental impact. Selective spraying using a sprayer boom can be implemented using automatic detection of weed type. This paper presents a weed classification method based on a modified line filter image analysis technique that can effectively detect the morphological differences, mainly directional shape features, between two types of weeds. After the result for binary classification has been verified, a third dataset is introduced which is mixed leaves which consists of an approximately balanced amount of broadleaves and narrow leaves. The weed images were pre-processed using the adaptive histogram method and difference of Gaussian to improve the image contrast and delineate the edges of the weed. The images were then processed using the proposed modified line filter feature extraction technique. The filter is based on the evaluation of pixel response that corresponds to the pre-defined lines at different orientations from 0o to 360o. The pixel strength of each line was compared to determine the overall response of the filter. The proposed method achieved around 97% classification, superior compared to previously reported methods such as Gabor wavelet as well as a combination of Gabor and Gradient Field Distribution (GFD).

Iris recognition used the iris features to verify and identify the identity of human. The iris has many advantages such as stability over time, easy to use and high recognition accuracy. However, the poor quality of iris images can degrade the recognition accuracy of iris recognition system. The recognition accuracy of this system is depended on the iris pattern quality captured during the iris acquisition. The iris pattern quality can degrade due to the blurry image. Blurry image happened due to the movement during image acquisition and poor camera resolution. Due to that, a deblurring method based on the Wiener filter was proposed to improve the quality of iris pattern. This work is significant since the proposed method can enhance the quality of iris pattern in the blurry image. Based to the results, the proposed method improved the quality of iris pattern in the blurry image. Moreover, it recorded the fastest execution time to improve the quality of iris pattern compared to the other methods.

The satellite signal deteriorates as it propagates from the source to the ground antenna on the surface of the earth. While some losses involving the amplitude and energy of the signal are unavoidably recovered due to the long slant path through the atmosphere, the impairment due to precipitation, especially rain, can be mitigated. Site diversity is one of the ways to obtain a less rain-attenuated signal, simply by preparing the other site to receive a link similar to that of the main site. Dual site diversity is common in practice with a site separation distance of at least a rain cell extent. This article presents an overview of the site diversity concept and a description of all parameters involved regarding the factor that contributed to the gain, which has been used as a performance metric to measure the effectiveness of a site diversity scheme. A detailed assessment of the capability of the gain prediction model is presented using site diversity experimental data conducted in two different climatic groups, namely, Greece in a temperate region and India in a tropical climatic region. The models involved in the evaluation were the ITU-R, Hodge, and Panagopoulos models, which were validated using temperate regional data, and the Semire and Yeo models, which were validated using tropical regional data. The observations of model behavior revealed that the Semire and Yeo models of the tropics were consistent with the measured gain obtained from India and Greece, respectively; thus, this demonstrated that the direction of future prediction models should consider both climates in the validation process.

Pertandingan robotik MakeX adalah salah satu pertandingan robotik terbesar di Malaysia, yang melibatkan peserta dari kalangan pelajar sekolah rendah dan menengah. Penganjuran pertandingan ini adalah unik berbanding dengan pengajuran pertandingan robotik lain, di mana, peserta yang bakal bertanding diberi latihan dan bengkel mengenai asas pemasangan dan pengatucaraan robot serta strategi dalam menyelesaikan tugasan pertandingan. Crystal UKM, selaku pengajur bersama pertandingan ini diberi tanggungjawap untuk menyediakan latihan kepada peserta-peserta pertandingan yang terdiri daripada pelajar sekolah berusia seawal 7 tahun hingga 17 tahun. Dalam menyediakan modul berkesan kepada peserta yang bertanding pada tahun ini, pihak Crystal UKM telah mengolah satu program pementoran yang unik melibatkan pelajar-pelajar prasiswazah tahun dua dan tiga, dari program Kejuruteraan Elektrik dan Elektronik. Pelajar-pelajar prasiswazah ini disamping bertanggungjawap memberi latihan teknikal, mereka juga berperanan untuk memaksimumkan potensi dan mengembangkan kemahiran peserta, bagi meningkatkan prestasi peserta disamping meningkatkan daya saing dikalangan peserta. Kertas kerja ini memberi tumpuan kepada peranan dan perspektif pelajar-pelajar sebagai mentor kepada peserta pertandingan, serta mengkaji keberkesanan program pementoran ini dalam meningkatkan kemahiran insaniah pelajar yang terlibat sebagai mentor. Kejayaan pasukan Malaysia merangkul pingat emas dalam pertandingan robotic MakeX peringkat antarabangsa, di Guangzhou, China baru-baru ini, dan pencapaian membanggakan 2 lagi pasukan yang tergolong dalam 20 pasukan teratas, membuktikan keberkesanan program pementoran yang dijalankan

Active contour is accurate for iris segmentation on the non-ideal and noisy iris images. However, understanding on how active contour reacts to the motion blur or blurry iris images is presently unclear and remains a major challenge in iris segmentation perspective. Moreover, studies on the initial contour position in the blurry iris images are infrequently reported and need further clarification. In addition, convergence or evolution speed is still a major drawback for active contour as it moves through the boundaries in the iris images. Based on the above issues, the experiment is conducted to obtain an accurate and fast iris segmentation algorithm for the blurry iris images. The initial contour is also investigated to clarify its positioning for the blurry iris segmentation. To achieve these objectives, the Wiener filter is used for pre-processing. Next, the morphological closing is applied to eliminate reflections. Then, the adaptive Chan-Vese active contour (ACVAC) algorithm is designed from the adaptive initial contour (AIC), δ and stopping function. Finally, the partly-normalization is designed where only prominent iris features near to the inner iris boundary are selected for normalization and feature extraction. The experimental results show that the proposed algorithm achieves the highest segmentation accuracy and the fastest computational time than the other active contour-based methods. The accurate initial contour position in the blurry iris images is clearly clarified. This shows that the proposed method is accurate for iris segmentation on the blurry iris images.

Prosiding Penyelidikan Prasiswazah, Issue No. 1, 2020, pp. 43-51

Iris recognition has been around for many years due to an extensive research on the uniqueness of human iris. It is well known that the iris is not similar to each other which means every human in the planet has their own iris pattern and cannot be shared. One of the main issues in iris recognition is iris segmentation. One element that can reduce the accuracy of iris segmentation is the presence of specular reflection. Another issue is the speed of specular reflection removal since the iris recognition system needs to process a lot of irises. In this paper, a specular reflection removal method was proposed to achieve a fast and accurate specular reflection removal. Some modifications were implemented on the existing pixels properties method. Based on the results, the proposed method achieved the fastest execution time, the highest segmentation accuracy and the highest SSIM compared to the other methods. This proves that the proposed method is fast and accurate to be implemented in the iris recognition systems.

The COVID-19 outbreak from the SARS-CoV-2 virus has shocking us with its fast transmission and deadly complication. Due to that, the movement restriction has been enforced to contain this pandemic. Recently, there is an increasing pressure to restart and resurrect social and economic sectors, and to allow people to get back to work. This must be well planned before the movement restriction is lifted. Because of that, this paper aims to review and make recommendations on the new normal for our daily activities and works. Firstly, the social and economic sectors must be opening in phases by emphasizing safety and health than an economic recovery. In the meantime, the WHO recommendations on social distancing and personal hygiene must be adapted and become a new normal. Because of that, the government and local authorities should develop a soft landing approach based on the WHO recommendations. Next, the community must be engaged and empowered to do their parts in preventing the spread of COVID-19. From the new normal recommendations, the people can continue their daily routines, and at the same time can reduce COVID-19 transmission. However, medical possibilities are not considered while compiling these new normals and procedures. The population must adapt and embrace the new normal to control, reduce and prevent the spreading of COVID-19, as it could be with us for a long time.

Software has become one of the most critical parts of a measuring instrument. Despite the sophistication and complexity of measuring instruments, legal metrology framework on the software are still poor. Several legal cases related to manipulation and modification of software used in measuring instrument have been discovered in ASEAN countries particularly in Malaysia. A survey has been conducted and shows that most ASEAN countries have yet to implement and enforce legal metrology control on the software in their metrological system. This paper discussed an approach to legalizing software for measuring instrument in the Malaysian context.

Iris recognition has become one of the most prominent biometrics due to its high recognition accuracy, and it is suitable for the verification and identification systems. Most iris recognition systems can recognize human identity especially when the iris region is free from noise. However, the iris region is typically occluded by noise, eyelid and eyelash. The occluded iris can hide rich iris features, which consists fewer iris features in the iris region, thus reducing the recognition accuracy of the system. The occluded iris is also called a non-ideal iris. In this study, an improvement is made to enhance the performance of an existing sub-iris technique. This can overcome the problem of obtaining iris features from the non-ideal iris. Moreover, the proposed method can also reduce the execution time of the iris recognition system. According to the results, the proposed method managed to localize the sub-iris region, while achieving an equal error rate of 3.75%; area under curve of 0.9832; execution time of 0.719 s; and decidability of 2.9332. These metrics are superior to those of other methods.

Protection of multimedia information from different types of attackers has become important for people and governments. A high definition image has a large amount of data, and thus, keeping it secret is difficult. Another challenge that security algorithms must face with respect to high definition images in medical and remote sensing applications is pattern appearances, which results from existing regions with high density in the same color, such as background regions. An encryption and hiding based new hybrid image security systems are proposed in this paper for the purpose of keeping high definition images secret. First, one hiding method and two encryption methods are used in two hybrid algorithms. The new hiding algorithm proposed here starts by applying reordering and scrambling operations to the six Most Significant Bit planes of the secret image, and then, it hides them in an unknown scene cover image using adding or subtracting operations. Second, two different ciphering algorithms are used to encrypt the stego-image to obtain two different hybrid image security systems. The first encryption algorithm is based on binary code decomposition, while the second algorithm is a modification of an advanced encryption standard. After evaluating each hybrid algorithm alone, a comparison between the two hybrid systems is introduced to determine the best system. Several parameters were used for the performance, including the visual scene, histogram analysis, entropy, security analysis, and execution time.

Iris recognition systems have demonstrated considerable improvement in recognizing people through their iris patterns. Recent iris recognition systems have focused on images acquired in unconstrained environments. Unconstrained imaging environments allow the capture of iris images at a distance, in motion and under visible wavelength illumination which lead to more noise factors such as off-focus, gaze deviation, and obstruction by eyelids, eyeglasses, hair, lighting and specular reflections. Segmenting irises taken in an unconstrained environment remains a challenging task for iris recognition. In this paper, a new iris segmentation method is developed and tested on UBIRIS.v2 and MICHE iris databases that reflect the challenges in recognition by unconstrained images. This method accurately localizes the iris by a model designed on the basis of the Histograms of Oriented Gradients (HOG) descriptor and Support Vector Machine (SVM), namely HOG-SVM. Based on this localization, iris texture is automatically extracted by means of a cellular automata which evolved via the GrowCut technique. Pre- and post-processing operations are also introduced to ensure higher segmentation accuracy. Extensive experimental results illustrate the effectiveness of the proposed method on unconstrained iris images.

Currently, the use of telephone systems is highly popular in speech telecommunication and also they have a wide presence in transmission of digital signals. In recent years, audio-speech watermarking as a modern technique makes use of the telephone channel to transmit the watermark data, but addressing the watermark’s vulnerability to noise in the telephone channel is a difficult problem in digital audio-speech watermarking. This paper presents a robust audio-speech watermarking scheme that operates against channel noise according to audio-speech specifications, the channel coding and channel equalizer technique. The proposed scheme is based on the spread spectrum technique and a psychoacoustic model with use of the channel equalizer to remove or minimize the effects of channel noise over the watermark signal. The simulation results for imperceptibility of the watermark, voice quality, and robustness against channel noise are presented in this study. The results indicate that the proposed scheme is highly satisfactory for the cases mentioned above.

Recent growth and development of internet and multimedia technologies have made it significant to upload data; however, in this situation, the protection of intellectual property rights has become a critical issue. Digital media, including videos, audios, and images are readily distributed, reproduced, and manipulated over these networks that will be lost copyright. Also, the development of various data manipulation tools like PDF converter and Photoshop Editor has resulted in digital data copyright issues. So, a digital watermarking technique has emerged as an efficient technique of protecting intellectual property rights by providing digital data copyright authentication and protection. In this technique, a watermarked document was integrated into electronic data to prevent unauthorized access. In this paper, A robust watermark algorithm based on a 5-level DWT and Two Log was proposed to enhance the copyright protection of images in unsecured media. Our lab results validate that our algorithm scheme is robust and forceful against several sets of attacks, and high quality watermarked image was achieved, where the algorithm was assessed by computation of many evaluation metrics such as PSNR, SNR, MAE, and RMSE.

This paper presents a review of the region of interest-based (ROI) image retrieval techniques. In this study, the techniques, the performance evaluation parameters, and databases used in image retrieval process are being reviewed. A part of an image that is considered important or a selected certain area of the image is what defines a region of interest. Retrieval performance in large databases can be improved with the application of content-based image retrieval systems which deals with the extraction of global and region features of images. The capability of reflecting users' specific interests with greater accuracy has shown to be more effective when using region-based features compared to global features. Segmentation, feature extraction, indexing, and retrieval of an image are the tasks required in retrieving images that contain similar regions as specified in a query. The idea of the region of interest-based image retrieval concepts is presented in this paper and it is expected to accommodate researchers that are working in the region-based image retrieval system field. This paper reviews the work of image retrieval researchers in the span of twenty years. The main goal of this paper is to provide a comprehensive reference source for scholars involved in image retrieval based on ROI.

Nowadays software has now become a critical element of measuring instruments require to be checked and certified in order to be used in trades. Most ASEAN countries still have not implemented the pattern approval or type approval process for software in measuring instrument. This paper will propose an approach in implementing the legalisation process for existing use of software for measuring instrument in Malaysian context.

This paper presents the performance of 8FSK base on PACTOR I data transfer protocol over AWGN channel. PACTOR I is a classic digital mode that once gain name in radio amateur community due to the reliability. The modulation type is always 2FSK and still been use in the latest advance modem of PACTOR 4 for robust mode. Using AWGN channel model, the throughput performance was studied base on 8FSK modulation to increase the performance. Simulation result was focus on PACTOR I basic data transfer with stop and wait ARQ type. Some parameters such as idle time and Huffman compression were not included in the calculation to focus more on modulation effect and throughput.

The rapid growth in the use of multimedia information has made the security of data storage and transmission important in avoiding unlawful, unofficial, unauthorised and illegal use. Encryption is an efficient operation to protect multimedia data secret. A new image encryption approach that uses binary coded decimal (BCD) code-based decomposition, reordering and scrambling bit planes, and an encryption process is suggested in this study. Image decomposition using BCD code for image encryption is introduced in this study. A simple scrambling process is used to shuffle binary bit planes after re-ordering them. A shift column operation is applied to the image that is constructed after scrambling the bit planes to increase the security level. A performance analysis and a comparison with other encryption algorithms are conducted to prove the proposed algorithm's image encryption capabilities. The experimental results show that the suggested method protects secret images against common attacks with shorter encryption/decryption times.

In this article, a high-speed and highly restricted encryption algorithm is proposed to cipher high-definition (HD) images based on the modified advanced encryption standard (AES) algorithm. AES is a well-known block cipher algorithm and has several advantages, such as high-level security and implementation ability. However, AES has some drawbacks, including high computation costs, pattern appearance, and high hardware requirements. The aforementioned problems become more complex when the AES algorithm ciphers an image, especially HD images. Three modifications are proposed in this paper to improve AES algorithm performance through, decreasing the computation costs, decreasing the hardware requirements, and increasing the security level. First, modification was conducted using MixColumn transformation in 5 rounds instead of 10 rounds in the original AES-128 to decrease the encryption time. Security is enhanced by improving the key schedule operation by adding MixColumn transformation to this operation as second modification. In addition, to decrease the hardware requirements, S-box and Inv. S-box in the original AES are replaced by one simple S-box used for encryption and decryption in the proposed method. The proposed AES version conducts one of the ciphering modes to solve the appearance pattern problem. Experimental results indicate that the proposed modifications to the AES algorithm made the algorithm more compatible with HD image encryption.

Segmenting iris from images captured under the visible wavelength spectrum represents a challenging task. To address this problem, a new iris segmentation method based on the Circular Gabor Filter (CGF) and optimization is proposed. The CGF is utilized to localize the rough position of the pupil center. According to the localization result, few pixels of the pupil (iris) and non-pupil (non-iris) regions are set as initial pixels in the related region. Next, by optimization scheme, initial pixels are automatically propagated over the image until they cover the whole pupil (iris) and non-pupil (non-iris) regions. The originality of the proposed method includes developing a new method to localize the iris and eyelids boundaries simultaneously, and furthermore robust to reflections. Experimental results on the non-cooperative UBIRIS.v1 iris images reveal the effectiveness of the proposed method in comparison with some of state-of-the-art methods. The results include classification error rates of 2.08 and 3.05 % for session one and two of the UBIRIS.v1 database, respectively.

This paper proposes a design and implementation approach of smart farming system using connected-agronomics technique for fig farm application. Nowadays, fig plants having a rapid growth in the current market demand due to its rich in natural health benefiting nutrients, antioxidants and vitamins where some farming systems have been used in maintaining fig plant’s environmental resources to grow without fail. Smart farming is a system applied to provide user with real time information and plan for desired plant such as time intervals for watering systems. There are two major problems on maintaining the fig fruit quality; watering system fail during emergency blackout and a contagious disease known as leaf rust due to external environments. The system implements two microcontrollers, the Arduino Uno & Raspberry Pi along with smartphone Android application. The system performance is evaluated based on the requirement specification, irrigation soil, surrounding temperature and moisture. It is found that all data collected by the sensors are within the optimal range of values, which are 1500 µS/cm to 1599 µS/cm for the EC reading of the fertilizer while 6.0 to 6.5 for the pH value of the soil. This prototype of smart farming was well developed and can be applied to the fig plantation environment.

Sending the private data is always one of the fundamental problems in the communication systems. Therefore, information hiding was presented to protect the data. The evolutionary process has been continued until the watermarking as a new technique was generated to promote the copyright marking. Watermarking is trying to embed the private data such as text or numbers as a guest signal in the host signal with minimal effect on it. Audio watermarking was introduced as a one of watermarking techniques against the attackers and hackers that were raised on social networks.This paper presents an audio watermark algorithm with a blind detection which is based on a spread spectrum (SS) technique. A series of simulations were done on the proposed algorithm to estimate the Bit Error Rate (BER) for various values of signal-to-watermarking ratio (SWR) and bit rate. The simulationresults show that by decreasing the SWR ratio, the BER ratio is reduced to less than 10−3.

Ciphering is very important operation to preserve the confidentiality of digital images transmitted over public network spatially with rapidly growth in communication techniques. Advanced Encryption Standard (AES) is a famous and strong encryption algorithm which has several advantages in data ciphering. However, AES suffer from some drawbacks such as high computations, pattern in ciphered images, and hardware requirement. Those problems are more complicated when AES algorithm willusefor images ciphering especially the HD images. Some modifications were proposed in this paper to enhance the performance of AES algorithm in terms of time ciphering and pattern appearance. First modification is decreasing the number of rounds to one while the second modification is replace the S-box with new S-box to decrease the hardware requirements. Applying AES in one of the ciphering mode solves the pattern appearance problems. The experimental results indicate that the proposed modifications make AES algorithm faster while fulfill the security requirements.

Passive and active noise cancellation headphones' performance is a very important issue when we want to use them in some applications. The ANC commercial headphone has passive and active noise cancellation features, making it suitable for health applications such as Pure Tone Hearing Screening. It can replace the sound-treated booth and standard headphones then reduce the test cost and make the test run in remote area. Bose headphone has better active and passive noise attenuation compared to Sony headphone. Bose headphone has 3.2 dB noise attenuation better than Sony headphone at 500 Hz. Bose headphone also provides quite zone. Bose headphone is also cheaper than Sony headphone. In term of passive attenuation TDH-49 better than Bose and Sony headphones. Therefore, Bose headphone is more suitable for health applications to protect the workers from ambient noise. If it can be calibrated to an accurate hearing cut off level, it can be used for pure tone hearing screening test (PTHST) outside sound-treated booth As such, 500 Hz test tone can be included for hearing screening because it has a good performance to attenuate low-frequency noise.

Over recent years, iris recognition has been an explosive growth of interest in human identification due to its high accuracy. Iris recognition is a biometric system that uses iris to verify and identify human identity. Iris has pattern that is rich with textures and can be compared among humans. There are many methods can be used in iris recognition. The methods based on the integro-differential operator and Hough transform are the most widely used in iris recognition. Unfortunately, both methods require more time to execute and has less accurate recognition accuracy due to the eyelid occlusion. In order to solve these problems, the Chan-Vese active contour is modified to reduce the execution time and to increase the recognition accuracy of iris recognition. Then, this method is compared with the integro-differential operator method. The iris images from CASIA-v4 database are used for the experiments. According to the results, the proposed method recorded 0.91 s for execution time which was 61.28 % faster than the integro-differential operator method. The proposed method also achieved 0.9831 for area under curve (AUC) which was 2.66 % higher recognition accuracy than the integro-differential operator method. To conclude, the modified Chan-Vese active contour was able to improve the performance of iris recognition compared to the integro-differential operator method.