| Annals of Emerging Technologies in Computing (AETiC) |
|
| IAER
| AETiC
| Editorial Board
| Instructions
| Indexing
| Submit Paper
| Special Issues
| Archives
| Contact Us
|
|
 |
|
|
|
Single-channel Speech Separation Based on Double-density Dual-tree CWT and SNMF Md Imran Hossain, Md Abdur Rahim and Md Najmul Hossain Abstract: Speech is essential to human communication; therefore, distinguishing it from noise is crucial. Speech separation becomes challenging in real-world circumstances with background noise and overlapping speech. Moreover, the speech separation using short-term Fourier transform (STFT) and discrete wavelet transform (DWT) addresses time and frequency resolution and time-variation issues, respectively. To solve the above issues, a new speech separation technique is presented based on the double-density dual-tree complex wavelet transform (DDDTCWT) and sparse non-negative matrix factorization (SNMF). The signal is separated into high-pass and low-pass frequency components using DDDTCWT wavelet decomposition. For this analysis, we only considered the low-pass frequency components and zeroed out the high-pass ones. Subsequently, the STFT is then applied to each sub-band signal to generate a complex spectrogram. Therefore, we have used SNMF to factorize the joint form of magnitude and the absolute value of real and imaginary (RI) components that decompose the basis and weight matrices. Most researchers enhance the magnitude spectra only, ignore the phase spectra, and estimate the separated speech using noisy phase. As a result, some noise components are present in the estimated speech results. We are dealing with the signal's magnitude as well as the RI components and estimating the phase of the RI parts. Finally, separated speech signals can be achieved using the inverse STFT (ISTFT) and the inverse DDDTCWT (IDDDTCWT). Separation performance is improved for estimating the phase component and the shift-invariant, better direction selectivity, and scheme freedom properties of DDDTCWT. The speech separation efficiency of the proposed algorithm outperforms performance by 6.53–8.17 dB SDR gain, 7.37-9.87 dB SAR gain, and 14.92–17.21 dB SIR gain compared to the NMF method with masking on the TIMIT dataset. Keywords: Double Density Dual-Tree Complex Wavelet Transform; Speech Separation; Sparse Non-negative Matrix Factorization; Short-time Fourier Transform. |
Optimisation and Performance Computation of a Phase Frequency Detector Module for IoT Devices Md. Shahriar Khan Hemel, Mamun Bin Ibne Reaz, Sawal Hamid Bin Md Ali, Mohammad Arif Sobhan Bhuiyan and Mahdi H. Miraz Abstract: The Internet of Things (IoT) is pivotal in transforming the way we live and interact with our surroundings. To cope with the advancement in technologies, it is vital to acquire accuracy with the speed. A phase frequency detector (PFD) is a critical device to regulate and provide accurate frequency in IoT devices. Designing a PFD poses challenges in achieving precise phase detection, minimising dead zones, optimising power consumption, and ensuring robust performance across various operational frequencies, necessitating complex engineering and innovative solutions. This study delves into optimising a PFD circuit, designed using 90 nm standard CMOS technology, aiming to achieve superior operational frequencies. An efficient and high-frequency PFD design is crafted and analysed using cadence virtuoso. The study focused on investigating the impact of optimising PFD design. With the optimised PFD, an operational frequency of 5 GHz has been achieved, along with a power consumption of only 29 µW. The dead zone of the PFD was only 25 ps. Keywords: Cadence virtuoso; Digital circuit; Optimisation; Phase-locked loop (PLL); Phase frequency detector (PFD); 90 nm CMOS. |
Trajectory Optimization for a 6 DOF Robotic Arm Based on Reachability Time Mahmoud A. A. Mousa, Abdelrahman T. Elgohr, and Hatem A. Khatern Abstract: The design of the robotic arm's trajectory is based on inverse kinematics problem solving, with additional refinements of certain criteria. One common design issue is the trajectory optimization of the robotic arm. Due to the difficulty of the work in the past, many of the suggested ways only resulted in a marginal improvement. This paper introduces two approaches to solve the problem of achieving robotic arm trajectory control while maintaining the minimum reachability time. These two approaches are based on rule-based optimization and a genetic algorithm. The way we addressed the problem here is based on the robot’s forward and inverse kinematics and takes into account the minimization of operating time throughout the operation cycle. The proposed techniques were validated, and all recommended criteria were compared on the trajectory optimization of the KUKA KR 4 R600 six-degree-of-freedom robot. As a conclusion, the genetic based algorithm behaves better than the rule-based one in terms of achieving a minimal trip time. We found that solutions generated by the Genetic based algorithm are approximately 3 times faster than the other solutions generated by the rule-based algorithm to the same paths. We argue that as the rule-based algorithm produces its solutions after discovering all the problem’s searching space which is time consuming, and it is not the case as per the genetic based algorithm. Keywords: Forward Kinematics; Genetic Algorithm; Inverse Kinematics; Rule-Based Optimization; Trajectory Control; Trajectory Optimization; 6 DOF Robotic Arm. |
Explainable Software Defects Classification Using SMOTE and Machine Learning Agboeze Jude and Jia Uddin Abstract: Software defect prediction is a critical task in software engineering that aims to identify and mitigate potential defects in software systems. In recent years, numerous techniques and approaches have been developed to improve the accuracy and efficiency of the defect prediction model. In this research paper, we proposed a comprehensive approach that addresses class imbalance by utilizing stratified splitting, explainable AI techniques, and a hybrid machine learning algorithm. To mitigate the impact of class imbalance, we employed stratified splitting during the training and evaluation phases. This method ensures that the class distribution is maintained in both the training and testing sets, enabling the model to learn from and generalize to the minority class examples effectively. Furthermore, we leveraged explainable AI methods, Lime and Shap, to enhance interpretability in the machine learning models. To improve prediction accuracy, we propose a hybrid machine learning algorithm that combines the strength of multiple models. This hybridization allows us to exploit the strength of each model, resulting in improved overall performance. The experiment is evaluated using the NASA-MD datasets. The result revealed that handling the class imbalanced data using stratify splitting approach achieves a better overall performance than the SMOTE approach in Software Defect Detection (SDD). Keywords: Classification; Detection; Explainable AI; Machine learning; Software Defect. |
Deep Learning Based Cyberbullying Detection in Bangla Language Sristy Shidul Nath, Razuan Karim and Mahdi H. Miraz Abstract: The Internet is currently the largest platform for global communication including expressions of opinions, reviews, contents, images, videos and so forth. Moreover, social media has now become a very broad and highly engaging platform due to its immense popularity and swift adoption trend. Increased social networking, however, also has detrimental impacts on the society leading to a range of unwanted phenomena, such as online assault, intimidation, digital bullying, criminality and trolling. Hence, cyberbullying has become a pervasive and worrying problem that poses considerable psychological and emotional harm to the people, particularly amongst the teens and the young adults. In order to lessen its negative effects and provide victims with prompt support, a great deal of research to identify cyberbullying instances at various online platforms is emerging. In comparison to other languages, Bangla (also known as Bengali) has fewer research studies in this domain. This study demonstrates a deep learning strategy for identifying cyberbullying in Bengali, using a dataset of 12282 versatile comments from multiple social media sites. In this study, a two-layer bidirectional long short-term memory (Bi-LSTM) model has been built to identify cyberbullying, using a variety of optimisers as well as 5-fold cross validation. To evaluate the functionality and efficacy of the proposed system, rigorous assessment and validation procedures have been employed throughout the project. The results of this study reveals that the proposed model’s accuracy, using momentum-based stochastic gradient descent (SGD) optimiser, is 94.46%. It also reflects a higher accuracy of 95.08% and a F1 score of 95.23% using Adam optimiser as well as a better accuracy of 94.31% in 5-fold cross validation. Keywords: Bangla; Bengali; Cyberbullying; Deep Learning; K-Fold Cross Validation; Natural Language Processing. |
|