-
Research Article
Image Reconstruction in Compressive Sensing Using the Level 3 Biorthogonal 4.4 (bior4.4) Discrete Wavelet Transform and SP, CoSaMP and ALISTA Algorithm
Issue:
Volume 9, Issue 2, December 2025
Pages:
14-21
Received:
1 October 2025
Accepted:
14 October 2025
Published:
31 October 2025
Abstract: This work proposes an efficient image reconstruction method based on compressive sensing (CS), combining the level-3 biorthogonal 4.4 (bior4.4) discrete wavelet transform with three iterative reconstruction algorithms: Subspace Pursuit (SP), Compressive Sampling Matched Pursuit (CoSaMP), and ALISTA. The approach follows four key steps: (1) decomposing the original image via the wavelet transform to obtain a sparse representation, (2) performing compressed sampling using a random measurement matrix, (3) reconstructing the sparse signal from the reduced measurements, and (4) recovering the final image through the inverse transform. Experimental evaluation uses the standard Lena image (200 × 200 pixels) and compares the performance of the three algorithms according to two criteria: reconstruction quality (measured by SSIM) and computational cost (reconstruction time in minutes), across sampling rates ranging from 10% to 60%. Results show that all three methods achieve very similar SSIM scores (up to >0.96 at 60%), indicating high structural fidelity. However, ALISTA stands out significantly for its temporal efficiency, particularly at low sampling rates (<0.1 minute at 10%), while CoSaMP exhibits high and unstable computation times (peaking at ~38 minutes at 40%). SP offers a stable compromise but is slower than ALISTA. These results demonstrate that ALISTA provides the best trade-off between quality and speed. Thus, this study validates the value of coupling the bior4.4 wavelet basis with modern optimization algorithms for practical CS applications in image processing, where computational efficiency is as critical as reconstruction accuracy.
Abstract: This work proposes an efficient image reconstruction method based on compressive sensing (CS), combining the level-3 biorthogonal 4.4 (bior4.4) discrete wavelet transform with three iterative reconstruction algorithms: Subspace Pursuit (SP), Compressive Sampling Matched Pursuit (CoSaMP), and ALISTA. The approach follows four key steps: (1) decompos...
Show More
-
Research Article
Image Reconstruction in Compressive Sensing Using Reverse Biorthogonal 6.8 (rbio6.8) and Lifting Wavelet Transforms with SP, CoSaMP, and ALISTA Algorithms
Issue:
Volume 9, Issue 2, December 2025
Pages:
22-35
Received:
20 October 2025
Accepted:
3 November 2025
Published:
9 December 2025
Abstract: This paper proposes an efficient image reconstruction for compressive sensing (CS) that combines the Lifting Wavelet Transform (LWT) using Reverse Biorthogonal 6.8 (rbio6.8) wavelets with three reconstruction algorithms: Subspace Pursuit (SP), Compressive Sampling Matching Pursuit (CoSaMP), and the Analytic Learned Iterative Shrinkage Thresholding Algorithm (ALISTA). Unlike the conventional Discrete Wavelet Transform (DWT) which relies on computationally intensive convolution operations the LWT provides a faster sparse representation while preserving the sparsity crucial for CS. The proposed approach leverages a key insight: among the four subbands produced by the LWT namely the approximation (CA) and the detail coefficients (LH, HL, HH) only the latter three are inherently sparse. Therefore, compressive sensing is applied exclusively to these detail subbands, while the CA subband is left uncompressed to retain essential low-frequency information. Experiments were conducted on both a natural test image (Lena) and a medical MRI scan, across image resolutions ranging from 200×200 to 512×512 pixels and sampling rates from 10% to 80%. Performance was assessed using the Structural Similarity Index (SSIM) and reconstruction time. Results consistently demonstrate that ALISTA significantly outperforms SP and CoSaMP in both reconstruction fidelity and computational efficiency. At an 80% sampling rate, ALISTA achieves SSIM values of 0.99314 for Lena and 0.97688 for the MRI image, compared to approximately 0.97402 and 0.93577, respectively, for the other two methods. Furthermore, ALISTA maintains remarkably low reconstruction times under 4 seconds even for 512×512-pixel images. These findings confirm that the ALISTA + LWT/rbio6.8 combination offers the best trade-off between image quality and speed, exhibiting robustness across different image types and scales.
Abstract: This paper proposes an efficient image reconstruction for compressive sensing (CS) that combines the Lifting Wavelet Transform (LWT) using Reverse Biorthogonal 6.8 (rbio6.8) wavelets with three reconstruction algorithms: Subspace Pursuit (SP), Compressive Sampling Matching Pursuit (CoSaMP), and the Analytic Learned Iterative Shrinkage Thresholding ...
Show More
-
Research Article
Application of Artificial Intelligence in Agricultural Process
Sina Moghadam
,
Reza Alimardani*
Issue:
Volume 9, Issue 2, December 2025
Pages:
36-44
Received:
24 October 2025
Accepted:
4 November 2025
Published:
9 December 2025
Abstract: The continuous growth of the global population and rapid scientific advancements have increased the demand for high precision and efficient agricultural practices. Artificial Intelligence (AI) has emerged as a transformative tool to enhance the speed, accuracy, and automation of various agricultural processes. This study reviews the recent applications of AI, particularly image processing and machine vision techniques, in different stages of agricultural production, including planting, plowing, harvesting, and post-harvest operations such as storage, silage preparation, and drying. The findings indicate that AI assisted systems can effectively detect plant diseases, estimate yield, monitor soil and crop conditions, and optimize machinery operations with minimal human interventions. Furthermore, the integration of AI with Internet of Things (IoT) technologies enables real time data collection and intelligent decision making in smart farming systems. Despite the significant process made. Continuous technological development and the emergence of new agricultural challenges highlight the need for further research into advanced image processing algorithms, deep learning models, and data driven optimization approaches. Overall, AI and machine vision technologies have proven to be essential components for achieving sustainable, precise, and intelligent agricultural production.
Abstract: The continuous growth of the global population and rapid scientific advancements have increased the demand for high precision and efficient agricultural practices. Artificial Intelligence (AI) has emerged as a transformative tool to enhance the speed, accuracy, and automation of various agricultural processes. This study reviews the recent applicat...
Show More
-
Research Article
Implementation of a Kalman Filter for Noise Reduction on the INA219 Current Sensor
Issue:
Volume 9, Issue 2, December 2025
Pages:
45-55
Received:
25 October 2025
Accepted:
13 November 2025
Published:
9 December 2025
Abstract: The existence of a sensor is very essential and is needed by a digital system to produce the right decision. But every use of a sensor will have an error and noise process that cannot be avoided, and greatly affects the accuracy of the measurement results. One of the popular sensors in the market place is the INA219 sensor made by Texas Instrument which is often used to measure dc current. But the results of the experiment show that the sensor cannot be used directly because its output is relatively unstable or fluctuates. This paper implements the Standard Kalman Filter to reduce noise on the INA219 sensor to produce more accurate dc current measurements. The experimental results show that the variance value of the KF output is much smaller than the sensor output, so that the Kalman filter algorithm has worked optimally to produce accurate DC current measurements. Besides that, Kalman Filer is also very suitable for use in DC motor control as a dynamic system that implements duty cycle (D) changes in the PWM method on its DC input voltage. The Output of Standard Kalman Filter which has been implemented with the ESP32 are influenced by the values assigned to the noise sensor covariance matrix (R) and process noise covariance (Q). With a value of R=100, for resistive loads the values of Q=0.5, while for inductive load (DC motor), the values of Q=0.05 have effectively reduced the amount of noise to enhance the accuracy and precision in using the INA219 current sensor.
Abstract: The existence of a sensor is very essential and is needed by a digital system to produce the right decision. But every use of a sensor will have an error and noise process that cannot be avoided, and greatly affects the accuracy of the measurement results. One of the popular sensors in the market place is the INA219 sensor made by Texas Instrument ...
Show More
