Search

Plant leaf diseases have various causes, leading to severe disorders. The early and accurate detection and classification of these diseases are fundamental for fostering healthy crop production. In recent years, smart agricultural systems have garnered significant attention due to their capability to enhance efficiency by deploying sensor networks and Internet of Things (IoT) devices that collect and analyze environmental data. However, traditional plant disease detection methods are manual, time-consuming, and often need help handling the data’s complexity and dynamism. These manual methods do not use heterogeneous data to make better decisions. Corn holds significant importance yet it faces numerous diseases that include main three diseases such as blight, common rust, and grey leaf spot. The advancement of computer technology has led to a pivotal focus on corn leaf diseases classification application based on deep learning. Convolutional Neural Networks (CNNs) have revealed remarkable achievements within Precision Agriculture (PA) due to their ability to enhance information. To this end, this work introduces a CNN-based architecture, the Multi-Model Fusion Network (MMF-Net). Its primary objective is to classify diseases within the realm of PA. MMF-Net integrates multi-contextual features using RL-block and PL-blocks 1 & 2, thus effectively combining different model streams trained on heterogeneous data. The RL-block uses spatial range to process coarse grained images to convolve the local context, while PL-block 1 extracts fine-grained global context by expanding the perceptual area of images. PL-block 2 deals with real-life environmental parameters as features. The extracted features are syndicated using multiple classifiers that ensemble three individual blocks at the decision level to improve the accuracy. After fusion, it uses adaptively the majority voting scheme to generate the final decision probability score of the base model. Multiple experiments are conducted involving the corn leaf diseases dataset and a real-life numerical dataset, generating an impressive 99.23% accuracy in the classification of corn leaf diseases. Overall, MMF-Net provides a promising and smart solution to identify plant leaf diseases in PA effectively.

Retinitis pigmentosa (RP) is a group of genetic retinal disorders characterized by progressive vision loss, culminating in blindness. Identifying pigment signs (PS) linked with RP is crucial for monitoring and possibly slowing the disease’s degenerative course. However, the segmentation and detection of PS are challenging due to the difficulty of distinguishing between PS and blood vessels and the variability in size, shape, and color of PS. Recently, advances in deep learning techniques have shown impressive results in medical image analysis, especially in ophthalmology. This study presents an approach for classifying pigment marks in color fundus images of RP using a modified squeeze-and-excitation ResNet (SE-ResNet) architecture. This variant synergizes the efficiency of residual skip connections with the robust attention mechanism of the SE block to amplify feature representation. The SE-ResNet model was fine-tuned to determine the optimal layer configuration that balances performance metrics and computational costs. We trained the proposed model on the RIPS dataset, which comprises images from patients diagnosed at various RP stages. Experimental results confirm the efficacy of the proposed model in classifying different types of pigment signs associated with RP. The model yielded performance metrics, such as accuracy, sensitivity, specificity, and f-measure of 99.16%, 97.70%, 96.93%, 90.47%, 99.37%, 97.80%, 97.44%, and 90.60% on the testing set, based on GT1 & GT2 respectively. Given its performance, this model is an excellent candidate for integration into computer-aided diagnostic systems for RP, aiming to enhance patient care and vision-related healthcare services.

Optical Mark Recognition (OMR) systems have been studied since the 1970s. Due to its simplicity of use and efficiency in bulk operations, OMR technology has been gaining popularity over time. They are used as an automated data input technique for surveys and multiple-choice question papers in educational institutions for automatic evaluation and grading of student inputs. The requirement of the conventional OMR systems comprises specialized OMR machines or optical scanners with automatic document feeding capability. These machines and scanners are fixed-location devices and cannot be moved easily. Their energy requirements are high, while they also require human efforts to operate. These machines are expensive and, hence pose budget constraints for small educational institutions. Due to being mechanical, their maintenance and operating cost is high. To overcome these limitations, alternate devices are smartphone cameras, which though handy adversely lack the capability of scanning documents in a controlled environment. An uncontrolled environment leads to inputs that existing OMR algorithms do not recognize at large, while the accuracy rate and precision stay low to an undesirable extent. Due to this shortcoming, the usage of smartphone cameras is still not feasible. In this experimental study, we have proposed an OMR algorithm specifically for inputs taken from smartphones equipped with decent cameras and running Android or iOS operating systems. Thus effectively, we have ported the OMR technology to smartphones, offering more flexibility, easiness, and mobility of its usage in daily life. The key issue that transpired in our experiments is the bad illumination in different lighting conditions. Our results are very promising and comparable to those obtained from the usage of optical scanners.

Enhancing the crop yield predictability in intercropping systems is important for optimizing agricultural productivity. However, accurately predicting yield in such systems is quite challenging due to complex interactions between crops. This study introduces an advanced methodology using integrated loss functions within an optimally driven Feedback Neural Network (FNN) approach to improve yield prediction in a pea-cucumber intercropping systems. Traditional models relying only on Mean Square Error (MSE) loss function often unable to capture the complexity of models, leading to suboptimal performance. To address this limitation, the advanced loss functions are introduced like Dynamic Margin Loss (DML), Risk-Adjusted Loss (RAL), Quantile Loss (QL), and Hybrid Agronomic Efficiency Loss (HAEL) along with three optimizers such as Adaptive Momentum (Adam), Root Mean Square Propagation (RMSprop), and Adaptive delta (Adadelta). These loss functions incorporate risk, uncertainty, and agronomic efficiency into the model training process, enhances predictive capabilities and robustness. This proposed framework is able to capture the complexity of yield prediction by incorporating agricultural factors. While Gradient Boost Machines (GBM) and Long Short Term Memory (LSTM) have some potential, they are not able to capture these dynamics. The sensitivity and weight analysis also focuses that HAEL targets important agronomic factors such as nitrogen uptake and residue biomass, which provide a holistic view of yield prediction. The proposed approach improves the predictive performance compared to traditional models and helps to identify the importance of features, which makes it an effective tool for decision making in sustainable agriculture. Selecting appropriate loss functions is essential to improve the accuracy and robustness of crops yield prediction models. Thus, study provides a strong foundation for enhancing yield prediction in intricate intercropping systems, which all significantly enhance the advancement of precision agriculture.

Regression testing is carried out to test the updated supply code within the constraints of time and sources. Since it is very difficult to run all the updated source code every time, test case prioritization is needed to decrease the fee of regression testing. Various methodologies including extensions of white box and black box prioritization, have been presented considering the prioritization of test instances. In this context, the employment of particle swarm optimization (PSO) is usually recommended for test case prioritization. Single test case prioritization focuses to order test cases to maximize objectives like fault detection rate, execution time, etc. Regression testing for single-objective test suite prioritization can become challenging due to its longer execution time. However, test case prioritization for multi-objective functions is a complex and time-consuming task. A check suite may be organized in a certain order by an appropriate technique, subsequently permitting the detection of flaws as early as possible. Multi-goal particle swarm optimization (MOPSO) is used for case prioritization in regression testing. The purpose of MOPSO in this context is to organize the test suite in a specific order that maximizes fault coverage, provides sufficient coverage of test cases, and minimizes execution time. This study proposes an approach based on MOPSO that focuses on maximum fault coverage, most circumstance insurance, and minimal execution time. Experiments are performed using the average percentage of faults detected (APFD) to evaluate its performance. Performance analysis using APFD consisting of no order, opposite order, and random order indicates that the MOPSO surpasses all the previous techniques and obtains an 85% fault coverage. Moreover, MOPSO is better in terms of execution time, fault detection fee, and early detection capabilities.

Thalassemia is viewed as a prevalent inherited blood disease that has gotten exorbitant consideration in the field of medical research around the world. Inherited diseases have a high risk that children will get these diseases from their parents. If both the parents are $\beta $ -Thalassemia carriers then there are 25% chances that each child will have $\beta $ -Thalassemia intermediate or $\beta $ -Thalassemia major, which in most of its cases leads to death. Prenatal screening after counseling of couples is an effective way to control $\beta $ -Thalassemia. Generally, identification of the Thalassemia carriers is performed by some quantifiable blood traits determined effectively by high-performance-liquid-chromatography (HPLC) test, which is costly, time-consuming, and requires specialized equipment. However, cost-effective and rapid screening techniques need to be devised for this problem. This study aims to detect $\beta $ -Thalassemia carriers by evaluating red blood cell indices from the complete-blood-count test. The present study included Punjab Thalassemia Prevention Project Lab Reports dataset. The proposed SGR-VC is an ensemble of three machine learning algorithms: Support Vector Machine, Gradient Boosting Machine, and Random Forest. Comparative analysis proved that the proposed ensemble model using all indices of red blood cells is very effective in $\beta $ -Thalassemia carrier screening with 93% accuracy.

A number of techniques for securing plaintext, images and video frames have been developed in cryptography using jointly DNA computing and Chaos Theory. With the advancement of DNA/quantum computing, the threats of security breaches to information have an increasing possibility. In this paper, we propose a symmetric encryption algorithm for color images by extending the current encryption/decryption techniques. Our encryption algorithm is based on three chaotic systems (PWLCM, Lorenz and 4D Lorenz-type), a Secure Hash Algorithm, a scrambler, a chaotic generator and DNA sequence based Linear Feedback Shift Register. We introduce multilevel security to increase the degree of diffusion and confusion. Through experiments, we present security analysis for key irreproducibility and sensitivity, Gray Level Co-occurrence Matrix based analysis, maximum deviation, irregular deviation, entropy, histogram, variance and correlation, number of pixel change rate, unified average cipher intensity, known/chosen-plaintext attacks, mean absolute error, robustness against noises of various types using PSNR and occlusion attacks. It is demonstrated that mostly our proposed encryption algorithm has enhanced performance as compared to contemporary works in information security, while comparable in other cases.

This paper presents the Inverse Complex Generalized Synchronization (ICGS) of non-identical nonlinear complex systems with unknown parameters. Using the philosophy of adaptive integral sliding mode control, an adaptive controller and laws regarding parametric upgradation are designed to realize ICGS and parameter identification of two non-identical chaotic complex systems with respect to a given complex map vector. To employ the control, the error system is transformed into a unique structure containing a nominal part and some unknown terms, which are computed adaptively. Then, the error system is stabilized by using integral sliding mode control. The stabilizing controller for the error system is constructed, which consists of the fractional-order control plus some compensator control. To avoid the chattering phenomenon, smooth continuous compensator control is incorporated instead of traditional discontinuous control. The compensator controller and the adapted law are derived in such a way that the time derivative of a Lyapunov function becomes strictly negative. This scheme is applied to synchronize a Memristor-Based Hyperchaotic Complex (MBHC) Lu system and a Memristor-Based Chaotic Complex (MBCC) Lorenz system, a chaotic complex Chen system and a memristor-based chaotic complex Lorenz system with entirely unknown parameters. The effectiveness and feasibility of the proposed scheme is validated through computer simulation using MATLAB software package.

Machine learning (ML) based forecasting mechanisms have proved their significance to anticipate in perioperative outcomes to improve the decision making on the future course of actions. The ML models have long been used in many application domains which needed the identification and prioritization of adverse factors for a threat. Several prediction methods are being popularly used to handle forecasting problems. This study demonstrates the capability of ML models to forecast the number of upcoming patients affected by COVID-19 which is presently considered as a potential threat to mankind. In particular, four standard forecasting models, such as linear regression (LR), least absolute shrinkage and selection operator (LASSO), support vector machine (SVM), and exponential smoothing (ES) have been used in this study to forecast the threatening factors of COVID-19. Three types of predictions are made by each of the models, such as the number of newly infected cases, the number of deaths, and the number of recoveries in the next 10 days. The results produced by the study proves it a promising mechanism to use these methods for the current scenario of the COVID-19 pandemic. The results prove that the ES performs best among all the used models followed by LR and LASSO which performs well in forecasting the new confirmed cases, death rate as well as recovery rate, while SVM performs poorly in all the prediction scenarios given the available dataset.

The success of AES encryption standard created challenges for the cryptographers to construct strong substitution-boxes using different underlying approaches. It is because they are solely responsible to decide the robustness of cryptosystem against linear and differential cryptanalyses. With an aim to fulfill the mentioned requirement of robustness, a novel group theoretic and graphical method is proposed to construct S-box with optimal features. Firstly, a strong S-box is generated with the help of orbits of coset graphs and the action of proposed powerful permutation of symmetric group S256. In addition, a specific group is designed the action of whose pairs of permutations has the ability to generate as many as 462422016 strong S-boxes. Few of such proposed S-boxes are reported and assessed against standard performance parameters to validate the effectiveness of proposed findings. The features of proposed S-boxes are compared with most of the recent S-boxes to validate the superior performance. Moreover, they are also applied for image encryption to demonstrate their suitability for multimedia security applications.

This paper presents the control design method for the transmission projective synchronization (TPS) of the Multiple Non-identical Coupled Chaotic systems using sliding mode. A total of four different cases of chaotic systems are studied which are: 1) systems with known parameters without fault; 2) systems with known parameters with a fault; 3) systems with unknown parameters without fault; and 4) systems with unknown parameters and fault occurrence. In first and third cases, the controllers are designed using sliding mode, and adaptive integral sliding mode (AISM) is used to design controllers for the second and fourth cases. To employ AISM, the error dynamics is broken into a structure comprising a nominal and some unknown part, which are adaptively computed. The error dynamics are stabilized by AISM control which consists of a nominal and a compensator control. To avoid the chattering phenomenon, smooth continuous compensator control is used instead of the traditional discontinuous control. The stability of adaptive law and compensator is derived using a Lyapunov function which becomes strictly negative. Finally, the simulations of a numerical example verify the TPS behavior.

Distributed agile software development is a promising paradigm, addressing the necessities of emergent software application markets that are described by huge user base and small time to market characteristics. A key decision involved during the development process, is task allocation to team members. An appropriate task-member assignment facilitates project management, lessens the complexities and influences chances of project success. Task allocation becomes a more challenging activity in a distributed agile software development due to insufficient understanding of different factors and dependencies involved. We propose a task allocation framework comprising of two phases: one, identifying factors and dependencies that strongly influence the task allocation decision; two, proposing a quantitative method that allocates tasks to team members who best match the task requirements. Task requirements are expressed as capabilities, catering for different aspects, such as technical, personal, and environment. Our method stays transparent to the targeted objectives, in this case the best match. Other objectives, such as quality and cost may be introduced conveniently; even multiple objectives can be addressed. Such a method also allows quality evaluation of task-member assignment during and after the project completion, toward minimizing related risks.

In the above article [1], the funding information should read “This work was supported in part by the Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education under Grant NRF-2019R1A2C1006159, and in part by the Ministry of Science and ICT (MSIT), South Korea, under the Information Technology Research Center (ITRC) support program supervised by the Institute for Information Communications Technology Promotion (IITP), under Grant IITP-2020-2016-0-00313.”

Rapid urbanization in Lahore, Pakistan, has led to significant ecological and thermal challenges, particularly the intensification of urban heat island (UHI) effects and increased thermal stress as measured by the urban thermal field variance index (UTFVI). This study employs a multitemporal evaluation of Landsat satellite imagery and GIS-based analysis to investigate the spatio-temporal trends in land-use and land-cover changes from 1994 to 2024. We detected substantial changes in urban growth, vegetation cover, and barren areas using supervised classification (random forest) methods and remote sensing indices such as normalized difference vegetation index, normalized difference moisture index, normalized difference built-up index, and normalized difference water index. The classification models demonstrated high accuracy, with combined values ranging from 96.7% to 98.4%. Our results indicate a significant increase in metropolitan regions, from 608.66 km2 (32.43%) in 1994 to 968.50 km2 (51.6%) in 2024. This urban expansion correlates with rising land surface temperatures, exacerbating UHI effects. The UTFVI analysis reveals a progressive rise in heat stress from 1994 to 2024. In 1994, most areas ranged from “Good” (0.020), indicating severe urban heat intensification, particularly in central and southern regions providing evidence of a significant increase in urban heat, especially in the center and southern areas of the city. These findings underscore the critical need for sustainable land management strategies to mitigate the adverse effects of Lahore's rapid urbanization on the environment. This study comprehensively explains unplanned urban growth's ecological and climatic consequences. The importance of balanced development in protecting natural ecosystems and enhancing urban resilience is highlighted, offering valuable insights for urban planners and policymakers.

Changes in land use and land cover (LULC) are critical for evaluating global spatiotemporal trends, especially regarding climate change and urbanization. This study investigates the dynamics of Landsat surface temperature (LST) in response to LULC changes and their effects on the seasonal microclimate in Kasur District, Pakistan. Using the Google Earth Engine platform, we employed a random forest algorithm to detect LULC changes (cropland, forest, built-up, fallow, barren, and water) and analyze seasonal spectral indices from Landsat imagery for 1988, 2002, and 2022. Significant LULC changes were observed, including a 9.8% increase in built-up areas, a 4.2% decrease in cropland, and a 1.4% decrease in forested areas, linked to urban heat island effects and population growth. Additionally, there was a 2.7% increase in fallow and open land, contributing to the district's impervious surface area. Significant correlations (p < 0.001) were found between LST and spectral indices—normalized difference vegetation index, enhanced vegetation index, and normalized difference built index (NDBI)—ranging from 0.7 to 0.8 in both winter and summer. In summer, the maximum LST increased from 43 °C in 1988 to 44 °C in 2002, with a linear correlation (R²) increase from 0.57 to 0.75 and a polynomial correlation (R²) increase from 0.63 to 0.76 with NDBI from 1988 to 2022. Understanding these dynamics is crucial as LULC changes and the resulting temperature variations have significant implications for local climate, agriculture, and human health. This study underscores the need for effective LULC policies to mitigate impacts, protect vegetation cover, and ensure sustainable land management. These findings provide valuable insights for policymakers and urban planners aiming to balance development with environmental sustainability.