Enhancing IoT Security through a Green and Sustainable Federated Learning Platform: Leveraging Efficient Encryption and the Quondam Signature Algorithm.

This research paper introduces a novel paradigm that synergizes innovative algorithms, namely efficient data encryption, the Quondam Signature Algorithm (QSA), and federated learning, to effectively counteract random attacks targeting Internet of Things (IoT) systems. The incorporation of federated learning not only fosters continuous learning but also upholds data privacy, bolsters security measures, and provides a robust defence mechanism against evolving threats. The Quondam Signature Algorithm (QSA) emerges as a formidable solution, adept at mitigating vulnerabilities linked to man-in-the-middle attacks. Remarkably, the QSA algorithm achieves noteworthy cost savings in IoT communication by optimizing communication bit requirements. By seamlessly integrating federated learning, IoT systems attain the ability to harmoniously aggregate and analyse data from an array of devices while zealously guarding data privacy. The decentralized approach of federated learning orchestrates local machine-learning model training on individual devices, subsequently amalgamating these models into a global one. Such a mechanism not only nurtures data privacy but also empowers the system to harness diverse data sources, enhancing its analytical capabilities. A thorough comparative analysis scrutinizes varied cost-in-communication schemes, meticulously weighing both encryption and federated learning facets. The proposed approach shines by virtue of its optimization of time complexity through the synergy of offline phase computations and online phase signature generation, hinged on an elliptic curve digital signature algorithm-based online/offline scheme. In contrast, the Slow Block Move (SBM) scheme lags behind, necessitating over 25 rounds, 1500 signature generations, and an equal number of verifications. The proposed scheme, fortified by its marriage of federated learning and efficient encryption techniques, emerges as an embodiment of improved efficiency and reduced communication costs. The culmination of this research underscores the intrinsic benefits of the proposed approach: marked reduction in communication costs, elevated analytical prowess, and heightened resilience against the spectrum of attacks that IoT systems confront.

Semi-Supervised Clustering-Based DANA Algorithm for Data Gathering and Disease Detection in Healthcare Wireless Sensor Networks (WSN).

Wireless sensor networks (WSNs) have emerged as a promising technology in healthcare, enabling continuous patient monitoring and early disease detection. This study introduces an innovative approach to WSN data collection tailored for disease detection through signal processing in healthcare scenarios. The proposed strategy leverages the DANA (data aggregation using neighborhood analysis) algorithm and a semi-supervised clustering-based model to enhance the precision and effectiveness of data collection in healthcare WSNs. The DANA algorithm optimizes energy consumption and prolongs sensor node lifetimes by dynamically adjusting communication routes based on the network's real-time conditions. Additionally, the semi-supervised clustering model utilizes both labeled and unlabeled data to create a more robust and adaptable clustering technique. Through extensive simulations and practical deployments, our experimental assessments demonstrate the remarkable efficacy of the proposed method and model. We conducted a comparative analysis of data collection efficiency, energy utilization, and disease detection accuracy against conventional techniques, revealing significant improvements in data quality, energy efficiency, and rapid disease diagnosis. This combined approach of the DANA algorithm and the semi-supervised clustering-based model offers healthcare WSNs a compelling solution to enhance responsiveness and reliability in disease diagnosis through signal processing. This research contributes to the advancement of healthcare monitoring systems by offering a promising avenue for early diagnosis and improved patient care, ultimately transforming the landscape of healthcare through enhanced signal processing capabilities.

Enhancing Generalizability in Biomedical Entity Recognition: Self-Attention PCA-CLS Model.

One of the primary tasks in the early stages of data mining involves the identification of entities from biomedical corpora. Traditional approaches relying on robust feature engineering face challenges when learning from available (un-)annotated data using data-driven models like deep learning-based architectures. Despite leveraging large corpora and advanced deep learning models, domain generalization remains an issue. Attention mechanisms are effective in capturing longer sentence dependencies and extracting semantic and syntactic information from limited annotated datasets. To address out-of-vocabulary challenges in biomedical text, the PCA-CLS (Position and Contextual Attention with CNN-LSTM-Softmax) model combines global self-attention and character-level convolutional neural network techniques. The model's performance is evaluated on eight distinct biomedical domain datasets encompassing entities such as genes, drugs, diseases, and species. The PCA-CLS model outperforms several state-of-the-art models, achieving notable F1-scores, including 88.19% on BC2GM, 85.44% on JNLPBA, 90.80% on BC5CDR-chemical, 87.07% on BC5CDR-disease, 89.18% on BC4CHEMD, 88.81% on NCBI, and 91.59% on the s800 dataset.

Corrigendum: Sensor-based precision nutrient and irrigation management enhances the physiological performance, water productivity, and yield of soybean under system of crop intensification.

[This corrects the article DOI: 10.3389/fpls.2023.1282217.].

Spatial attention-based residual network for human burn identification and classification.

Diagnosing burns in humans has become critical, as early identification can save lives. The manual process of burn diagnosis is time-consuming and complex, even for experienced doctors. Machine learning (ML) and deep convolutional neural network (CNN) models have emerged as the standard for medical image diagnosis. The ML-based approach typically requires handcrafted features for training, which may result in suboptimal performance. Conversely, DL-based methods automatically extract features, but designing a robust model is challenging. Additionally, shallow DL methods lack long-range feature dependency, decreasing efficiency in various applications. We implemented several deep CNN models, ResNeXt, VGG16, and AlexNet, for human burn diagnosis. The results obtained from these models were found to be less reliable since shallow deep CNN models need improved attention modules to preserve the feature dependencies. Therefore, in the proposed study, the feature map is divided into several categories, and the channel dependencies between any two channel mappings within a given class are highlighted. A spatial attention map is built by considering the links between features and their locations. Our attention-based model BuRnGANeXt50 kernel and convolutional layers are also optimized for human burn diagnosis. The earlier study classified the burn based on depth of graft and non-graft. We first classified the burn based on the degree. Subsequently, it is classified into graft and non-graft. Furthermore, the proposed model performance is evaluated on Burns_BIP_US_database. The sensitivity of the BuRnGANeXt50 is 97.22% and 99.14%, respectively, for classifying burns based on degree and depth. This model may be used for quick screening of burn patients and can be executed in the cloud or on a local machine. The code of the proposed method can be accessed at https://github.com/dhirujis02/Journal.git for the sake of reproducibility.

Distinctive approach in brain tumor detection and feature extraction using biologically inspired DWT method and SVM.

Brain tumors result from uncontrolled cell growth, potentially leading to fatal consequences if left untreated. While significant efforts have been made with some promising results, the segmentation and classification of brain tumors remain challenging due to their diverse locations, shapes, and sizes. In this study, we employ a combination of Discrete Wavelet Transform (DWT) and Principal Component Analysis (PCA) to enhance performance and streamline the medical image segmentation process. Proposed method using Otsu's segmentation method followed by PCA to identify the most informative features. Leveraging the grey-level co-occurrence matrix, we extract numerous valuable texture features. Subsequently, we apply a Support Vector Machine (SVM) with various kernels for classification. We evaluate the proposed method's performance using metrics such as accuracy, sensitivity, specificity, and the Dice Similarity Index coefficient. The experimental results validate the effectiveness of our approach, with recall rates of 86.9%, precision of 95.2%, F-measure of 90.9%, and overall accuracy. Simulation of the results shows improvements in both quality and accuracy compared to existing techniques. In results section, experimental Dice Similarity Index coefficient of 0.82 indicates a strong overlap between the machine-extracted tumor region and the manually delineated tumor region.

Inferring linear-B cell epitopes using 2-step metaheuristic variant-feature selection using genetic algorithm.

Linear-B cell epitopes (LBCE) play a vital role in vaccine design; thus, efficiently detecting them from protein sequences is of primary importance. These epitopes consist of amino acids arranged in continuous or discontinuous patterns. Vaccines employ attenuated viruses and purified antigens. LBCE stimulate humoral immunity in the body, where B and T cells target circulating infections. To predict LBCE, the underlying protein sequences undergo a process of feature extraction, feature selection, and classification. Various system models have been proposed for this purpose, but their classification accuracy is only moderate. In order to enhance the accuracy of LBCE classification, this paper presents a novel 2-step metaheuristic variant-feature selection method that combines a linear support vector classifier (LSVC) with a Modified Genetic Algorithm (MGA). The feature selection model employs mono-peptide, dipeptide, and tripeptide features, focusing on the most diverse ones. These selected features are fed into a machine learning (ML)-based parallel ensemble classifier. The ensemble classifier combines correctly classified instances from various classifiers, including k-Nearest Neighbor (kNN), random forest (RF), logistic regression (LR), and support vector machine (SVM). The ensemble classifier came up with an impressively high accuracy of 99.3% as a result of its work. This accuracy is superior to the most recent models that are considered to be state-of-the-art for linear B-cell classification. As a direct consequence of this, the entire system model can now be utilised effectively in real-time clinical settings.

Elucidating the interactive impact of tillage, residue retention and system intensification on pearl millet yield stability and biofortification under rainfed agro-ecosystems.

Micronutrient malnutrition and suboptimal yields pose significant challenges in rainfed cropping systems worldwide. To address these issues, the implementation of climate-smart management strategies such as conservation agriculture (CA) and system intensification of millet cropping systems is crucial. In this study, we investigated the effects of different system intensification options, residue management, and contrasting tillage practices on pearl millet yield stability, biofortification, and the fatty acid profile of the pearl millet. ZT systems with intercropping of legumes (cluster bean, cowpea, and chickpea) significantly increased productivity (7-12.5%), micronutrient biofortification [Fe (12.5%), Zn (4.9-12.2%), Mn (3.1-6.7%), and Cu (8.3-16.7%)], protein content (2.2-9.9%), oil content (1.3%), and fatty acid profile of pearl millet grains compared to conventional tillage (CT)-based systems with sole cropping. The interactive effect of tillage, residue retention, and system intensification analyzed using GGE statistical analysis revealed that the best combination for achieving stable yields and micronutrient fortification was residue retention in both (wet and dry) seasons coupled with a ZT pearl millet + cowpea-mustard (both with and without barley intercropping) system. In conclusion, ZT combined with residue recycling and legume intercropping can be recommended as an effective approach to achieve stable yield levels and enhance the biofortification of pearl millet in rainfed agroecosystems of South Asia.

Sensor-based precision nutrient and irrigation management enhances the physiological performance, water productivity, and yield of soybean under system of crop intensification.

Sensor-based decision tools provide a quick assessment of nutritional and physiological health status of crop, thereby enhancing the crop productivity. Therefore, a 2-year field study was undertaken with precision nutrient and irrigation management under system of crop intensification (SCI) to understand the applicability of sensor-based decision tools in improving the physiological performance, water productivity, and seed yield of soybean crop. The experiment consisted of three irrigation regimes [I1: standard flood irrigation at 50% depletion of available soil moisture (DASM) (FI), I2: sprinkler irrigation at 80% ETC (crop evapo-transpiration) (Spr 80% ETC), and I3: sprinkler irrigation at 60% ETC (Spr 60% ETC)] assigned in main plots, with five precision nutrient management (PNM) practices{PNM1-[SCI protocol], PNM2-[RDF, recommended dose of fertilizer: basal dose incorporated (50% N, full dose of P and K)], PNM3-[RDF: basal dose point placement (BDP) (50% N, full dose of P and K)], PNM4-[75% RDF: BDP (50% N, full dose of P and K)] and PNM5-[50% RDF: BDP (50% N, full P and K)]} assigned in sub-plots using a split-plot design with three replications. The remaining 50% N was top-dressed through SPAD assistance for all the PNM practices. Results showed that the adoption of Spr 80% ETC resulted in an increment of 25.6%, 17.6%, 35.4%, and 17.5% in net-photosynthetic rate (Pn), transpiration rate (Tr), stomatal conductance (Gs), and intercellular CO2 concentration (Ci), respectively, over FI. Among PNM plots, adoption of PNM3 resulted in a significant (p=0.05) improvement in photosynthetic characters like Pn (15.69 µ mol CO2 m-2 s-1), Tr (7.03 m mol H2O m-2 s-1), Gs (0.175 µmol CO2 mol-1 year-1), and Ci (271.7 mol H2O m2 s-1). Enhancement in SPAD (27% and 30%) and normalized difference vegetation index (NDVI) (42% and 52%) values were observed with nitrogen (N) top dressing through SPAD-guided nutrient management, helped enhance crop growth indices, coupled with better dry matter partitioning and interception of sunlight. Canopy temperature depression (CTD) in soybean reduced by 3.09-4.66°C due to adoption of sprinkler irrigation. Likewise, Spr 60% ETc recorded highest irrigation water productivity (1.08 kg ha-1 m-3). However, economic water productivity (27.5 INR ha-1 m-3) and water-use efficiency (7.6 kg ha-1 mm-1 day-1) of soybean got enhanced under Spr 80% ETc over conventional cultivation. Multiple correlation and PCA showed a positive correlation between physiological, growth, and yield parameters of soybean. Concurrently, the adoption of Spr 80% ETC with PNM3 recorded significantly higher grain yield (2.63 t ha-1) and biological yield (8.37 t ha-1) over other combinations. Thus, the performance of SCI protocols under sprinkler irrigation was found to be superior over conventional practices. Hence, integrating SCI with sensor-based precision nutrient and irrigation management could be a viable option for enhancing the crop productivity and enhance the resource-use efficiency in soybean under similar agro-ecological regions.

Image-based decision making for reliable and proper diagnosing in NIFTI format using watermarking.

Nowadays, advancement in Magnetic Resonance Imaging (MRI) and Computed Tomography Scan (CT-Scan) technologies have defined modern neuroimaging and drastically change the diagnosing of disease in the world healthcare system. These imaging technologies generate NIFTI (Neuroimaging Informatics Technology Initiative) images. Due to COVID-19 last several months CT-Scan has been performed on millions of the CORONA patients, so billions of the NIFTI images have been produced and communicate over the internet for the diagnosing purpose to detect the coronavirus. The communication of these medical images over the internet yielding the major problem of integrity, copyright protection, and other ethical issues for the world health care system. Another critical problem is that; is doctor diagnose the impeccable medical image of the patient because a large amount of COVID-19 patient's data exists. For proper diagnosing it is also necessary to identify impeccable medical image. Therefore, to address these problems a secure and robust watermarking scheme is needed for these images. Various watermarking schemes have been developed for bmp, .jpg, .png, DICOM, and other image formats but the noticeable contribution is not reported for the NIFTI images. In this paper a robust and hybrid watermarking scheme for NIFTI images based on Lifting Wavelet Transform (LWT), MSVD (Multiresolution Singular Value Decomposition) and QR factorization. The combination of LWT, QR, and MSVD helps in retaining the sensitivity of the NIFTI image and improve the robustness of the watermarking scheme. In this scheme, multiple watermarks are inserted across the first slice of the NIFTI image. The proposed watermarking scheme is sustained against various noise attacks and performance is measured in terms of PSNR, SNR, SSIM, Quality of image, and Normalized correlation. Quality of the image is much significant that lie between .99994 to .99998 and SSIM reported from .94 to .99. Whereas the PSNR of the proposed scheme lies between 56.76 to 57.28 db and NC values lie between .9993 to .9998. which shows that the results are better than the existing schemes where PSNR is lies between 32.66 to 52.02 db. Watermarking, NIFTI, MSVD, LWT, QR and Image.

Noise Suppression and Edge Preservation for Low-Dose COVID-19 CT Images Using NLM and Method Noise Thresholding in Shearlet Domain.

In the COVID-19 era, it may be possible to detect COVID-19 by detecting lesions in scans, i.e., ground-glass opacity, consolidation, nodules, reticulation, or thickened interlobular septa, and lesion distribution, but it becomes difficult at the early stages due to embryonic lesion growth and the restricted use of high dose X-ray detection. Therefore, it may be possible for a patient who may or may not be infected with coronavirus to consider using high-dose X-rays, but it may cause more risks. Conclusively, using low-dose X-rays to produce CT scans and then adding a rigorous denoising algorithm to the scans is the best way to protect patients from side effects or a high dose X-ray when diagnosing coronavirus involvement early. Hence, this paper proposed a denoising scheme using an NLM filter and method noise thresholding concept in the shearlet domain for noisy COVID CT images. Low-dose COVID CT images can be further utilized. The results and comparative analysis showed that, in most cases, the proposed method gives better outcomes than existing ones.

Seed Germination Ecology of Chenopodium album and Chenopodium murale.

Chenopodium album L. and Chenopodium murale L. are two principal weed species, causing substantial damage to numerous winter crops across the globe. For sustainable and resource-efficient management strategies, it is important to understand weeds' germination behaviour under diverse conditions. For the germination investigations, seeds of both species were incubated for 15 days under different temperatures (10−30 °C), salinity (0−260 mM NaCl), osmotic stress (0−1 MPa), pH (4−10), and heating magnitudes (50−200 °C). The results indicate that the germination rates of C. album and C. murale were 54−95% and 63−97%, respectively, under a temperature range of 10 to 30 °C. The salinity levels for a 50% reduction in the maximum germination (GR50) for C. album and C. murale were 139.9 and 146.3 mM NaCl, respectively. Regarding osmotic stress levels, the GR50 values for C. album and C. murale were 0.44 and 0.43 MPa, respectively. The two species showed >95% germination with exposure to an initial temperature of 75 °C for 5 min; however, seeds exposed to 100 °C and higher temperatures did not show any germination. Furthermore, a drastic reduction in germination was observed when the pH was less than 6.0 and greater than 8.0. The study generated information on the germination biology of two major weed species under diverse ecological scenarios, which may be useful in developing efficient weed management tactics for similar species in future agri-food systems.

No-Tillage with Residue Retention and Foliar Sulphur Nutrition Enhances Productivity, Mineral Biofortification and Crude Protein in Rainfed Pearl Millet under Typic Haplustepts: Elucidating the Responses Imposed on an Eight-Year Long-Term Experiment.

Yield limitation and widespread sulphur (S) deficiency in pearl-millet-nurturing dryland soils has emerged as a serious threat to crop productivity and quality. Among diverse pathways to tackle moisture and nutrient stress in rainfed ecologies, conservation agriculture (CA) and foliar nutrition have the greatest potential due to their economic and environmentally friendly nature. Therefore, to understand ammonium thiosulphate (ATS)-mediated foliar S nutrition effects on yield, protein content, mineral biofortification, and sulphur economy of rainfed pearl millet under diverse crop establishment systems, a field study was undertaken. The results highlighted that pearl millet grain and protein yield was significantly higher under no-tillage +3 t/ha crop residue mulching (NTCRM) as compared to no-tillage without mulch (NoTill) and conventional tillage (ConvTill), whereas the stover yield under NTCRM and ConvTill remained at par. Likewise, grain and stover yield in foliar S application using ATS 10 mL/L_twice was 19.5% and 13.2% greater over no S application. The sulphur management strategy of foliar-applied ATS 10 mL/L_twice resulted in significant improvement in grain protein content, protein yield, micronutrient fortification, and net returns (₹ 54.6 × 1000) over the control. Overall, ATS-mediated foliar S nutrition can be an alternate pathway to S management in pearl millet for yield enhancement, micronutrient biofortification and grain protein content increase under ConvTill, as well as under the new NTCRM systems.

Foliar nutrient supplementation with micronutrient-embedded fertilizer increases biofortification, soil biological activity and productivity of eggplant.

Micronutrient malnutrition or hidden hunger remains a major global challenge for human health and wellness. The problem results from soil micro- and macro-nutrient deficiencies combined with imbalanced fertilizer use. Micronutrient-embedded NPK (MNENPK) complex fertilizers have been developed to overcome the macro- and micro-element deficiencies to enhance the yield and nutritive value of key crop products. We investigated the effect of foliar applications of an MNENPK fertilizer containing N, P, K, Fe, Zn and B in combination with traditional basal NPK fertilizers in terms of eggplant yield, fruit nutritive quality and on soil biological properties. Applying a multi-element foliar fertilizer improved the nutritional quality of eggplant fruit, with a significant increases in the concentration of Fe (+ 26%), Zn (+ 34%), K (+ 6%), Cu (+ 24%), and Mn (+ 27%), all of which are essential for human health. Increasing supply of essential micronutrients during the plant reproductive stages increased fruit yield, as a result of improved yield parameters. The positive effect of foliar fertilizing with MNENPK on soil biological parameters (soil microbial biomass carbon, dehydrogenase, alkaline phosphatase) also demonstrated its capacity to enhance soil fertility. This study suggests that foliar fertilizing with a multi-nutrient product such as MNENPK at eggplant flowering and fruiting stages, combined with the recommended-doses of NPK fertilizers is the optimal strategy to improve the nutritional quality of eggplant fruits and increase crop yields, both of which will contribute to reduce micronutrient malnutrition and hunger globally.

Crop and varietal diversification of rainfed rice based cropping systems for higher productivity and profitability in Eastern India.

Rice-rice system and rice fallows are no longer productive in Southeast Asia. Crop and varietal diversification of the rice based cropping systems may improve the productivity and profitability of the systems. Diversification is also a viable option to mitigate the risk of climate change. In Eastern India, farmers cultivate rice during rainy season (June-September) and land leftovers fallow after rice harvest in the post-rainy season (November-May) due to lack of sufficient rainfall or irrigation amenities. However, in lowland areas, sufficient residual soil moistures are available in rice fallow in the post-rainy season (November-March), which can be utilized for raising second crops in the region. Implementation of suitable crop/varietal diversification is thus very much vital to achieve this objective. To assess the yield performance of rice varieties under timely and late sown conditions and to evaluate the performance of dry season crops following them, three different duration rice cultivars were transplanted in July and August. In dry season several non-rice crops were sown in rice fallow to constitute a cropping system. The results revealed that tiller occurrence, biomass accumulation, dry matter remobilization, crop growth rate, and ultimately yield were significantly decreased under late transplanting. On an average, around 30% yield reduction obtained under late sowing may be due to low temperature stress and high rainfall at reproductive stages of the crop. Dry season crops following short duration rice cultivars performed better in terms of grain yield. In the dry season, toria was profitable when sown earlier and if sowing was delayed greengram was suitable. Highest system productivity and profitability under timely sown rice may be due to higher dry matter remobilization from source to sink. A significant correlation was observed between biomass production and grain yield. We infer that late transplanting decrease the tiller occurrence and assimilate remobilization efficiency, which may be responsible for the reduced grain yield.