Global rice production systems face two opposing challenges: the need to increase production to accommodate the world's growing population while simultaneously reducing greenhouse gas (GHG) ...emissions. Adaptations to drainage regimes are one of the most promising options for methane mitigation in rice production. Whereas several studies have focused on mid-season drainage (MD) to mitigate GHG emissions, early-season drainage (ED) varying in timing and duration has not been extensively studied. However, such ED periods could potentially be very effective since initial available C levels (and thereby the potential for methanogenesis) can be very high in paddy systems with rice straw incorporation. This study tested the effectiveness of seven drainage regimes varying in their timing and duration (combinations of ED and MD) to mitigate CH4 and N2O emissions in a 101-day growth chamber experiment. Emissions were considerably reduced by early-season drainage compared to both conventional continuous flooding (CF) and the MD drainage regime. The results suggest that ED+MD drainage may have the potential to reduce CH4 emissions and yield-scaled GWP by 85–90% compared to CF and by 75–77% compared to MD only. A combination of (short or long) ED drainage and one MD drainage episode was found to be the most effective in mitigating CH4 emissions without negatively affecting yield. In particular, compared with CF, the long early-season drainage treatments LE+SM and LE+LM significantly (p<0.01) decreased yield-scaled GWP by 85% and 87% respectively. This was associated with carbon being stabilised early in the season, thereby reducing available C for methanogenesis. Overall N2O emissions were small and not significantly affected by ED. It is concluded that ED+MD drainage might be an effective low-tech option for small-scale farmers to reduce GHG emissions and save water while maintaining yield.
Display omitted
•The effects of timing and duration of drainage in rice soils amended with residue were studied.•Early-season drainage (ED) in combination with midseason drainage reduced CH4 emission up to 90%.•Yield-scaled GWPs were reduced up to 87% compared to conventional continuous flooding.•ED results in stabilisation of carbon early in the season, restricting potential for methanogenesis.•ED is an effective option for small-scale farmers to reduce emissions, water use while maintaining yield.
•e-AWD water regime reduced seasonal CH4 emissions up to 85 %.•DOC was reduced up to 47 % which was linked to the reduction of CH4 emissions.•Grain As, Pb and Cd levels were reduced up to 65, 72 and ...33 % respectively.•Root biomass and length increased up to 72 %, which was linked to the yield increase.•Yield-scaled GWPs were reduced up to 84 % compared to conventional CF practice.
Flooded rice production is crucial to global food security, but there are associated environmental concerns. In particular, it is a significant source of methane (CH4) and nitrous oxide (N2O) emissions and a large consumer of water resources, while arsenic levels in the grain are a serious health concern. There is also a tendency to use more organic fertilisers to close nutrient cycles, posing a threat of even higher GHG emissions and grain arsenic levels. It has been shown that alternate wetting and drying (AWD) water management reduces both water use and GHG emissions, but success at maintaining yields varies. This study tested the effect of early AWD (e-AWD) versus continuous flooding (CF) water management practices on grain yields, GHG emissions and grain arsenic levels in a split-plot field experiment with organic fertilisers under organic management. The treatments included: i) farmyard manure, ii) compost, and iii) biogas digestate, alone or in combination with mineral fertiliser. The e-AWD water regime showed no difference in yield for the organic treatments. Yields significantly increased by 5–16 % in the combination treatments. Root biomass and length increased in the e-AWD treatments up to 72 and 41 %, respectively. The e-AWD water regime reduced seasonal CH4 emissions by 71–85 % for organic treatments and by 51–76 % for combination treatments; this was linked to a 15–47 % reduction in dissolved organic carbon (DOC), thereby reducing methanogenesis. N2O emissions increased by 23–305 % but accounted for <20 % of global warming potential (GWP). Area and yield-scaled GWPs were reduced by 67–83 %. The e–AWD regime altered soil redox potentials, resulting in a reduction in grain arsenic and lead concentrations of up to 66 % and 73 % respectively. Grain cadmium levels were also reduced up to 33 % in organic treatments. Structural equation modelling showed that DOC, redox, ammonium and root biomass were the key traits that regulated emissions and maintained yield. Despite the fact that the experiment was conducted in the dry-season when soil moisture conditions can be relatively well-controlled, our findings should be confirmed in multi-year studies in farmers’ fields. These results suggest that in flooded rice systems receiving organic amendments or organic management, the e-AWD water regime can achieve multiple environmental and food safety objectives without compromising yield.
Clinical notes are documents that contain detailed information about the health status of patients. Medical codes generally accompany them. However, the manual diagnosis is costly and error-prone. ...Moreover, large datasets in clinical diagnosis are susceptible to noise labels because of erroneous manual annotation. Therefore, machine learning has been utilized to perform automatic diagnoses. Previous state-of-the-art (SOTA) models used convolutional neural networks to build document representations for predicting medical codes. However, the clinical notes are usually long-tailed. Moreover, most models fail to deal with the noise during code allocation. Therefore, denoising mechanism and long-tailed classification are the keys to automated coding at scale.
In this paper, a new joint learning model is proposed to extend our attention model for predicting medical codes from clinical notes. On the MIMIC-III-50 dataset, our model outperforms all the baselines and SOTA models in all quantitative metrics. On the MIMIC-III-full dataset, our model outperforms in the macro-F1, micro-F1, macro-AUC, and precision at eight compared to the most advanced models. In addition, after introducing the denoising mechanism, the convergence speed of the model becomes faster, and the loss of the model is reduced overall.
The innovations of our model are threefold: firstly, the code-specific representation can be identified by adopted the self-attention mechanism and the label attention mechanism. Secondly, the performance of the long-tailed distributions can be boosted by introducing the joint learning mechanism. Thirdly, the denoising mechanism is suitable for reducing the noise effects in medical code prediction. Finally, we evaluate the effectiveness of our model on the widely-used MIMIC-III datasets and achieve new SOTA results.
This paper presents the performance comparison of a dual-band conventional antenna with a split-ring resonator (SRR)- and electromagnetic bandgap (EBG)-based dual-band design operating at 2.4 GHz and ...5.4 GHz. The compactness and dual-frequency operation in the legacy Wi-Fi range of this design make it highly favorable for wearable sensor network-based Internet of Things (IoT) applications. Considering the current need for wearable antennas, wash cotton (with a relative permittivity of 1.51) is used as a substrate material for both conventional and metamaterial-based antennas. The radiation characteristics of the conventional antenna are compared with the EBG and SRR ground planes-based antennas in terms of return loss, gain, and efficiency. It is found that the SRR-based antenna is more efficient in terms of gain and surface wave suppression as well as more compact in comparison with its two counterparts. The compared results are found to be based on two distinct frequency ranges, namely, 2.4 GHz and 5.4 GHz. The suggested SRR-based antenna exhibits improved performance at 5.4 GHz, with gains of 7.39 dbi, bandwidths of 374 MHz, total efficiencies of 64.7%, and HPBWs of 43.2 degrees. The measurements made in bent condition are 6.22 db, 313 MHz, 52.45%, and 22.3 degrees, respectively. The three considered antennas (conventional, EBG-based, and SRR-based) are designed with a compact size to be well-suited for biomedical sensors, and specific absorption rate (SAR) analysis is performed to ensure user safety. In addition, the performance of the proposed antenna under bending conditions is also considered to present a realistic approach for a practical antenna design.
S-box plays an imperative role in designing a cryptographically strong block cipher. Designing S-box based on chaos has attracted lots of attentions because of its distinct characteristics relevant ...to cryptography. In this paper, a 4D-4wing hyperchaotic system is investigated. Its sophisticated nonlinear behaviors are used to generate two pseudorandom 8-bit integer sequences, which further drive iterative two-position swap on the identical map on GF(2
8
). According to the indicator of typical evaluation criteria including nonlinearity, differential uniformity, strict avalanche criterion, output bits independence criterion and bijective property, the preferred S-box is obtained from all those batch-generated ones. The comparison with the state-of-the-art chaos-based schemes shows that the obtained S-box achieves better cryptographical performance.
The ability to identify human actions in uncontrolled environments is essential for human–computer interaction, especially in sports, to provide athletes, coaches, and analysts, important information ...about movement techniques and aid in making well-informed decisions regarding player’s movements. Recognizing player’s actions, particularly in the context of basketball sports remains a challenging task due to issues like complex backgrounds, obstructed actions, and inconsistent lighting conditions. Artificial Intelligence and deep learning has promising applications in basketball movement analysis, as it can help basketball athletes enhance their shooting techniques and accuracy, thereby improving the efficiency of both games and training sessions. However, the traditional deep learning-based feature extraction methods lack robustness due to simple architecture and low efficiency. In this study, a hybrid Yolo-T2FLSTM system is proposed for basketball player’s detection and action recognition. An enhanced Yolo algorithm is employed for detecting players in the frame and the integration of LSTM and fuzzy logic is used to perform the final basketball action classification. The models of VGG 16, VGG 19 and ResNet50 are combined in the backbone of Yolo for multi-feature extraction to establish a multi-feature fusion approach and enhance the performance of basketball player and action recognition. The proposed model is evaluated on different basketball videos and achieved a high recognition rate for player detection and 99.3% accuracy for eight basketball actions. Comparative experiments are carried out under various conditions to validate the robustness of the hybrid Yolo-T2FLSTM model. Results show that the proposed method has a high player detection and action recognition rate as compared to other feature extraction models.
The evergrowing diversity of encrypted and anonymous network traffic makes network management more formidable to manage the network traffic. An intelligent system is essential to analyse and identify ...network traffic accurately. Network management needs such techniques to improve the Quality of Service and ensure the flow of secure network traffic. However, due to the usage of non‐standard ports and encryption of data payloads, the classical port‐based and payload‐based classification techniques fail to classify the secured network traffic. To solve the above‐mentioned problems, this paper proposed an effective deep learning‐based framework employed with flow‐time‐based features to predict heterogeneous secure network traffic best. The state‐of‐the‐art machine learning strategies (C4.5, random forest, and K‐nearest neighbour) are investigated for comparison. The proposed 1D‐CNN model achieved higher accuracy in classifying the heterogeneous secure network traffic. In the next step, the proposed deep learning model characterises the major categories (virtual private network traffic, the onion router network traffic, and plain encrypted network traffic) into several application types. The experimental results show the effectiveness and feasibility of the proposed deep learning framework, which yields improved predictive power compared to the state‐of‐the‐art machine learning techniques employed for secure network traffic analysis.
This paper provides a lightweight 1D‐CNN model to distinguish different types of network traffic flows passing through a secure network. More specifically, it identifies and further characterizes the application type in complex network flows.
Network management is facing a great challenge to analyze and identify encrypted network traffic with specific applications and protocols. A significant number of network users applying different ...encryption techniques to network applications and services to hide the true nature of the network communication. These challenges attract the network community to improve network security and enhance network service quality. Network managers need novel techniques to cope with the failure and shortcomings of the port-based and payload-based classification methods of encrypted network traffic due to emergent security technologies. Mainly, the famous network hopping mechanisms used to make network traffic unknown and anonymous are VPN (virtual private network) and TOR (Onion Router). This paper presents a novel scheme to unveil encrypted network traffic and easily identify the tunneled and anonymous network traffic. The proposed identification scheme uses the highly desirable deep learning techniques to easily and efficiently identify the anonymous network traffic and extract the Voice over IP (VoIP) and Non VoIP ones within encrypted traffic flows. Finally, the captured traffic has been classified into four different categories, i-e., VPN VoIP, VPN Non-VoIP, TOR VoIP, and TOR Non-VoIP. The experimental results show that our identification engine is extremely robust to VPN and TOR network traffic.
The gut microbiota has the capacity to de-novo manufacture or change endogenous and exogenous substances to produce or alter xenometabolites (i.e., non-host-derived metabolites). A wide-scale ...characterization of these metabolites is still lacking, despite rare instances of xenometabolites impacting host health and illness. Numerous studies have been conducted to investigate how the gut microbiome affects individual function and health, including links between specific intestinal microorganism populations and metabolites and the health of the systemic-immune system and gastrointestinal tract. The current review article delves into the sources of xenometabolites and the role of modeling in addressing the complexity of the xenometabolites process, as well as various nutraceutical benefits such as antibiotics, anti-tumor, and anti-cancer action.