Explore the vast range of titles available.

Dysarthria, a motor speech disorder that impacts articulation and speech clarity, presents significant challenges for Automatic Speech Recognition (ASR) systems. This study proposes a groundbreaking approach to enhance the accuracy of Dysarthric Speech Recognition (DSR). A primary innovation lies in the integration of the SepFormer-Speech Enhancement Generative Adversarial Network (S-SEGAN), an advanced generative adversarial network tailored for Dysarthric Speech Enhancement (DSE), as a front-end processing stage for DSR systems. The S-SEGAN integrates SEGAN’s adversarial learning with SepFormer speech separation capabilities, demonstrating significant improvements in performance. Furthermore, a multistage transfer learning approach is employed to assess the DSR models for both word-level and sentence-level DSR. These DSR models are first trained on a large speech dataset (LibriSpeech) and then fine-tuned on dysarthric speech data (both isolated and augmented). Evaluations demonstrate significant DSR accuracy improvements in DSE integration. The Dysarthric Speech (DS)-baseline models (without DSE), Transformer and Conformer achieved Word Recognition Accuracy (WRA) percentages of 68.60% and 69.87%, respectively. The introduction of Hierarchical Attention Network (HAN) with the Transformer and Conformer architectures resulted in improved performance, with T-HAN achieving a WRA of 71.07% and C-HAN reaching 73%. The Transformer model with DSE + DSR for isolated words achieves a WRA of 73.40%, while that of the Conformer model reaches 74.33%. Notably, the T-HAN and C-HAN models with DSE + DSR demonstrate even more substantial enhancements, with WRAs of 75.73% and 76.87%, respectively. Augmenting words further boosts model performance, with the Transformer and Conformer models achieving WRAs of 76.47% and 79.20%, respectively. Remarkably, the T-HAN and C-HAN models with DSE + DSR and augmented words exhibit WRAs of 82.13% and 84.07%, respectively, with C-HAN displaying the highest performance among all proposed models.

The agricultural sector plays a key role in supplying quality food and makes the greatest contribution to growing economies and populations. Plant disease may cause significant losses in food production and eradicate diversity in species. Early diagnosis of plant diseases using accurate or automatic detection techniques can enhance the quality of food production and minimize economic losses. In recent years, deep learning has brought tremendous improvements in the recognition accuracy of image classification and object detection systems. Hence, in this paper, we utilized convolutional neural network (CNN)-based pre-trained models for efficient plant disease identification. We focused on fine tuning the hyperparameters of popular pre-trained models, such as DenseNet-121, ResNet-50, VGG-16, and Inception V4. The experiments were carried out using the popular PlantVillage dataset, which has 54,305 image samples of different plant disease species in 38 classes. The performance of the model was evaluated through classification accuracy, sensitivity, specificity, and F1 score. A comparative analysis was also performed with similar state-of-the-art studies. The experiments proved that DenseNet-121 achieved 99.81% higher classification accuracy, which was superior to state-of-the-art models.

Word-level sign language recognition (WSLR) is the backbone for continuous sign language recognition (CSLR) that infers glosses from sign videos. Finding the relevant gloss from the sign sequence and detecting explicit boundaries of the glosses from sign videos is a persistent challenge. In this paper, we propose a systematic approach for gloss prediction in WLSR using the Sign2Pose Gloss prediction transformer model. The primary goal of this work is to enhance WLSR’s gloss prediction accuracy with reduced time and computational overhead. The proposed approach uses hand-crafted features rather than automated feature extraction, which is computationally expensive and less accurate. A modified key frame extraction technique is proposed that uses histogram difference and Euclidean distance metrics to select and drop redundant frames. To enhance the model’s generalization ability, pose vector augmentation using perspective transformation along with joint angle rotation is performed. Further, for normalization, we employed YOLOv3 (You Only Look Once) to detect the signing space and track the hand gestures of the signers in the frames. The proposed model experiments on WLASL datasets achieved the top 1% recognition accuracy of 80.9% in WLASL100 and 64.21% in WLASL300. The performance of the proposed model surpasses state-of-the-art approaches. The integration of key frame extraction, augmentation, and pose estimation improved the performance of the proposed gloss prediction model by increasing the model’s precision in locating minor variations in their body posture. We observed that introducing YOLOv3 improved gloss prediction accuracy and helped prevent model overfitting. Overall, the proposed model showed 17% improved performance in the WLASL 100 dataset.

The academic and research communities are showing significant interest in the modern and highly promising technology of wireless mesh networks (WMNs) due to their low-cost deployment, self-configuration, self-organization, robustness, scalability, and reliable service coverage. Multicasting is a broadcast technique in which the communication is started by an individual user and is shared by one or multiple groups of destinations concurrently as one-to-many allotments. The multicasting protocols are focused on building accurate paths with proper channel optimization techniques. The forwarder nodes of the multicast protocol may behave with certain malicious characteristics, such as dropping packets, and delayed transmissions that cause heavy packet loss in the network. This leads to a reduced packet delivery ratio and throughput of the network. Hence, the forwarder node validation is critical for building a secure network. This research paper presents a secure forwarder selection between a sender and the batch of receivers by utilizing the node’s communication behavior. The parameters of the malicious nodes are analyzed using orthogonal projection and statistical methods to distinguish malicious node behaviors from normal node behaviors based on node actions. The protocol then validates the malicious behaviors and subsequently eliminates them from the forwarder selection process using secure path finding strategies, which lead to dynamic and scalable multicast mesh networks for communication.

Group management is practiced to deploy access control and to ease multicast and broadcast communication. However, the devices that constitute the Internet of Things (IoT) are resource-constrained, and the network of IoT is heterogeneous with variable topologies interconnected. Hence, to tackle heterogeneity, SDN-aided centralized group management as a service framework is proposed to provide a global network perspective and administration. Group management as a service includes a group key management function, which can be either centralized or decentralized. Decentralized approaches use complex cryptographic primitives, making centralized techniques the optimal option for the IoT ecosystem. It is also necessary to use a safe, scalable approach that addresses dynamic membership changes with minimal overhead to provide a centralized group key management service. A group key management strategy called a one-way Function Tree (OFT) was put forth to lower communication costs in sizable dynamic groups. The technique, however, is vulnerable to collusion attacks in which an appending and withdrawing device colludes and conspires to obtain unauthorized keys for an unauthorized timeline. Several collusion-deprived improvements to the OFT method are suggested; however, they come at an increased cost for both communication and computation. The Modified One-Way Function Tree (MOFT), a novel technique, is suggested in this proposed work. The collusion resistance of the proposed MOFT system was demonstrated via security analysis. According to performance studies, MOFT lowers communication costs when compared to the original OFT scheme. In comparison to the OFT’s collusion-deprived upgrades, the computation cost is smaller.

Background Uganda faced its sixth reported Ebola outbreak between September 2022 and January 2023, the fifth to be recorded as Sudan Virus Disease (SVD) in the country. In response to this, the Ugandan Ministry of Health (MoH), rapidly deployed a mobile laboratory from the National Health Laboratory and Diagnostics Services (NHLDS) within one week of the declared outbreak. Here we describe the deployment of the mobile laboratory to Mubende, the outbreak epicentre, as part of the national response. This provided (1) efficient diagnostics and characterization of Sudan virus cases to support national data reporting (2), greater insight into Sudan virus kinetics, including viral clearance and risk factor analysis and (3) evaluation of the integration of the mobile laboratory into the national outbreak response. Methods The mobile laboratory was deployed to the Mubende Regional Referral Hospital and positioned next to the established Ebola Treatment Unit (ETU). The laboratory was deployed for 177 days, in continuous operation by a team of 18 trained personnel. Molecular testing, using reverse-transcriptase polymerase chain reaction (RT-PCR) was carried out on all samples received in the laboratory for both Sudan virus diagnosis and differential diagnosis for other viral haemorrhagic fever (VHFs). All results from the mobile laboratory were fed directly into the national database, to enable a coordinated response to the outbreak and analysis of the outbreak data on a national level. Results Nationwide, there were 142 confirmed cases, 55 deaths and 22 probable cases reported in the outbreak. During the mobile laboratory deployment, 3282 samples were tested and 72 SVD cases confirmed by RT-PCR, with an average turn-around-time (TAT) of 6 h. In addition to molecular diagnostic confirmation of suspect cases, the mobile laboratory functioned to support follow-up surveillance of Sudan virus survivors (4 breast feeding mothers and 22 males). Sudan virus RNA was found in the breast milk a median of 135 days after initial test positivity and in the semen of male survivors median 176 days later. We observed the highest risk for contracting the disease in health care workers and a significant correlation between patient viral load at initial diagnosis and patient outcome. Differential diagnosis of other VHFs in the mobile laboratory and at the Uganda Virus Research Institute (UVRI) identified 6 Rift Valley fever (RVF) and 7 Crimean-Congo haemorrhagic fever (CCHF) cases co-circulating in the current SVD outbreak. Conclusion Having the mobile laboratory stationed next to the ETU at the epicentre of the outbreak, markedly reduced diagnostic turn-around-time (TAT) and improved interoperability between the laboratory and the ETU, supporting containment and treatment. Furthermore, integration of the mobile laboratory into existing national outbreak systems, ensured rapid data provision for daily decision making by the national task force. The data from this study contributes to a greater understanding of Sudan virus. Clinical trial number Not applicable.

Background A cholera outbreak started on 29 February in Bwikhonge Sub-county, Bulambuli District in Eastern Uganda. Local public health authorities implemented initial control measures. However, in late March, cases sharply increased in Bwikhonge Sub-county. We investigated the outbreak to determine its scope and mode of transmission, and to inform control measures. Methods We defined a suspected case as sudden onset of watery diarrhea from 1 March 2016 onwards in a resident of Bulambuli District. A confirmed case was a suspected case with positive stool culture for V. cholerae . We conducted descriptive epidemiologic analysis of the cases to inform the hypothesis on mode of transmission. To test the hypothesis, we conducted a case-control study involving 100 suspected case-patients and 100 asymptomatic controls, individually-matched by residence village and age. We collected seven water samples for laboratory testing. Results We identified 108 suspected cases (attack rate: 1.3%, 108/8404), including 7 confirmed cases. The case-control study revealed that 78% (78/100) of case-patients compared with 51% (51/100) of control-persons usually collected drinking water from the nearby Cheptui River (OR MH  = 7.8, 95% CI = 2.7–22); conversely, 35% (35/100) of case-patients compared with 54% (54/100) of control-persons usually collected drinking water from borehole pumps (OR MH  = 0.31, 95% CI = 0.13–0.65). The index case in Bwikhonge Sub-county had onset on 29 February but the outbreak had been on-going in the neighbouring sub-counties in the previous 3 months. V. cholera was isolated in 2 of the 7 river water samples collected from different locations. Conclusions We concluded that this cholera outbreak was caused by drinking contaminated water from Cheptui River. We recommended boiling and/or treating drinking water, improved sanitation, distribution of chlorine tablets to the affected villages, and as a long-term solution, construction of more borehole pumps. After implementing preventive measures, the number of cases declined and completely stopped after 6th April.

Diabetes mellitus is considered one of the main causes of death worldwide. If diabetes fails to be treated and diagnosed earlier, it can cause several other health problems, such as kidney disease, nerve disease, vision problems, and brain issues. Early detection of diabetes reduces healthcare costs and minimizes the chance of serious complications. In this work, we propose an e-diagnostic model for diabetes classification via a machine learning algorithm that can be executed on the Internet of Medical Things (IoMT). The study uses and analyses two benchmarking datasets, the PIMA Indian Diabetes Dataset (PIDD) and the Behavioral Risk Factor Surveillance System (BRFSS) diabetes dataset, to classify diabetes. The proposed model consists of the random oversampling method to balance the range of classes, the interquartile range technique-based outlier detection to eliminate outlier data, and the Boruta algorithm for selecting the optimal features from the datasets. The proposed approach considers ML algorithms such as random forest, gradient boosting models, light gradient boosting classifiers, and decision trees, as they are widely used classification algorithms for diabetes prediction. We evaluated all four ML algorithms via performance indicators such as accuracy, F 1 score, recall, precision, and AUC-ROC. Comparative analysis of this model suggests that the random forest algorithm outperforms all the remaining classifiers, with the greatest accuracy of 92% on the BRFSS diabetes dataset and 94% accuracy on the PIDD dataset, which is greater than the 3% accuracy reported in existing research. This research is helpful for assisting diabetologists in developing accurate treatment regimens for patients who are diabetic.

Background Antimicrobial resistance (AMR) is increasing worldwide, undermining strides in public health and the economy, particularly in low- and middle-income countries. Africa is the continent with the highest death rate attributed to antimicrobial-resistant infections. There is a lack of information on AMR mitigation strategies and their implementation in the region. The aim of this study was to analyze national strategies to tackle AMR with focus on AMR surveillance in the East African Community (EAC) and their implementation status including the analysis of strengths, weaknesses, opportunities, and threats. Methods Within our expert group (composed of representatives from the National Public Health Laboratories (NPHL), Ministries of Health of Burundi, Kenya, Rwanda, South Sudan, Tanzania, and Uganda) we used a qualitative approach to analyze AMR National Action Plans (NAPs), AMR surveillance programs, publications and reports on the AMR situation and strategies in the EAC. Results: We found varying levels of implementation of antimicrobial resistance (AMR) strategies among East African Community (EAC) Partner States. For example, progress in key steps for the sustainable implementation of National Action Plans on AMR (AMR-NAPs) ranged from 7% in Burundi to 94% in Kenya. The overall accomplishment of the WHO checklist for AMR surveillance also varied: 44% in South Sudan, 61% in Burundi, 89% in Rwanda, 94% in Tanzania, and 100% in both Uganda and Kenya. Within EAC Partner States, the detection of bacterial pathogens and their antimicrobial susceptibility profiles is coordinated by national reference laboratories. Most EAC countries have established AMR surveillance systems. However, challenges such as limited laboratory testing capacity, low representativeness of surveillance data, lack of integration among existing systems, and financial constraints undermine efforts to curb AMR. Conclusions Regional collaboration among EAC Partner States is essential for an effective and sustainable response to antimicrobial resistance. Strengthening joint efforts will enable countries to share resources, harmonize surveillance systems, and address common challenges more efficiently. The EAC Regional Network of Reference Laboratories is one example of a regional mechanism that can support such collaboration. The findings of this study will inform the development of a regional AMR strategy focused on laboratory-based surveillance and help guide the prioritization of technical and financial support across the EAC region.