Diagnosis of Alternaria disease and leafminer pest on tomato leaves using image processing techniques

Expansion of the multi-locus gene alignment approach to improve identification of the fungal species Alternaria alternata

Alternaria alternata is part of a genus comprised of over 600 different species that occur all over the world and cause damage to humans, plants and thereby to the economy. Yet, even though some species are causing tremendous issues, the past years have shown that assigning newly found isolates to known species was rather inconsistent. Most identifications are usually done on the basis of spore morphology, chemotype and molecular markers. In this work we used strains isolated from the wild as well as commercial strains of the DSMZ (German collection of microorganisms and cell cultures) as a reference, to show, that the variation within the Alternaria alternata species is comparable to the variation between different species of the genus Alternaria in regards to spore morphology and chemotype. We compared the different methods of identification and discerned the concatenation of multiple molecular markers as the deciding factor for better identification. Up until this point, usually a concatenation of two or three traditional molecular markers was used. Some of those markers being stronger some weaker. We show that the concatenation of five molecular markers improves the likeliness of a correct assignment, thus a better distinction between the different Alternaria species.

Deep Learning Technology to Recognize American Sign Language Alphabet

Historically, individuals with hearing impairments have faced neglect, lacking the necessary tools to facilitate effective communication. However, advancements in modern technology have paved the way for the development of various tools and software aimed at improving the quality of life for hearing-disabled individuals. This research paper presents a comprehensive study employing five distinct deep learning models to recognize hand gestures for the American Sign Language (ASL) alphabet. The primary objective of this study was to leverage contemporary technology to bridge the communication gap between hearing-impaired individuals and individuals with no hearing impairment. The models utilized in this research include AlexNet, ConvNeXt, EfficientNet, ResNet-50, and VisionTransformer were trained and tested using an extensive dataset comprising over 87,000 images of the ASL alphabet hand gestures. Numerous experiments were conducted, involving modifications to the architectural design parameters of the models to obtain maximum recognition accuracy. The experimental results of our study revealed that ResNet-50 achieved an exceptional accuracy rate of 99.98%, the highest among all models. EfficientNet attained an accuracy rate of 99.95%, ConvNeXt achieved 99.51% accuracy, AlexNet attained 99.50% accuracy, while VisionTransformer yielded the lowest accuracy of 88.59%.

Systematic review of passenger demand forecasting in aviation industry

Forecasting aviation demand is a significant challenge in the airline industry. The design of commercial aviation networks heavily relies on reliable travel demand predictions. It enables the aviation industry to plan ahead of time, evaluate whether an existing strategy needs to be revised, and prepare for new demands and challenges. This study examines recently published aviation demand studies and evaluates them in terms of the various forecasting techniques used, as well as the advantages and disadvantages of each. This study investigates numerous forecasting techniques for passenger demand, emphasizing the multiple factors that influence aviation demand. It examined the benefits and drawbacks of various models ranging from econometric to statistical, machine learning to deep neural networks, and the most recent hybrid models. This paper discusses multiple application areas where passenger demand forecasting is used effectively. In addition to the benefits, the challenges and potential future scope of passenger demand forecasting were discussed. This study will be helpful to future aviation researchers while also inspiring young researchers to pursue careers in this industry.

A bidirectional multilayer contrastive adaptation network with anatomical structure preservation for unpaired cross-modality medical image segmentation

Multi-modal medical image segmentation has achieved great success through supervised deep learning networks. However, because of domain shift and limited annotation information, unpaired cross-modality segmentation tasks are still challenging. The unsupervised domain adaptation (UDA) methods can alleviate the segmentation degradation of cross-modality segmentation by knowledge transfer between different domains, but current methods still suffer from the problems of model collapse, adversarial training instability, and mismatch of anatomical structures. To tackle these issues, we propose a bidirectional multilayer contrastive adaptation network (BMCAN) for unpaired cross-modality segmentation. The shared encoder is first adopted for learning modality-invariant encoding representations in image synthesis and segmentation simultaneously. Secondly, to retain the anatomical structure consistency in cross-modality image synthesis, we present a structure-constrained cross-modality image translation approach for image alignment. Thirdly, we construct a bidirectional multilayer contrastive learning approach to preserve the anatomical structures and enhance encoding representations, which utilizes two groups of domain-specific multilayer perceptron (MLP) networks to learn modality-specific features. Finally, a semantic information adversarial learning approach is designed to learn structural similarities of semantic outputs for output space alignment. Our proposed method was tested on three different cross-modality segmentation tasks: brain tissue, brain tumor, and cardiac substructure segmentation. Compared with other UDA methods, experimental results show that our proposed BMCAN achieves state-of-the-art segmentation performance on the above three tasks, and it has fewer training components and better feature representations for overcoming overfitting and domain shift problems. Our proposed method can efficiently reduce the annotation burden of radiologists in cross-modality image analysis.