Search

Introduction: Zanthoxylum bungeanum Maxim is an economically significant crop in Asia, but large-scale cultivation is often threatened by frequent diseases, leading to significant yield declines. Deep learning-based methods for crop disease recognition have emerged as a vital research area in agriculture. Methods: This paper presents a novel model, LT-DeepLab, for the semantic segmentation of leaf spot (folium macula), rust, frost damage (gelu damnum), and diseased leaves and trunks in complex field environments. The proposed model enhances DeepLabV3+ with an innovative Fission Depth Separable with CRCC Atrous Spatial Pyramid Pooling module, which reduces the structural parameters of Atrous Spatial Pyramid Pooling module and improves cross-scale extraction capability. Incorporating Criss-Cross Attention with the Convolutional Block Attention Module provides a complementary boost to channel feature extraction. Additionally, deformable convolution enhances low-dimensional features, and a Fully Convolutional Network auxiliary header is integrated to optimize the network and enhance model accuracy without increasing parameter count. Results: LT-DeepLab improves the mean Intersection over Union (mIoU) by 3.59%, the mean Pixel Accuracy (mPA) by 2.16%, and the Overall Accuracy (OA) by 0.94% compared to the baseline DeepLabV3+. It also reduces computational demands by 11.11% and decreases the parameter count by 16.82%. Discussion: These results indicate that LT-DeepLab demonstrates excellent disease segmentation capabilities in complex field environments while maintaining high computational efficiency, offering a promising solution for improving crop disease management efficiency. [ABSTRACT FROM AUTHOR]

IntroductionZanthoxylum bungeanum Maxim is an economically significant crop in Asia, but large-scale cultivation is often threatened by frequent diseases, leading to significant yield declines. Deep learning-based methods for crop disease recognition have emerged as a vital research area in agriculture.MethodsThis paper presents a novel model, LT-DeepLab, for the semantic segmentation of leaf spot (folium macula), rust, frost damage (gelu damnum), and diseased leaves and trunks in complex field environments. The proposed model enhances DeepLabV3+ with an innovative Fission Depth Separable with CRCC Atrous Spatial Pyramid Pooling module, which reduces the structural parameters of Atrous Spatial Pyramid Pooling module and improves cross-scale extraction capability. Incorporating Criss-Cross Attention with the Convolutional Block Attention Module provides a complementary boost to channel feature extraction. Additionally, deformable convolution enhances low-dimensional features, and a Fully Convolutional Network auxiliary header is integrated to optimize the network and enhance model accuracy without increasing parameter count.ResultsLT-DeepLab improves the mean Intersection over Union (mIoU) by 3.59%, the mean Pixel Accuracy (mPA) by 2.16%, and the Overall Accuracy (OA) by 0.94% compared to the baseline DeepLabV3+. It also reduces computational demands by 11.11% and decreases the parameter count by 16.82%.DiscussionThese results indicate that LT-DeepLab demonstrates excellent disease segmentation capabilities in complex field environments while maintaining high computational efficiency, offering a promising solution for improving crop disease management efficiency.

For effective human-robot collaboration, it is crucial for robots to understand requests from users perceiving the three-dimensional space and ask reasonable follow-up questions when there are ambiguities. While comprehending the users’ object descriptions in the requests, existing studies have focused on this challenge for limited object categories that can be detected or localized with existing object detection and localization modules. Further, they have mostly focused on comprehending the object descriptions using flat RGB images without considering the depth dimension. On the other hand, in the wild, it is impossible to limit the object categories that can be encountered during the interaction, and 3-dimensional space perception that includes depth information is fundamental in successful task completion. To understand described objects and resolve ambiguities in the wild, for the first time, we suggest a method leveraging explainability. Our method focuses on the active areas of an RGB scene to find the described objects without putting the previous constraints on object categories and natural language instructions. We further improve our method to identify the described objects considering depth dimension. We evaluate our method in varied real-world images and observe that the regions suggested by our method can help resolve ambiguities. When we compare our method with a state-of-the-art baseline, we show that our method performs better in scenes with ambiguous objects which cannot be recognized by existing object detectors. We also show that using depth features significantly improves performance in scenes where depth data is critical to disambiguate the objects and across our evaluation dataset that contains objects that can be specified with and without the depth dimension.

The development of a vaccine marks a breakthrough in the fight against infectious diseases. However, to eradicate highly infectious diseases globally, the immunization of large parts of the population is needed. Otherwise, diseases, such as polio, measles, or more recently COVID-19, will repeatedly flare-up, with devastating effects on individuals and, in the worst case, on significant shares of the world population. For example, polio has been almost eradicated over the past three decades through an unprecedented global effort, but complete immunization has not yet been achieved. In this article, we use polio as an example to show how the global effort of developing and administering a vaccine can be understood as solving a complex problem since it involves cultural, political, and geographical barriers that demand solutions in dynamically changing and highly versatile environments. Referring to the literature on problem-solving, higher-order thinking, and complex reasoning, we demonstrate how the ability to deal with real-world environments that are complex and dynamically changing, adapting initial solutions to new circumstances and collaborate efficiently with others, has been essential for this endeavor. We argue that problem-solving abilities form one basis for solving consequential world problems. [ABSTRACT FROM AUTHOR]

Laboratory-based gait assessments are indicative of clinical outcomes (e.g., disease identification). Real-world gait may be more sensitive to clinical outcomes, as impairments may be exaggerated in complex environments. This study aims to investigate how different environments (e.g., lab, real world) impact gait. Different walking bout lengths in the real world will be considered proxy measures of context. Data collected in different dementia disease subtypes will be analysed as disease-specific gait impairments are reported between these groups. Thirty-two people with cognitive impairment due to Alzheimer’s disease (AD), 28 due to dementia with Lewy bodies (DLB) and 25 controls were recruited. Participants wore a tri-axial accelerometer for six 10 m walks in lab settings, and continuously for seven days in the real world. Fourteen gait characteristics across five domains were measured (i.e., pace, variability, rhythm, asymmetry, postural control). In the lab, the DLB group showed greater step length variability (p = 0.008) compared to AD. Both subtypes demonstrated significant gait impairments (p < 0.01) compared to controls. In the real world, only very short walking bouts (

People have always tried to understand natural phenomena. In computer science natural phenomena are mostly used as a source of inspiration for solving various problems in distributed systems such as optimization, clustering, and data processing. In this paper we will give an overview of research in field of computer science where fireflies in nature are used as role models for time synchronization. We will compare two models of oscillators that explain firefly synchronization along with other phenomena of synchrony in nature (e.g., synchronization of pacemaker cells of the heart and synchronization of neuron networks of the circadian pacemaker). Afterwards, we will present Mirollo and Strogatz׳s pulse coupled oscillator model together with its limitations. As discussed by the authors of the model, this model lacks of explanation what happens when oscillators are nonidentical. It also does not support mobile and faulty oscillators. Finally, it does not take into consideration that in communication among oscillators there are communication delays. Since these limitations prevent Mirollo and Strogatz׳s model to be used in real-world environments (such as Machine-to-Machine systems), we will sum up related work in which scholars investigated how to modify the model in order for it to be applicable in distributed systems. However, one has to bear in mind that there are usually large differences between mathematical models in theory and their implementation in practice. Therefore, we give an overview of both mathematical models and mechanisms in distributed systems that were designed after them. [ABSTRACT FROM AUTHOR]

An observer’s visual perception of the absolute distance between his or her position and an object is based on multiple sources of information that must be extracted during scene viewing. Research has not yet discovered the viewing duration observers need to fully extract distance information, particularly in navigable real-world environments. In a visually directed walking task, participants showed a sensitive response to distance when they were given 9-ms glimpses of floor- and eye-level targets. However, sensitivity to distance decreased markedly when targets were presented at eye level and angular size was rendered uninformative. Performance after brief viewing durations was characterized by underestimation of distance, unless the brief-viewing trials were preceded by a block of extended-viewing trials. The results indicate that experience plays a role in the extraction of information during brief glimpses. Even without prior experience, the extraction of useful information is virtually immediate when the cues of angular size or angular declination are informative for the observer. [ABSTRACT FROM PUBLISHER]

Animals have to accomplish several tasks in their lifetime, such as finding food and mates and avoiding predators. Animals that locate these using sound need to detect, recognize and localize appropriate acoustic objects in their environment, typically in noisy, non-ideal conditions. Quantitative models attempting to explain or predict animal behaviour should be able to accurately simulate behaviour in such complex, real-world conditions. Female crickets locate potential mates in choruses of simultaneously calling males. In the present study, we have tested field cricket acoustic orientation behaviour in complex acoustic conditions in the field and also successfully predicted female orientation and paths under these conditions using a simulation model based on auditory physiology. Such simulation models can provide powerful tools to predict and dissect patterns of behaviour in complex, natural environments. [ABSTRACT FROM AUTHOR]

Laboratory-based gait assessments are indicative of clinical outcomes (e.g., disease identification). Real-world gait may be more sensitive to clinical outcomes, as impairments may be exaggerated in complex environments. This study aims to investigate how different environments (e.g., lab, real world) impact gait. Different walking bout lengths in the real world will be considered proxy measures of context. Data collected in different dementia disease subtypes will be analysed as disease-specific gait impairments are reported between these groups. Thirty-two people with cognitive impairment due to Alzheimer's disease (AD), 28 due to dementia with Lewy bodies (DLB) and 25 controls were recruited. Participants wore a tri-axial accelerometer for six 10 m walks in lab settings, and continuously for seven days in the real world. Fourteen gait characteristics across five domains were measured (i.e., pace, variability, rhythm, asymmetry, postural control). In the lab, the DLB group showed greater step length variability (p = 0.008) compared to AD. Both subtypes demonstrated significant gait impairments (p < 0.01) compared to controls. In the real world, only very short walking bouts (<10 s) demonstrated different gait impairments between subtypes. The context where walking occurs impacts signatures of gait impairment in dementia subtypes. To develop real-world gait assessment as a clinical tool, algorithms and metrics must accommodate for changes in context. [ABSTRACT FROM AUTHOR]