There is a common tendency in object recognition research to accumulate large volumes of image features to improve performance. However, whether using more information contributes to higher accuracy is still controversial given the increased computational cost. This work investigates the performance of grayscale images compared to RGB counterparts for visual object classification. A comparison between object recognition based on RGB images and RGB images converted to grayscale was conducted using a cascaded CNN-RNN neural network structure, and compared with other types of commonly used classifiers such as Random Forest, SVM and SP-HMP. Experimental results showed that classification with grayscale images resulted in higher accuracy classification than with RGB images across the different types of classifiers. Results also demonstrated that utilizing a small receptive field CNN and edgy feature selection on grayscale images can result in higher classification accuracy with the advantage of reduced computational cost.

Deep neural networks (DNNs) trained on large data sets have been shown to be able to capture high-quality features describing image data. Numerous studies have proposed various ways to transfer DNN structures trained on large data sets to perform classification tasks represented by relatively small data sets. Due to the limitations of these proposals, it is not well known how to effectively adapt the pre-trained model into the new task. Typically, the transfer process uses a combination of fine-tuning and training of adaptation layers; however, both tasks are susceptible to problems with data shortage and high computational complexity. This paper proposes an improvement to the well-known AlexNet feature extraction technique. The proposed approach applies a recursive neural network structure on features extracted by a deep convolutional neural network pre-trained on a large data set. Object recognition experiments conducted on the Washington RGBD image data set have shown that the proposed method has the advantages of structural simplicity combined with the ability to provide higher recognition accuracy at a low computational cost compared with other relevant methods. The new approach requires no training at the feature extraction phase, and can be performed very efficiently as the output features are compact and highly discriminative, and can be used with a simple classifier in object recognition settings.

Background: Motor impairment is a common consequence of stroke causing difficulty in independent movement. The first month of post-stroke rehabilitation is the most effective period for recovery. Movement imagination, known as motor imagery, in combination with virtual reality may provide a way for stroke patients with severe motor disabilities to begin rehabilitation. Methods: The aim of this study is to verify whether motor imagery and virtual reality help to activate stroke patients’ motor cortex. 16 acute/subacute (< 6 months) stroke patients participated in this study. All participants performed motor imagery of basketball shooting which involved the following tasks: listening to audio instruction only, watching a basketball shooting animation in 3D with audio, and also performing motor imagery afterwards. Electroencephalogram (EEG) was recorded for analysis of motor-related features of the brain such as power spectral analysis in the $$\alpha$$α and $$\beta$$β frequency bands and spectral entropy. 18 EEG channels over the motor cortex were used for all stroke patients. Results: All results are normalised relative to all tasks for each participant. The power spectral densities peak near the $$\alpha$$α band for all participants and also the $$\beta$$β band for some participants. Tasks with instructions during motor imagery generally show greater power spectral peaks. The p-values of the Wilcoxon signed-rank test for band power comparison from the 18 EEG channels between different pairs of tasks show a 0.01 significance of rejecting the band powers being the same for most tasks done by stroke subjects. The motor cortex of most stroke patients is more active when virtual reality is involved during motor imagery as indicated by their respective scalp maps of band power and spectral entropy. Conclusion: The resulting activation of stroke patient’s motor cortices in this study reveals evidence that it is induced by imagination of movement and virtual reality supports motor imagery. The framework of the current study also provides an efficient way to investigate motor imagery and virtual reality during post-stroke rehabilitation.

Functional magnetic resonance imaging (fMRI) has emerged as a prevalent tool for investigating motor deficits and rehabilitation in the context of stroke. Particularly, the exploration of functional connectivity (FC) through resting-state fMRI has the potential to unveil the neural connectivity mechanisms underlying post-stroke motor impairment and recovery. Despite the significance of this approach, there exists a gap in the literature where a comprehensive reviewdedicated to post-stroke functional connectivity analysis is lacking. In this paper, we undertake an extensive review of both static functional connectivity network analysis (SFC) and dynamic functional connectivity network analysis (DFC) in the context of post-stroke motor dysfunction. Our primary goal is to present comprehensive methodological insights and the latest research findings pertaining to motor function recovery after stroke. We commence by providing a succinct overviewof SFC and DFC methods, elucidating the preprocessing and denoising techniques essential to these analyses. Subsequently, we summarize the application of two methods in stroke disease, mainly focusing on the extracted insight into post-stroke brain dysfunction and rehabilitation. Our review indicates a prevalence of SFC as the method of choice for post-stroke functional connectivity investigations. Specifically, SFC studies reveal a reduction in FC between motor areas due to stroke lesions, with increased FC correlating positively with functional recovery. Nevertheless, the DFC for post-stroke analysis has only begun to unveil its potential due to its ability in temporal dynamics. In summary, this review paper presents a thorough understanding of post-stroke functional connectivity analysis and its implications for the study of motor function recovery, offering valuable insights for future research and clinical applications.

The brain continually reorganizes its functional network to adapt to post-stroke functional impairments. Previous studies using static modularity analysis have presented global-level behavior patterns of this network reorganization. However, it is far from understood how the brain reconfigures its functional network dynamically following a stroke. This study collected resting-state functional MRI data from 15 stroke patients, with mild (n = 6) and severe (n = 9) two subgroups based on their clinical symptoms. Additionally, 15 age-matched healthy subjects were considered as controls. By applying a multilayer temporal network method, a dynamic modular structure was recognized based on a time-resolved function network. The dynamic network measurements (recruitment, integration, and flexibility) were calculated to characterize the dynamic reconfiguration of post-stroke brain functional networks, hence, revealing the neural functional rebuilding process. It was found from this investigation that severe patients tended to have reduced recruitment and increased between-network integration, while mild patients exhibited low network flexibility and less network integration. It's also noted that previous studies using static methods could not reveal this severity-dependent alteration in network interaction. Clinically, the obtained knowledge of the diverse patterns of dynamic adjustment in brain functional networks observed from the brain neuronal images could help understand the underlying mechanism of the motor, speech, and cognitive functional impairments caused by stroke attacks. The present method not only could be used to evaluate patients' current brain status but also has the potential to provide insights into prognosis analysis and prediction.

While traditional industrial robots participate in repetitive manufacturing processes from behind caged safety enclosures, collaborative robots (cobots) offer a highly flexible and human-interactive solution to manufacturing automation. Rather than operating from within cages, safety features such as force and proximity sensors and programmed protection zones allow cobots to work safely, close to human workers. Cobots can be configured to either stop or slow their motion if they come in contact with a human or obstacle or enter a protection zone, which may be a high pedestrian traffic area. In this way, a task can be divided into sub-processes allocated to the cobot or the human based on suitability, capability or human preference. The flexible nature of the cobot makes it ideal for low-volume, ‘just-in-time’ manufacturing; however, this requires frequent reprogramming of the cobot to adapt to the dynamic processes. This paper reviews relevant cobot programming and control methods currently used in the manufacturing industry and alternative solutions proposed in the literature published from 2018 to 2023. The paper aims to (1) study the features and characteristics of existing cobot programming and control methods and those proposed in the literature, (2) compare the complexity of the task that the cobot is to perform with the skills needed to program it, (3) determine who is the ideal person to perform the programming role, and (4) assess whether the cobot programming and control methods are suited to that person’s skillset or if another solution is needed. The study is presented as a guide for potential adopters of cobots for manufacturing and a reference for further research.