YOLOv8-CML: a lightweight target detection method for color-changing melon ripening in intelligent agriculture.

Color-changing melon is an ornamental and edible fruit. Aiming at the problems of slow detection speed and high deployment cost for Color-changing melon in intelligent agriculture equipment, this study proposes a lightweight detection model YOLOv8-CML.Firstly, a lightweight Faster-Block is introduced to reduce the number of memory accesses while reducing redundant computation, and a lighter C2f structure is obtained. Then, the lightweight C2f module fusing EMA module is constructed in Backbone to collect multi-scale spatial information more efficiently and reduce the interference of complex background on the recognition effect. Next, the idea of shared parameters is utilized to redesign the detection head to simplify the model further. Finally, the α-IoU loss function is adopted better to measure the overlap between the predicted and real frames using the α hyperparameter, improving the recognition accuracy. The experimental results show that compared to the YOLOv8n model, the parametric and computational ratios of the improved YOLOv8-CML model decreased by 42.9% and 51.8%, respectively. In addition, the model size is only 3.7 MB, and the inference speed is improved by 6.9%, while mAP@0.5, accuracy, and FPS are also improved. Our proposed model provides a vital reference for deploying Color-changing melon picking robots.

OPG gene-modified adipose-derived stem cells improve bone formation around implants in osteoporotic rat maxillae.

Background: Osteoporosis is a significant barrier to the use of dental implants in the elderly for the treatment of tooth defects. Adipose derived stem cells (ADSCs) have demonstrated extensive potential for tissue repair and regeneration. The present study aimed to investigate the effectiveness of ADSCs engineered to express high levels of osteoprotegerin (OPG) for the treatment of bone loss in implant dentistry caused by estrogen deficiency. Methods: A rat model of osteoporosis was established through double oophorectomy, and the rats were treated by gene modified cells Adv-OPG-ADSCs. The effects of the treatment on maxilla tissue changes were evaluated using HE staining and micro-CT. Additionally, ALP and TRAP staining were used to assess osteoblast and osteoclast alterations. Finally, the changes in related osteoblast and osteoclast indicators were measured by RT-qPCR, Western blot, and ELISA. Results: The successfully generated high-OPG-expressing ADSCs led to increase of cell viability, proliferation, and osteoblast differentiation. Treatment with Adv-OPG-ADSCs significantly ameliorated maxillary morphology, trabecular volume reduction, and bone mineral density decline in the model of estrogen-deficient maxillary implant dentistry. Furthermore, the treatment was beneficial to promoting the generation of osteoblasts and inhibiting the generation of osteoclast. Adv-OPG-ADSCs increased OPG, ALP, OCN, and Runx-2 expressions in the maxilla while suppressing RANKL expression, and also increased the concentration of COL I and PINP, as well as decreased the concentration of CTX-1. Conclusion: Adv-OPG-ADSCs promote the formation of osteoblasts and inhibit the generation of osteoclasts, thereby inhibiting bone absorption, facilitating bone formation, and promoting the repair of maxillary bone after dental implantation in the presence of osteoporosis-related complications, especially in the setting of estrogen deficiency, providing scientific basis for the application of Adv-OPG-ADSCs in the treatment of implant related osteoporosis.

A Model for Infrastructure Detection along Highways Based on Remote Sensing Images from UAVs.

Infrastructure along the highway refers to various facilities and equipment: bridges, culverts, traffic signs, guardrails, etc. New technologies such as artificial intelligence, big data, and the Internet of Things are driving the digital transformation of highway infrastructure towards the future goal of intelligent roads. Drones have emerged as a promising application area of intelligent technology in this field. They can help achieve fast and precise detection, classification, and localization of infrastructure along highways, which can significantly enhance efficiency and ease the burden on road management staff. As the infrastructure along the road is exposed to the outdoors for a long time, it is easily damaged and obscured by objects such as sand and rocks; on the other hand, based on the high resolution of the images taken by Unmanned Aerial Vehicles (UAVs), the variable shooting angles, complex backgrounds, and high percentage of small targets mean the direct use of existing target detection models cannot meet the requirements of practical applications in industry. In addition, there is a lack of large and comprehensive image datasets of infrastructure along highways from UAVs. Based on this, a multi-classification infrastructure detection model combining multi-scale feature fusion and an attention mechanism is proposed. In this paper, the backbone network of the CenterNet model is replaced with ResNet50, and the improved feature fusion part enables the model to generate fine-grained features to improve the detection of small targets; furthermore, the attention mechanism is added to make the network focus more on valuable regions with higher attention weights. As there is no publicly available dataset of infrastructure along highways captured by UAVs, we filter and manually annotate the laboratory-captured highway dataset to generate a highway infrastructure dataset. The experimental results show that the model has a mean Average Precision (mAP) of 86.7%, an improvement of 3.1 percentage points over the baseline model, and the new model performs significantly better than other detection models overall.

Detection and Recognition Algorithm of Arbitrary-Oriented Oil Replenishment Target in Remote Sensing Image.

In view of the fact that the aerial images of UAVs are usually taken from a top-down perspective, there are large changes in spatial resolution and small targets to be detected, and the detection method of natural scenes is not effective in detecting under the arbitrary arrangement of remote sensing image direction, which is difficult to apply to the detection demand scenario of road technology status assessment, this paper proposes a lightweight network architecture algorithm based on MobileNetv3-YOLOv5s (MR-YOLO). First, the MobileNetv3 structure is introduced to replace part of the backbone network of YOLOv5s for feature extraction so as to reduce the network model size and computation and improve the detection speed of the target; meanwhile, the CSPNet cross-stage local network is introduced to ensure the accuracy while reducing the computation. The focal loss function is improved to improve the localization accuracy while increasing the speed of the bounding box regression. Finally, by improving the YOLOv5 target detection network from the prior frame design and the bounding box regression formula, the rotation angle method is added to make it suitable for the detection demand scenario of road technology status assessment. After a large number of algorithm comparisons and data ablation experiments, the feasibility of the algorithm was verified on the Xinjiang Altay highway dataset, and the accuracy of the MR-YOLO algorithm was as high as 91.1%, the average accuracy was as high as 92.4%, and the detection speed reached 96.8 FPS. Compared with YOLOv5s, the p-value and mAP values of the proposed algorithm were effectively improved. It can be seen that the proposed algorithm improves the detection accuracy and detection speed while greatly reducing the number of model parameters and computation.

R-YOLO: A YOLO-Based Method for Arbitrary-Oriented Target Detection in High-Resolution Remote Sensing Images.

In view of the existence of remote sensing images with large variations in spatial resolution, small and dense objects, and the inability to determine the direction of motion, all these components make object detection from remote sensing images very challenging. In this paper, we propose a single-stage detection network based on YOLOv5. This method introduces the MS Transformer module at the end of the feature extraction network of the original network to enhance the feature extraction capability of the network model and integrates the Convolutional Block Attention Model (CBAM) to find the attention area in dense scenes. In addition, the YOLOv5 target detection network is improved by incorporating a rotation angle approach from the a priori frame design and the bounding box regression formulation to make it suitable for rotating frame-based detection scenarios. Finally, the weighted combination of the two difficult sample mining methods is used to improve the focal loss function, so as to improve the detection accuracy. The average accuracy of the test results of the improved algorithm on the DOTA data set is 77.01%, which is higher than the previous detection algorithm. Compared with the average detection accuracy of YOLOv5, the average detection accuracy is improved by 8.83%. The experimental results show that the algorithm has higher detection accuracy than other algorithms in remote sensing scenes.

CGR-Block: Correlated Feature Extractor and Geometric Feature Fusion for Point Cloud Analysis.

Point cloud processing based on deep learning is developing rapidly. However, previous networks failed to simultaneously extract inter-feature interaction and geometric information. In this paper, we propose a novel point cloud analysis module, CGR-block, which mainly uses two units to learn point cloud features: correlated feature extractor and geometric feature fusion. CGR-block provides an efficient method for extracting geometric pattern tokens and deep information interaction of point features on disordered 3D point clouds. In addition, we also introduce a residual mapping branch inside each CGR-block module for the further improvement of the network performance. We construct our classification and segmentation network with CGR-block as the basic module to extract features hierarchically from the original point cloud. The overall accuracy of our network on the ModelNet40 and ScanObjectNN benchmarks achieves 94.1% and 83.5%, respectively, and the instance mIoU on the ShapeNet-Part benchmark also achieves 85.5%, proving the superiority of our method.

Topographical organization of mammillary neurogenesis and efferent projections in the mouse brain.

The mammillary body is a hypothalamic nucleus that has important functions in memory and spatial navigation, but its developmental principles remain not well understood. Here, we identify progenitor-specific Fezf2 expression in the developing mammillary body and develop an intersectional fate-mapping approach to demonstrate that Fezf2+ mammillary progenitors generate mammillary neurons in a rostral-dorsal-lateral to caudal-ventral-medial fashion. Axonal tracing from different temporal cohorts of labeled mammillary neurons reveal their topographical organization. Unsupervised hierarchical clustering based on intrinsic properties further identify two distinct neuronal clusters independent of birthdates in the medial nuclei. In addition, we generate Fezf2 knockout mice and observe the smaller mammillary body with largely normal anatomy and mildly affected cellular electrophysiology, in contrast to more severe deficits in neuronal differentiation and projection in many other brain regions. These results indicate that Fezf2 may function differently in the mammillary body. Our results provide important insights for mammillary development and connectivity.

piR-823 demonstrates tumor oncogenic activity in esophageal squamous cell carcinoma through DNA methylation induction via DNA methyltransferase 3B.

Piwi-interacting RNAs (piRNAs) dysregulation occurs frequently in extensive cancers. However, there was no report about piRNA expression in esophageal cancer (EC). In this study, the expression levels of piR-823 and DNMT1, DNMT3A, DNMT3B were detected in 54 pairs of ESCC tissues and adjacent normal tissues using the quantitative real-time polymerase chain reaction method. Pearson's chi-squared test and receiver operating characteristic curves were established to evaluate the diagnostic and prognostic value of piR-823 in ESCC. Spearman's correlation analysis was used to evaluate the association between piR-823 and DNMTs. We found that piR-823 was significantly upregulated in ESCC tissues compared with matched normal tissues (P = 0.0213), the level of piR-823 was significantly associated with lymph node metastasis (P = 0.042). The ROC curve analysis of piR-823 expression level yielded an area under the ROC curve value of 0.713 (P = 0.0001). DNMT3B was upregulated in ESCC tissues compared with matched normal tissues (P = 0.0286). There was an obvious positive correlation between piR-823 and DNMT3B expression (r = 0.6420, P < 0.0001). In conclusion, for the first time, we provided evidence about piRNA expression in EC. piRNA-823 and DNMT3B were both upregulated in ESCC and positively correlated with each other, suggesting the tumor oncogenic role of piR-823 in ESCC to epigenetically induce aberrant DNA methylation through DNMT3B. In addition, piRNA-823 showed high specificity in detecting ESCC and higher piRNA-823 level indicated higher risk of lymph node metastasis, suggesting its diagnostic and prognostic biomarker potential.

Association between polymorphisms in the CYP1A1, CYP2E1 and GSTM1 genes, and smoking, alcohol and upper digestive tract carcinomas in a high-incidence area of northern China.

Metabolic gene variants, smoking, and alcohol consumption are important upper digestive tract cancer (UDTC) risk factors. However, the gene-gene and gene-environment interactions remain unclear. A case-control study in a high incidence area for upper digestive tract cancer was conducted in China. DNA was extracted from buffy coat samples for PCR or PCR-restriction fragment length polymorphism. Smoking and alcohol drinking status was determined by questionnaires. Odds ratios (ORs) and 95% confidence intervals (CIs) were used to assess the associations. After adjusting for confounding factors, smoking increased esophageal cancer (EC), gastric cardia cancer (GCC) and gastric antral carcinoma (GAC) risk by 3.594, 4.658, and 3.999-fold, respectively. Alcohol consumption increased EC, GCC and GAC risk by 1.953, 2.442 and 1.765-fold, respectively. The cytochrome P4501A1 (CYP1A1) rs4646903 T>C polymorphism increased GCC risk, the cytochrome P4502E1 (CYP2E1) rs2031920 C>T polymorphism increased EC risk, while the GSTM1 null genotype decreased EC risk. An association existed between the following: CYP1A1 rs4646903 and smoking in EC, GCC and GAC; CYP1A1 rs4646903 and alcohol consumption in EC and GCC; CYP2E1 rs2031920 and smoking in EC, GCC and GAC and CYP2E1 rs2031920 and alcohol consumption in EC and GCC. No association was observed between CYP1A1 and CYP2E1. The glutathione S-transferase mu 1 (GSTM1) null genotype decreased EC risk (OR=0.510). Smoking/drinking are upper digestive tract cancer risk factors. The CYP1A1 rs4646903 and CYP2E1 rs2031920 polymorphisms were risk factors of GCC or EC, and the GSTM1 null genotype may serve a protective role against EC. The results of the present study indicated that gene-environment interactions increase the risk of UDTC.

[Research on electroencephalogram emotion recognition based on the feature fusion algorithm of auto regressive model and wavelet packet entropy].

Focused on the world-wide issue of improving the accuracy of emotion recognition, this paper proposes an electroencephalogram (EEG) signal feature extraction algorithm based on wavelet packet energy entropy and auto-regressive (AR) model. The auto-regressive process can be approached to EEG signal as much as possible, and provide a wealth of spectral information with few parameters. The wavelet packet entropy reflects the spectral energy distribution of the signal in each frequency band. Combination of them gives a better reflect of the energy characteristics of EEG signals. Feature extraction and fusion are implemented based on kernel principal component analysis. Six emotional states from a public multimodal database for emotion analysis using physiological signals (DEAP) are recognized. The results show that the recognition accuracy of the proposed algorithm is more than 90%, and the highest recognition accuracy is 99.33%. It indicates that this algorithm can extract the feature of EEG emotion well, and it is a kind of effective emotion feature extraction algorithm, providing support to emotion recognition.

[Research on analysis method of multi-fractal de-trended fluctuation of electroencephalogram focus on mental stress evaluation].

The multi-fractal de-trended fluctuation analysis was used to estimate the mental stress in the present study. In order to obtain the optimal fractal order of the multi-fractal de-trended fluctuation analysis, we analyzed the relationship between singular index and Hurst index with order. We recorded the electroencephalogram (EEG) of 14 students, compared the relationship between singular index, Hurst index and quality index, ensured the optimal order being [-5, 5] and achieved the estimation of mental stress with the ß wave in the EEGs. The result indicated that Hurst index and quality index of the EEGs under mental stress were greater than those of EEGs in the relaxing state. The Hurst index was gradually decreasing with the order increasing and was finally approaching a constant, while the quality index was amplified and variation of amplitude of the singular index was more obvious. We also compared the amplitude and the width of singular spectrum of the EEGs under the two conditions, and results indicated that the characteristics of multi-fractal spectrum of the EEGs under different conditions were different, namely the width of singular spectrum of the EEGs under mental stress was greater than that under relax condition.

Strategies and Tools for Combinatorial Targeting of GABAergic Neurons in Mouse Cerebral Cortex.

Systematic genetic access to GABAergic cell types will facilitate studying the function and development of inhibitory circuitry. However, single gene-driven recombinase lines mark relatively broad and heterogeneous cell populations. Although intersectional approaches improve precision, it remains unclear whether they can capture cell types defined by multiple features. Here we demonstrate that combinatorial genetic and viral approaches target restricted GABAergic subpopulations and cell types characterized by distinct laminar location, morphology, axonal projection, and electrophysiological properties. Intersectional embryonic transcription factor drivers allow finer fate mapping of progenitor pools that give rise to distinct GABAergic populations, including laminar cohorts. Conversion of progenitor fate restriction signals to constitutive recombinase expression enables viral targeting of cell types based on their lineage and birth time. Properly designed intersection, subtraction, conversion, and multi-color reporters enhance the precision and versatility of drivers and viral vectors. These strategies and tools will facilitate studying GABAergic neurons throughout the mouse brain.

[Affective Stress Rating Method Based on Improved Hidden Markov Model].

To solve the defect which is recognizing but not rating the stress,or rating but not considering the influence of the previous stress state to the current state of the existing affective stress evaluation method,this paper proposes an approach of affective stress rating model on electrocardiogram(ECG).An affective stress rating algorithm based on hidden Markov model(HMM)was established with the theory of affective computing.The individual's affective stress was rated using this affective rating model combining the investigation questionnaire.Features like complexity and approximate entropy of ECG were used in the model,and a matching process suggested that it improved the accuracy of affective stress rating.The result of the experiment illustrated that the model considering the environmental factors and the influence of previous stress state to the current state was an effective method in affective stress rating,and the accuracy of rating was improved by this affective stress rating method.

[Applications of Wavelet Transform Combining Empirical Mode Decomposition in EEG Analysis with Music Intervention].

In the present paper,wavelet transform and empirical mode decomposition(EMD)are combined to extracted the features of electroencephalogram(EEG)signal with music intervention,and to achieve a better classification accuracy rate and reliability in emotional assessment in order to provide a support for music therapy.The data were from Database for Emotion Analysis using Physiological Signals(DEAP).Based on wavelet transformα,ßandθrhythms were extracted at frontal(F3,F4),temporal(T7,T8)and central regions(C3,C4).Based on the EMD,the intrinsic mode function(IMF)was analyzed and extracted.Furthermore,average energy and amplitude difference of IMF were analyzed and obtained.The support vector machine was used to assess the state of emotion in order to support music therapy.According to this algorithm,the classification accuracy rate could reach 100% between no emotions,positive emotions and negative emotions,which made a 10%improvement between positive and negative emotion recognition.Effective evaluation result between positive and negative emotions was achieved.The states of emotion would influence the effect of music therapy,undoubtedly,the classification accuracy rate increasing of emotional assessment will further help improve the effect of music therapy and provide a better support to the therapy.

[Methods and Applications of Psychological Stress State Assessment].

In this paper, the response of individual's physiological system under psychological stress state is discussed, and the theoretical support for psychological stress assessment research is provided. The two methods, i.e., the psychological stress assessment of questionnaire and physiological parameter assessment used for current psychological stress assessment are summarized. Then, the future trend of development of psychological stress assessment research is pointed out. We hope that this work could do and provide further support and help to psychological stress assessment studies.

[Affective computing--a mysterious tool to explore human emotions].

Perception, affection and consciousness are basic psychological functions of human being. Affection is the subjective reflection of different kinds of objects. The foundation of human being's thinking is constituted by the three basic functions. Affective computing is an effective tool of revealing the affectiveness of human being in order to understand the world. Our research of affective computing focused on the relation, the generation and the influent factors among different affections. In this paper, the affective mechanism, the basic theory of affective computing, is studied, the method of acquiring and recognition of affective information is discussed, and the application of affective computing is summarized as well, in order to attract more researchers into this working area.