Chunming Ma

Bio: Chunming Ma is an academic researcher from Dalian University of Technology. The author has contributed to research in topics: Computer science & Artificial intelligence. The author has an hindex of 1, co-authored 1 publications receiving 1 citations.

A Novel Fluorescent Probe for Hydrogen Peroxide and Its Application in Bio-Imaging.

Abstract: Hydrogen peroxide (H2O2) plays an important role in the human body and monitoring its level is meaningful due to the relationship between its level and diseases. A fluorescent sensor (CMB) based on coumarin was designed and its ability for detecting hydrogen peroxide by fluorescence signals was also studied. The CMB showed an approximate 25-fold fluorescence enhancement after adding H2O2 due to the interaction between the CMB and H2O2 and had the potential for detecting physiological H2O2. It also showed good biocompatibility and permeability, allowing it to penetrate cell membranes and zebrafish tissues, thus it can perform fluorescence imaging of H2O2 in living cells and zebrafish. This probe is a promising tool for monitoring the level of H2O2 in related physiological and pathological research.

Multimodal Sentiment Analysis Representations Learning via Contrastive Learning with Condense Attention Fusion

Abstract: Multimodal sentiment analysis has gained popularity as a research field for its ability to predict users’ emotional tendencies more comprehensively. The data fusion module is a critical component of multimodal sentiment analysis, as it allows for integrating information from multiple modalities. However, it is challenging to combine modalities and remove redundant information effectively. In our research, we address these challenges by proposing a multimodal sentiment analysis model based on supervised contrastive learning, which leads to more effective data representation and richer multimodal features. Specifically, we introduce the MLFC module, which utilizes a convolutional neural network (CNN) and Transformer to solve the redundancy problem of each modal feature and reduce irrelevant information. Moreover, our model employs supervised contrastive learning to enhance its ability to learn standard sentiment features from data. We evaluate our model on three widely-used datasets, namely MVSA-single, MVSA-multiple, and HFM, demonstrating that our model outperforms the state-of-the-art model. Finally, we conduct ablation experiments to validate the efficacy of our proposed method.

Fast and Robust Infrared Small Target Detection Using Weighted Local Difference Variance Measure

Abstract: Infrared (IR) small-target-detection performance restricts the development of infrared search and track (IRST) systems. Existing detection methods easily lead to missed detection and false alarms under complex backgrounds and interference, and only focus on the target position while ignoring the target shape features, which cannot further identify the category of IR targets. To address these issues and guarantee a certain runtime, a weighted local difference variance measure (WLDVM) algorithm is proposed. First, Gaussian filtering is used to preprocess the image by using the idea of a matched filter to purposefully enhance the target and suppress noise. Then, the target area is divided into a new tri-layer filtering window according to the distribution characteristics of the target area, and a window intensity level (WIL) is proposed to represent the complexity level of each layer of windows. Secondly, a local difference variance measure (LDVM) is proposed, which can eliminate the high-brightness background through the difference-form, and further use the local variance to make the target area appear brighter. The background estimation is then adopted to calculate the weighting function to determine the shape of the real small target. Finally, a simple adaptive threshold is used after obtaining the WLDVM saliency map (SM) to capture the true target. Experiments on nine groups of IR small-target datasets with complex backgrounds illustrate that the proposed method can effectively solve the above problems, and its detection performance is better than seven classic and widely used methods.

Exploring Multimodal Sentiment Analysis via CBAM Attention and Double-layer BiLSTM Architecture

Abstract: Because multimodal data contains more modal information, multimodal sentiment analysis has become a recent research hotspot. However, redundant information is easily involved in feature fusion after feature extraction, which has a certain impact on the feature representation after fusion. Therefore, in this papaer, we propose a new multimodal sentiment analysis model. In our model, we use BERT + BiLSTM as new feature extractor to capture the long-distance dependencies in sentences and consider the position information of input sequences to obtain richer text features. To remove redundant information and make the network pay more attention to the correlation between image and text features, CNN and CBAM attention are added after splicing text features and picture features, to improve the feature representation ability. On the MVSA-single dataset and HFM dataset, compared with the baseline model, the ACC of our model is improved by 1.78% and 1.91%, and the F1 value is enhanced by 3.09% and 2.0%, respectively. The experimental results show that our model achieves a sound effect, similar to the advanced model.

GCAT-GTCU: Graph-Connected Attention Network and Gate Than Change Unit for Aspect-Level Sentiment Analysis

Abstract: Currently, attention mechanisms are widely used in aspect-level sentiment analysis tasks. Previous studies have only used attention mechanisms combined with neural networks for aspect-level sentiment classification, and the feature extraction of the model is insufficient. When the same aspect and sentiment polarity appear in multiple sentences, the semantic information sharing of the same domain is also ignored, resulting in low model performance. To address these problems, the paper proposes an aspect-level sentiment analysis model, GCAT-GTCU, which combines a Graph-connected Attention Network containing symmetry with Gate Than Change Unit. Three nodes of words, sentences, and aspects are constructed, and local and deep-level features of sentences are extracted using CNN splicing BiGRU; node connection information is added to GAT to form a GCAT containing symmetry to realize the information interaction of three nodes, pay attention to the contextual information, and update the shared information of three nodes at any time; a new gating mechanism GTCU is constructed to filter noisy information and control the flow of sentiment information; finally, the three nodes are extracted information to predict the final sentiment polarity. The experimental results on four publicly available datasets show that the model outperforms the baseline model against which it is compared in some very controlled situations.

Fluorescence imaging to probe mercury induced oxidative stress in living systems

Abstract: Mercury is known a toxic heavy metal pollutant, and mercuric derivatives severely threaten ecological environment and human health. Their toxicological effects are usually associated with oxidative stress and redox imbalance. However, rare visualized evidences to reveal mercury induced oxidative stress in living systems. According to its characteristics, we suspected mercury resulted in two consequences, one is reactive oxygen species (ROS) outburst, the other is oxygen consumption caused hypoxia stress. Hydrogen peroxide (H2O2) is an important oxygen metabolite, and superfluous H2O2 will attack intracellular antioxidants and trigger oxidative stress, then cause dysfunctions and many diseases. Although the research of H2O2 fluorescence probe has been greatly advanced, the exploration of H2O2 bioeffects under environmental stress was scarce. There is still necessary to develop powerful tools to explore redox homeostasis and H2O2 fluctuations under mercury stress. Herein, we have designed fluorescent probe MSO-Bindol for monitoring H2O2 fluctuations through destruction of carbon-carbon double bond leading to ratiometric fluorescent changes. MSO-Bindol is successfully used to observe H2O2 variations in cells and zebrafish exposed to various stimulations or environmental stress especially mercury stress. Moreover, imaging results provide visualization proofs for Hg2+-mediated H2O2 variations and reveal the relationship between Hg2+-induced oxidative stress and up-regulated H2O2 in biological systems.

Rational design of a selective and sensitive “turn-on” fluorescent probe for monitoring and imaging hydrogen peroxide in living cells

Abstract: As one type of reactive oxygen species (ROS), hydrogen peroxide (H2O2) plays a key role in regulating a variety of cellular functions. Herein, a fluorescent probe N-Py-BO was well designed and synthesized and its ability for detecting H2O2 by fluorescence intensity was evaluated. In the design, the arylboronate ester group was acted as a reaction site for H2O2. Upon reaction with H2O2 under physiological conditions, the boronate moiety in the probe was oxidized, followed by detachment from the probe and as a result, a “turn-on” fluorescence response for H2O2 was acquired. Due to the D–A structure formation between N,N′-dimethylaminobenzene and the –CN group and the linkage by thiophene and CC bonds to increase the conjugate length, this probe showed a remarkable red shift of emission wavelength (650 nm) as well as a large Stokes shift (214 nm). An excellent linear relation with concentrations of H2O2 ranging from 2.0 to 200 μM and a good selectivity over other biological species were obtained. Importantly, taking advantage of the low toxicity and good biocompatibility, the developed probe was successfully applied to monitoring and imaging H2O2 and its level fluctuation in living cells, which provided a powerful tool for evaluation of cellular oxidative stress and understanding the pathophysiological process of H2O2-related diseases.

Exploring Multimodal Sentiment Analysis via CBAM Attention and Double-layer BiLSTM Architecture

Abstract: Because multimodal data contains more modal information, multimodal sentiment analysis has become a recent research hotspot. However, redundant information is easily involved in feature fusion after feature extraction, which has a certain impact on the feature representation after fusion. Therefore, in this papaer, we propose a new multimodal sentiment analysis model. In our model, we use BERT + BiLSTM as new feature extractor to capture the long-distance dependencies in sentences and consider the position information of input sequences to obtain richer text features. To remove redundant information and make the network pay more attention to the correlation between image and text features, CNN and CBAM attention are added after splicing text features and picture features, to improve the feature representation ability. On the MVSA-single dataset and HFM dataset, compared with the baseline model, the ACC of our model is improved by 1.78% and 1.91%, and the F1 value is enhanced by 3.09% and 2.0%, respectively. The experimental results show that our model achieves a sound effect, similar to the advanced model.