Prediction Problem Research Articles

Food Image Classification and Calorie Prediction for Dietary Analysis

Abstract: This paper presents a unique method to classify food items and estimate the calorie content based on photos by combining Convolutional Neural Networks (CNNs) with image processing techniques. To improve the quality of the dataset, we first curate a wide range of food photographs from different presentation styles and cuisines. We do this by applying preprocessing techniques including image segmentation and feature extraction. Next, using the CNN's capacity to extract hierarchical features from raw pixel data, a custom deep CNN architecture is trained on this dataset to efficiently classify diverse food items and achieve high accuracy in differentiating between different dishes. Furthermore, we tackle the problem of calorie prediction by employing regression models that include features extracted from the CNN, which allows one to forecast the calorie content of a food item based on its visual attributes. Our technique intends to enable users to make more educated nutritional decisions and better control their caloric intake by fusing image categorization with calorie prediction. The suggested approach shows encouraging results in terms of food item classification accuracy and precision in calorie estimate. Its possible uses include promoting better eating practices and assisting individuals, dietitians, and the food industry with their dietary monitoring. In addition, our technology gives customers access to weekly calorie intake information, which can help them avoid obesity-related illnesses like diabetes.

Spatiotemporal Mechanism-Based Spacetimeformer Network for InSAR Deformation Prediction and Identification of Retrogressive Thaw Slumps in the Chumar River Basin

The increasing incidence of retrogressive thaw slumps (RTSs) in permafrost regions underscores the need for detailed spatial and temporal analysis using InSAR technology to monitor and predict dynamic changes in the process of RTSs. Nevertheless, current InSAR deformation forecasting methods employing deep learning strategies such as the traditional long short-term memory (LSTM) and recent transformer models encounter difficulties in effectively capturing temporal features. Moreover, they are limited in their ability to directly integrate spatial information. In this paper, an innovative deep learning approach named Spacetimeformer is proposed for predicting medium- and short-term InSAR deformation of RTSs in the Chumar River area. This method employs a transformer architecture with a spatiotemporal attention mechanism,which enhances the long-term prediction capabilities of time series models and dynamic spatial modeling. It is applicable to multivariate InSAR spatiotemporal deformation prediction problems. The findings include a list of 72 RTSs compiled based on derived InSAR deformation maps and Sentinel-2 optical images, of which 64 have an average deformation rate exceeding 10 mm/year, indicating signs of permafrost degradation. The density distribution of the displacement maps predicted by the Spacetimeformer model aligned well with the InSAR deformation maps obtained from the small baseline subset (SBAS) method, with the overall prediction deviation controlled within 20 mm. In addition, the point-scale prediction results were compared with LSTM and transformer models. This study indicates that the Spacetimeformer network achieved good results in predicting the deformation of RTSs, with a root mean square error of 1.249 mm. The Spacetimeformer method for deformation prediction with the spacetime mechanism presented in this study can serve as a general framework for multivariate deformation prediction based on InSAR results. It can also quantitatively assess the spatial deformation characteristics and deformation trends of RTSs.

Residual Spatiotemporal Convolutional Neural Network Based on Multisource Fusion Data for Approaching Precipitation Forecasting

Approaching precipitation forecast refers to the prediction of precipitation within a short time scale, which is usually regarded as a spatiotemporal sequence prediction problem based on radar echo maps. However, due to its reliance on single-image prediction, it lacks good capture of sudden severe convective events and physical constraints, which may lead to prediction ambiguities and issues such as false alarms and missed alarms. Therefore, this study dynamically combines meteorological elements from surface observations with upper-air reanalysis data to establish complex nonlinear relationships among meteorological variables based on multisource data. We design a Residual Spatiotemporal Convolutional Network (ResSTConvNet) specifically for this purpose. In this model, data fusion is achieved through the channel attention mechanism, which assigns weights to different channels. Feature extraction is conducted through simultaneous three-dimensional and two-dimensional convolution operations using a pure convolutional structure, allowing the learning of spatiotemporal feature information. Finally, feature fitting is accomplished through residual connections, enhancing the model’s predictive capability. Furthermore, we evaluate the performance of our model in 0–3 h forecasting. The results show that compared with baseline methods, this network exhibits significantly better performance in predicting heavy rainfall. Moreover, as the forecast lead time increases, the spatial features of the forecast results from our network are richer than those of other baseline models, leading to more accurate predictions of precipitation intensity and coverage area.

Classification of Major Solar Flares from Extremely Imbalanced Multivariate Time Series Data Using Minimally Random Convolutional Kernel Transform

Solar flares are characterized by sudden bursts of electromagnetic radiation from the Sun’s surface, and are caused by the changes in magnetic field states in active solar regions. Earth and its surrounding space environment can suffer from various negative impacts caused by solar flares, ranging from electronic communication disruption to radiation exposure-based health risks to astronauts. In this paper, we address the solar flare prediction problem from magnetic field parameter-based multivariate time series (MVTS) data using multiple state-of-the-art machine learning classifiers that include MINImally RandOm Convolutional KErnel Transform (MiniRocket), Support Vector Machine (SVM), Canonical Interval Forest (CIF), Multiple Representations Sequence Learner (Mr-SEQL), and a Long Short-Term Memory (LSTM)-based deep learning model. Our experiment is conducted on the Space Weather Analytics for Solar Flares (SWAN-SF) benchmark data set, which is a partitioned collection of MVTS data of active region magnetic field parameters spanning over nine years of operation of the Solar Dynamics Observatory (SDO). The MVTS instances of the SWAN-SF dataset are labeled by GOES X-ray flux-based flare class labels, and attributed to extreme class imbalance because of the rarity of the major flaring events (e.g., X and M). As a performance validation metric in this class-imbalanced dataset, we used the True Skill Statistic (TSS) score. Finally, we demonstrate the advantages of the MVTS learning algorithm MiniRocket, which outperformed the aforementioned classifiers without the need for essential data preprocessing steps such as normalization, statistical summarization, and class imbalance handling heuristics.

Hierarchical Alignment with Polar Contrastive Learning for Next-Basket Recommendation

Next-basket recommendation methods focus on the inference of the next basket by considering the corresponding bas- ket sequence. Although many methods have been developed for the task, they usually suffer from data sparsity. The number of inter- actions between entities is relatively small compared to their huge bases, so it is crucial to mine as much hidden information as possible from the limited historical interactions for prediction. However, the existing methods mainly just treat the next-basket recommendation task as a single-view sequential prediction problem, which leads to the inadequate mining of the information hidden in multiple views, and the mining of other patterns in the historical interactions is neglected, thus making it difficult to learn high-quality representa- tions and limiting the recommendation effect. To alleviate the above issues, we propose a novel method named Hap CL for next-basket recommendation, which mines information from multiple views and patterns with the help of polar contrastive learning. A hier- archical module is designed to mine multiple patterns of historical interactions from different views at two levels. In order to mine self- supervised signals, we design a polar contrastive learning module with a novel graph-based augmentation approach. Experiments on three real-world datasets validate the effectiveness of Hap CL.

Sailfish optimizer based CLAHE with U-NET for MRI brain tumour segmentation

Semantic brain tumour segmentation is a significant contribution to medical image processing. This research is helpful for doctors making diagnoses and determining the severity of lesions. In recent years, convolutional neural networks have sometimes been known as self-remarkable representations in computer vision tasks. In three-dimensional medical image processing, CNN with architecture and skip connections has become increasingly popular. However, they are inadequate at both acquiring nearby and far-off semantic knowledge. However, the transformer's use of a vision. This accomplishment was made possible by the global information modelling capabilities of the transformer. When tryingto perform challenging prediction tasks, such as segmenting 3D medical pictures, it is vital to consider local and global features. In this study, we propose a hypothesis that predicts pre-processing steps that enhance the image quality and significantly impact accuracy with any statistical image classification method. We used a better picture enhancement methodology to back up our idea. This method has three unique stages: a median filter to eliminate noise, a histogram equalisation technique to boost contrast, and a grayscale-to-RGB conversion. The clipping limit of contrast-limited Adaptive Histogram Equalisation (CLAHE)is calculated by the Sailfish Optimization Algorithm (SOA) to achieve optimal picture enhancement. This study classifies semantically segmenting 3D brain tumours as a sequence-to-sequence prediction problem. U-net is proposed in the article as a novel method for segmenting 3D medical images; it incorporates a structure. A new technique for segmenting 3D medical images, U-net, is emerging. We trained and assessed our method on the BRATS 2019 dataset, which was found to outperform state-of-the-art algorithms and be competitive under similar settings.

Investigation on the Reduced-Order Model for the Hydrofoil of the Blended-Wing-Body Underwater Glider Flow Control with Steady-Stream Suction and Jets Based on the POD Method

The rapid acquisition of flow field characterization information is crucial for closed-loop active flow control. The proper orthogonal decomposition (POD) method is a widely used flow field downscaling modeling method to obtain flow characteristics effectively. Based on the POD method, a flow field reduced-order model (ROM) is constructed in this paper for the flow field control of a hydrofoil of a blended-wing-body underwater glider (BWB-UG) with stabilized suction and blowing forces. Compared with the computational fluid dynamics (CFD) simulation, the computational time required to predict the target flow field using the established POD-ROM is only about 0.1 s, which is significantly less than the CFD simulation time. The average relative error of the predicted surface pressure is not more than 6.9%. These results confirm the accuracy and efficiency of the POD-ROM in reconstructing flow characteristics. The timeliness problem of fast flow field prediction in BWB-UG active flow control is solved by establishing a fast prediction model in an innovative way.

Use of machine learning models in condition monitoring of abrasive belt in robotic arm grinding process

AbstractAlthough the aspects that affect the performance and the deterioration of abrasive belt grinding are known, wear prediction of abrasive belts in the robotic arm grinding process is still challenging. Massive wear of coarse grains on the belt surface has a serious impact on the integrity of the tool and it reduces the surface quality of the finished products. Conventional wear status monitoring strategies that use special tools result in the cessation of the manufacturing production process which sometimes takes a long time and is highly dependent on human capabilities. The erratic wear behavior of abrasive belts demands machining processes in the manufacturing industry to be equipped with intelligent decision-making methods. In this study, to maintain a uniform tool movement, an abrasive belt grinding is installed at the end-effector of a robotic arm to grind the surface of a mild steel workpiece. Simultaneously, accelerometers and force sensors are integrated into the system to record its vibration and forces in real-time. The vibration signal responses from the workpiece and the tool reflect the wear level of the grinding belt to monitor the tool’s condition. Intelligent monitoring of abrasive belt grinding conditions using several machine learning algorithms that include K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), and Decision Tree (DT) are investigated. The machine learning models with the optimized hyperparameters that produce the highest average test accuracy were found using the DT, Random Forest (RF), and XGBoost. Meanwhile, the lowest latency was obtained by DT and RF. A decision-tree-based classifier could be a promising model to tackle the problem of abrasive belt grinding prediction. The application of various algorithms will be a major focus of our research team in future research activities, investigating how we apply the selected methods in real-world industrial environments.

A Transformer Approach for Cognitive Impairment Classification and Prediction.

Early classification and prediction of Alzheimer disease (AD) and amnestic mild cognitive impairment (aMCI) with noninvasive approaches is a long-standing challenge. This challenge is further exacerbated by the sparsity of data needed for modeling. Deep learning methods offer a novel method to help address these challenging multiclass classification and prediction problems. We analyzed 3 target feature-sets from the National Alzheimer's Coordinating Center (NACC) dataset: (1) neuropsychological (cognitive) data; (2) patient health history data; and (3) the combination of both sets. We used a masked Transformer-encoder without further feature selection to classify the samples on cognitive status (no cognitive impairment, aMCI, AD)-dynamically ignoring unavailable features. We then fine-tuned the model to predict the participants' future diagnosis in 1 to 3 years. We analyzed the sensitivity of the model to input features via Feature Permutation Importance. We demonstrated (1) the masked Transformer-encoder was able to perform prediction with sparse input data; (2) high multiclass current cognitive status classification accuracy (87% control, 79% aMCI, 89% AD); (3) acceptable results for 1- to 3-year multiclass future cognitive status prediction (83% control, 77% aMCI, 91% AD). The flexibility of our methods in handling inconsistent data provides a new venue for the analysis of cognitive status data.

Incorporating Multi-Source Market Sentiment and Price Data for Stock Price Prediction

The problem of stock price prediction has been a hot research issue. Stock price is influenced by various factors at the same time, and market sentiment is one of the most critical factors. Financial texts such as news and investor comments reflect investor sentiment in the stock market and influence market movements. Previous research models have struggled to accurately mine multiple sources of market sentiment information originating from the Internet and traditional sentiment analysis models are challenging to quantify and combine indicator data from market data and multi-source sentiment data. Therefore, we propose a BERT-LLA stock price prediction model incorporating multi-source market sentiment and technical analysis. In the sentiment analysis module, we propose a semantic similarity and sector heat-based model to screen for related sectors and use fine-tuned BERT models to calculate the text sentiment index, transforming the text data into sentiment index time series data. In the technical indicator calculation module, technical indicator time series are calculated using market data. Finally, in the prediction module, we combine the sentiment index time series and technical indicator time series and employ a two-layer LSTM network prediction model with an integrated attention mechanism to predict stock close price. Our experiment results show that the BERT-LLA model can accurately capture market sentiment and has a strong practicality and forecasting ability in analyzing market sentiment and stock price prediction.

Joint reconstruction and prediction regions for unobserved exponential lifetimes under doubly Type II censoring

ABSTRACT The doubly Type II censoring scheme, in which some of the smallest and largest lifetimes are censored, is an important and widely used censoring scheme in life-testing experiments and reliability. In this paper, the problem of simultaneous reconstruction and prediction for unobserved lifetimes in a doubly Type II censored sample from the one-parameter exponential distribution is discussed. For this purpose, the joint reconstruction and prediction (JRP) regions are obtained based on two independent pivotal quantities. First, the balanced JRP regions for the unobserved lifetimes are derived, and then a constrained optimization problem is formulated and solved to find the JRP regions with the smallest area. For illustrative and comparative purposes, a simulation study and two illustrative examples are presented.

Psychomotor symptoms, cognitive impairments and suicidal thoughts after COVID-19 infection: a case report and the possible allostatic mechanism.

Although neuropsychiatric manifestations are common in survivors of coronavirus disease 2019 (COVID-19), the pathophysiology is not yet elucidated. Here we describe the case of a geriatric inpatient who developed postCOVID depression with psychomotor retardation, anxiety, hopelessness, executive function problems, and suicidal ideations. The language problems and cognitive impairments coemerged with the motor problems. We propose a mechanism associated with problems in energy prediction and regulation in which the coronavirus infection, which causes neuroinflammation and viral activity in the nervous system, interferes with the reward pathway and sensory prediction process. Sigma-1 receptor agonists such as sertraline may regulate energy expenditure and, thus, be beneficial to the process. The treatment improvements in our patient included those in the autonomic nervous system, activity, and circadian rhythm.

Application of the Nadaraya-Watson estimator based attention mechanism to the field of predictive maintenance

Attention mechanism has recently gained immense importance in the natural language processing (NLP) world. This technique highlights parts of the input text that the NLP task (such as translation) must pay “attention” to. Inspired by this, some researchers have recently applied the NLP domain, deep-learning based, attention mechanism techniques to predictive maintenance. In contrast to the deep-learning based solutions, Industry 4.0 predictive maintenance solutions that often rely on edge-computing, demand lighter predictive models. With this objective, we have investigated the adaptation of a simpler, incredibly fast and compute-resource friendly, “Nadaraya-Watson estimator based” attention method. We develop a method to predict tool-wear of a milling machine using this attention mechanism and demonstrate, with the help of heat-maps, how the attention mechanism highlights regions that assist in predicting onset of tool-wear. We validate the effectiveness of this adaptation on the benchmark IEEEDataPort PHM Society dataset, by comparing against other comparatively “lighter” machine learning techniques – Bayesian Ridge, Gradient Boosting Regressor, SGD Regressor and Support Vector Regressor. Our experiments indicate that the proposed Nadaraya-Watson attention mechanism performed best with an MAE of 0.069, RMSE of 0.099 and R2 of 83.40 %, when compared to the next best technique Gradient Boosting Regressor with figures of 0.100, 0.138, 66.51 % respectively. Additionally, it produced a lighter and faster model as well.•We propose a Nadaraya-Watson estimator based “attention mechanism”, applied to a predictive maintenance problem.•Unlike the deep-learning based attention mechanisms from the NLP domain, our method creates fast, light and high-performance models, suitable for edge computing devices and therefore supports the Industry 4.0 initiative.•Method validated on real tool-wear data of a milling machine.

Risk analysis of noise-induced hearing loss of workers in the automobile manufacturing industries based on back-propagation neural network model: a cross-sectional study in Han Chinese population.

This study aims to predict the risk of noise-induced hearing loss (NIHL) through a back-propagation neural network (BPNN) model. It provides an early, simple and accurate prediction method for NIHL. Population based, a cross sectional study. Han, China. This study selected 3266 Han male workers from three automobile manufacturing industries. Information including personal life habits, occupational health test information and occupational exposure history were collected and predictive factors of NIHL were screened from these workers. BPNN and logistic regression models were constructed using these predictors. The input variables of BPNN model were 20, 16 and 21 important factors screened by univariate, stepwise and lasso-logistic regression. When the BPNN model was applied to the test set, it was found to have a sensitivity (TPR) of 83.33%, a specificity (TNR) of 85.92%, an accuracy (ACC) of 85.51%, a positive predictive value (PPV) of 52.85%, a negative predictive value of 96.46% and area under the receiver operating curve (AUC) is: 0.926 (95% CI: 0.891 to 0.961), which demonstrated the better overall properties than univariate-logistic regression modelling (AUC: 0.715) (95% CI: 0.652 to 0.777). The BPNN model has better predictive performance against NIHL than the stepwise-logistic and lasso-logistic regression model in terms of TPR, TNR, ACC, PPV and NPV (p<0.05); the area under the receiver operating characteristics curve of NIHL is also higher than that of the stepwise and lasso-logistic regression model (p<0.05). It was a relatively important factor in NIHL to find cumulative noise exposure, auditory system symptoms, age, listening to music or watching video with headphones, exposure to high temperature and noise exposure time in the trained BPNN model. The BPNN model was a valuable tool in dealing with the occupational risk prediction problem of NIHL. It can be used to predict the risk of an individual NIHL.

Multi‐event‐based distributed cooperative predictive control for the multi‐agent system

AbstractIn this paper, we provide the detailed distributed cooperative predictive control scheme for the multi‐agent system (MAS) affected by the network delays. Firstly, we restate the distributed cooperative predictive control problem by introducing iterative learning‐based MAS, which can guarantee the cooperative predictive control of the MAS. To alleviate the unfavorable network constrains, the multi‐event‐triggered conditions are formulated via considering the predictive and error data sufficiently. With these preparations, the well‐posed Roesser‐type two‐dimensional (2D) system is achieved equivalently to the distributed iterative learning predictive system. On this basis, we employ 2D predictive system analysis and control theory to realize the predictive control for the equivalent 2D system and then obtain the collaborative predictive control for the MAS under multi‐event‐triggered mechanism. The corresponding stability criteria, controller, and observer gains are provided by the executable matrix constraints and algorithms design. To conclude the paper, the numerical example is proposed to illustrate the effectiveness and practicability of the provided methods and algorithms.

A Multiple Controlled Toffoli Driven Adaptive Quantum Neural Network Model for Dynamic Workload Prediction in Cloud Environments.

The key challenges in cloud computing encompass dynamic resource scaling, load balancing, and power consumption. Accurate workload prediction is identified as a crucial strategy to address these challenges. Despite numerous methods proposed to tackle this issue, existing approaches fall short of capturing the high-variance nature of volatile and dynamic cloud workloads. Consequently, this paper introduces a novel model aimed at addressing this limitation. This paper presents a novel Multiple Controlled Toffoli-driven Adaptive Quantum Neural Network (MCT-AQNN) model to establish an empirical solution to complex, elastic as well as challenging workload prediction problems by optimizing the exploration, adaption, and exploitation proficiencies through quantum learning. The computational adaptability of quantum computing is ingrained with machine learning algorithms to derive more precise correlations from dynamic and complex workloads. The furnished input data point and hatched neural weights are refitted in the form of qubits while the controlling effects of Multiple Controlled Toffoli (MCT) gates are operated at the hidden and output layers of Quantum Neural Network (QNN) for enhancing learning capabilities. Complimentarily, a Uniformly Adaptive Quantum Machine Learning (UAQL) algorithm has evolved to functionally and effectually train the QNN. The extensive experiments are conducted and the comparisons are performed with state-of-the-art methods using four real-world benchmark datasets. Experimental results evince that MCT-AQNN has up to 32%-96% higher accuracy than the existing approaches.

TransFOL: A Logical Query Model for Complex Relational Reasoning in Drug-Drug Interaction.

Predicting drug-drug interaction (DDI) plays a crucial role in drug recommendation and discovery. However, wet lab methods are prohibitively expensive and time-consuming due to drug interactions. In recent years, deep learning methods have gained widespread use in drug reasoning. Although these methods have demonstrated effectiveness, they can only predict the interaction between a drug pair and do not contain any other information. However, DDI is greatly affected by various other biomedical factors (such as the dose of the drug). As a result, it is challenging to apply them to more complex and meaningful reasoning tasks. Therefore, this study regards DDI as a link prediction problem on knowledge graphs and proposes a DDI prediction model based on Cross-Transformer and Graph Convolutional Networks (GCN) in first-order logical query form, TransFOL. In the model, a biomedical query graph is first built to learn the embedding representation. Subsequently, an enhancement module is designed to aggregate the semantics of entities and relations. Cross-Transformer is used for encoding to obtain semantic information between nodes, and GCN is used to gather neighbour information further and predict inference results. To evaluate the performance of TransFOL on common DDI tasks, we conduct experiments on two benchmark datasets. The experimental results indicate that our model outperforms state-of-the-art methods on traditional DDI tasks. Additionally, we introduce different biomedical information in the other two experiments to make the settings more realistic. Experimental results verify the strong drug reasoning ability and generalization of TransFOL in complex settings. Data and code are available at https://github.com/Cheng0829/TransFOL.

SEMA 2.0: web-platform for B-cell conformational epitopes prediction using artificial intelligence.

Prediction of conformational B-cell epitopes is a crucial task in vaccine design and development. In this work, we have developed SEMA 2.0, a user-friendly web platform that enables the research community to tackle the B-cell epitopes prediction problem using state-of-the-art protein language models. SEMA 2.0 offers comprehensive research tools for sequence- and structure-based conformational B-cell epitopes prediction, accurate identification of N-glycosylation sites, and a distinctive module for comparing the structures of antigen B-cell epitopes enhancing our ability to analyze and understand its immunogenic properties. SEMA 2.0 website https://sema.airi.net is free and open to all users and there is no login requirement. Source code is available at https://github.com/AIRI-Institute/SEMAi.

Research on power generation prediction of hydropower in river basin based on multi-head attention graph convolutional neural network

For the power generation prediction of traditional hydropower stations, most of them only use time series prediction and neglect to study the spatial topological relationship of hydropower stations in the river basin, so that it is difficult to fully explore the characteristic relationship of space power stations. In this paper, a research method for power generation prediction of hydropower in river basin hydropower stations based on multi-head attention map convolutional neural network is proposed. This method establishes a first-level node neighborhood feature map based on the spatial geographic distribution information of hydropower stations in the basin, and uses the method of graph convolution to carry out node feature mining and feature learning, so as to transform the power generation capacity evaluation problem of the hydropower station in the basin into the node prediction problem in the graph, which is different from the global normalization rule. the multi-head attention mechanism introduced further improves the information aggregation quality of the graph node, and uses the historical temperature, power generation, electricity price, unit status and other data of each hydropower station in the basin for training. The reasoning results show that the proposed method achieves higher accuracy than other schemes, and the power prediction method is conducive to the formulation of power plans of hydropower stations in the basin, and can also play a positive role in guiding the site selection of hydropower plants.

Parallel Dual-Branch Fusion Network for Epileptic Seizure Prediction

Epilepsy is a prevalent chronic disorder of the central nervous system. The timely and accurate seizure prediction using the scalp Electroencephalography (EEG) signal can make patients adopt reasonable preventive measures before seizures occur and thus reduce harm to patients. In recent years, deep learning-based methods have made significant progress in solving the problem of epileptic seizure prediction. However, most current methods mainly focus on modeling short- or long-term dependence in EEG, while neglecting to consider both. In this study, we propose a Parallel Dual-Branch Fusion Network (PDBFusNet) which aims to combine the complementary advantages of Convolutional Neural Network (CNN) and Transformer. Specifically, the features of the EEG signal are first extracted using Mel Frequency Cepstral Coefficients (MFCC). Then, the extracted features are delivered into the parallel dual-branches to simultaneously capture the short- and long-term dependencies of EEG signal. Further, regarding the Transformer branch, a novel feature fusion module is developed to enhance the ability of utilizing time, frequency, and channel information. To evaluate our proposal, we perform sufficient experiments on the public epileptic EEG dataset CHB-MIT, where the accuracy, sensitivity, specificity and precision are 95.76%, 95.81%, 95.71% and 95.71%, respectively. PDBFusNet shows superior performance compared to state-of-the-art competitors, which confirms the effectiveness of our proposal.