Search

Accurate identification of fungal species is crucial for mycological research, relying significantly on experienced taxonomists’ ability to recognize fungal morphology. With the dwindling number of taxonomists, developing a rapid, accurate, and automated fungal identification method is essential, promising to markedly decrease the time and resources needed for such tasks. To address the challenges in the automatic identification of nematode-trapping fungi (NTF, belong to Orbiliaceae, Orbiliomycetes, a group of filamentous fungi that catch nematodes in soil), specifically focusing on their conidia which are often aggregated and morphologically similar, we developed an enhanced method. Our approach integrates an efficient channel attention (ECA) mechanism within the backbone layer of YOLOv8l, improving the algorithm’s capability to detect global information effectively. This adjustment significantly optimizes the detection and differentiation of limited features and small-sized conidia among aggregated samples. The experimental outcomes demonstrated that our method increases precision by 0.3%, recall by 1.8%, and mean average precision (mAP) by 0.4%, surpassing the performance of existing target detection algorithms. In addition, this method accurately identified the aggregated fungal conidia and distinguished morphologically similar spores. In conclusion, the system accurately detects and recognizes the conidia of NTF in mixed spore environments, thus providing crucial technical support for the automatic detection and early prediction of NTF.

The sine cosine algorithm (SCA) is a recently developed meta-heuristic algorithm for solving global optimization problems. It has shown excellent performance in meta-heuristic algorithms. But this algorithm also has shortcomings such as low accuracy, easy to fall into a local solution, and slow convergence speed. Aiming at these deficiencies of the SCA, a modified sine cosine algorithm with teacher supervision learning (TSL-SCA) for global optimization is proposed. First, the teacher supervision strategy can guide the population convergence and accelerate the convergence speed. Second, individuals perform reflective learning after the standard SCA position is updated, which can effectively prevent individuals from stagnating in the evolutionary process and increase population diversity. In addition, a hybrid inverse learning method is proposed. It can not only enhance the ability of finding global optimal solution and increase population distributivity, but also balance the exploration and exploitation capabilities. Differential evolution algorithm (DE), particle swarm optimization (PSO), cuckoo search (CS) algorithm, moth-flame optimization (MFO), whale optimization algorithm (WOA), Teaching-Learning-Based Optimization (TLBO), SCA and TSL-SCA are selected for simulation experiment to solve 33 benchmark optimization problems. The experimental results show that the TSL-SCA can significantly enhance the optimization accuracy and convergence speed. Furthermore, the effectiveness of the proposed method is examined by solving analog circuit fault diagnosis of filter circuit examples.

Medical datasets are usually imbalanced, where negative cases severely outnumber positive cases. Therefore, it is essential to deal with this data skew problem when training machine learning algorithms. This study uses two representative lung cancer datasets, PLCO and NLST, with imbalance ratios (the proportion of samples in the majority class to those in the minority class) of 24.7 and 25.0, respectively, to predict lung cancer incidence. This research uses the performance of 23 class imbalance methods (resampling and hybrid systems) with three classical classifiers (logistic regression, random forest, and LinearSVC) to identify the best imbalance techniques suitable for medical datasets. Resampling includes ten under-sampling methods (RUS, etc.), seven over-sampling methods (SMOTE, etc.), and two integrated sampling methods (SMOTEENN, SMOTE-Tomek). Hybrid systems include (Balanced Bagging, etc.). The results show that class imbalance learning can improve the classification ability of the model. Compared with other imbalanced techniques, under-sampling techniques have the highest standard deviation (SD), and over-sampling techniques have the lowest SD. Over-sampling is a stable method, and the AUC in the model is generally higher than in other ways. Using ROS, the random forest performs the best predictive ability and is more suitable for the lung cancer datasets used in this study. The code is available at https://mkhushi.github.io/

Previous research focused on the qualitative discussion of the correlation between surgical time and mortality in acute pancreatitis (AP). Recommendations for surgical timing of necrotizing pancreatitis are delayed as far as possible, without recommendations for individuals. The aim of this article is to predict timing of surgical intervention in necrotizing pancreatitis with recurrent neural network (RNN). Time series data in AP were retrospectively extracted from a hospital in China (n = 15,813) to develop model, and the Cerner Health Facts database in the United States (n = 142,650) was used to externally validate. The developed model, time-aware Phased-Decay long short-term memory (LSTM), was used to predict timing of surgical intervention and critical clinical features in necrotizing pancreatitis based on laboratory tests, compared to other machine learning models. Area under the ROC curve (AUC) of RNN-based models was more than 0.70. The AUC of time-aware Phased-Decay LSTM (0.75) with more explanatory was similar to that (0.76) of Phased-Decay LSTM to predict surgical timing. The developed model visualized the specific surgical process and laboratory indicators changes for the patients with AP from the onset to discharge. Different clinical features had different contribution modes with time to the specific surgical event in AP. Heart function contributed the most to the prediction of surgical intervention at the onset and in the first week. Our developed model could monitor the specific surgical process from the onset of AP to discharge and extract the contribution modes of clinical features with time in necrotizing pancreatitis.

The high complexity behind SQL language and database schemas has made database querying a challenging task to human programmers. In this paper, we present our new natural language database querying (NADAQ) system as an alternative solution, by designing new translation models smoothly fusing deep learning and traditional database parsing techniques. On top of the popular encoder-decoder model for machine translation, NADAQ injects new dimensions of schema-aware bits associated with the input words into encoder phase and adds new hidden memory neurons controlled by the finite state machine for grammatical state tracking into the decoder phase. We further develop new techniques to enable the augmented neural network to reject queries irrelevant to the contents of the target database and recommend candidate queries reversely transformed into natural language. NADAQ performs well on real-world database systems over human labeled workload, returning query results at 90% accuracy.