In recent years, visual cancer information retrieval using Artificial Intelligence has been shown to be effective in diagnosis and treatment. Especially for a modern liver-cancer diagnosis system, the automated tumor annotation plays a crucial role. So-called tumor annotation refers to tagging the tumor in Biomedical images by computer vision technologies such as Deep Learning. After annotation, the tumor information such as tumor location, tumor size and tumor characteristics can be output into a clinical report. To this end, this paper proposes an effective approach that includes tumor segmentation, tumor location, tumor measuring, and tumor recognition to achieve high-quality tumor annotation, thereby assisting radiologists in efficiently making accurate diagnosis reports. For tumor segmentation, a Multi-Residual Attention Unet is proposed to alleviate problems of vanishing gradient and information diversity. For tumor location, an effective Multi-SeResUnet is proposed to partition the liver into 8 couinaud segments. Based on the partitioned segments, the tumor is located accurately. For tumor recognition, an effective multi-labeling classifier is used to recognize the tumor characteristics by the visual tumor features. For tumor measuring, a regression model is proposed to measure the tumor size. To reveal the effectiveness of individual methods, each method was evaluated on real datasets. The experimental results reveal that the proposed methods are more promising than the state-of-the-art methods in tumor segmentation, tumor measuring, tumor localization and tumor recognition. Specifically, the average tumor size error and the annotation accuracy are 0.432 cm and 91.6%, respectively, which suggest potential for reducing radiologists’ workload. In summary, this paper proposes an effective tumor annotation for an automated diagnosis support system. Clinical and Translational Impact Statement—The proposed methods have been evaluated and shown to significantly improve the efficiency and accuracy of liver tumor annotation, reducing the time required for radiologists to complete reports on tumor segmentation, liver partition, tumor measuring and tumor recognition. By integrating into existing clinical decision support systems, it has the potential to reduce diagnostic errors and treatment delays, thereby improving patient outcomes and clinical workflow.

In this paper, we study the scheduling problem of semiconductor-product thermal cycling tests (TCT), in which a batch of TCT test orders is issued to a testing machine. Each test order contains one or several test items, each with its own parameter conditions that must be satisfied. A machine has its capacity and overall equipment effectiveness (OEE). Additionally, order priorities are also considered. We propose a genetic-algorithm-based grouping scheduling method that handles grouping and scheduling at the same time with the objective of minimizing lateness. It groups genes and encodes chromosomes with variable lengths. Furthermore, to evaluate each chromosome, we propose a fitness function that simultaneously considers the delay time, number of test items, priority sequence, and equipment effectiveness rate. We also discuss strategies to eliminate non-feasible solutions after genetic operations. The effectiveness of the proposed method is validated through experiments using simulated production data and is compared against traditional methods. The experimental results for data with different densities of orders (off-peak season and peak season) show that the proposed method outperforms the others under the different types of orders.

Over the past few decades, recognition of early lung cancers was researched for effective treatments. In early lung cancers, the invasiveness is an important factor for expected survival rates. Hence, how to effectively identify the invasiveness by computed tomography (CT) images became a hot topic in the field of biomedical science. Although a number of previous works were shown to be effective on this topic, there remain some problems unsettled still. First, it needs a large amount of marked data for a better prediction, but the manual cost is high. Second, the accuracy is always limited in imbalance data. To alleviate these problems, in this paper, we propose an effective CT invasiveness recognizer by semi-automated segmentation. In terms of semi-automated segmentation, it is easy for doctors to mark the nodules. Just based on one clicked pixel, a nodule object in a CT image can be marked by fusing two proposed segmentation methods, including thresholding-based morphology and deep learning-based mask region-based convolutional neural network (Mask-RCNN). For thresholding-based morphology, an initial segmentation is derived by adaptive pixel connections. Then, a mathematical morphology is performed to achieve a better segmentation. For deep learning-based mask-RCNN, the anchor is fixed by the clicked pixel to reduce the computational complexity. To incorporate advantages of both, the segmentation is switched between these two sub-methods. After segmenting the nodules, a boosting ensemble classification model with feature selection is executed to identify the invasiveness by equalized down-sampling. The extensive experimental results on a real dataset reveal that the proposed segmentation method performs better than the traditional segmentation ones, which can reach an average dice improvement of 392.3%. Additionally, the proposed ensemble classification model infers better performances than the compared method, which can reach an area under curve (AUC) improvement of 5.3% and a specificity improvement of 14.3%. Moreover, in comparison with the models with imbalance data, the improvements of AUC and specificity can reach 10.4% and 33.3%, respectively.

In the past, the liver tumors were reported manually in an unstructured format. There actually exists much valuable knowledge in these reports for further disease risk assessment, disease recognition and treatment recommendation. Yet, it is not easy to read and mine knowledge from the unstructured reports. Hence, how to extract the knowledge from these biomedical reports effectively and efficiently has been a challenging issue in the past decades. Although a set of Natural Language Processing techniques were proposed for Bio-medical information retrieval, few related works were made on transforming the unstructured CT liver-tumor reports into structured ones. To aim at this issue, in this paper, we propose a two-stage report structuring method by integrating effective Natural Language Processing (NLP) and interpretable machine learning. For the first stage, the candidate keywords in unstructured reports are extracted. Next, the feature keywords are determined by the feature-selection technique. For the second stage, the well-known multi-classifiers are performed, and finally the reports are labeled in a refined structure format. Further, the factor keywords in the classification model are filtered to interpret the performance. In overall, the proposed report structuring method generates a hierarchical data structure, including the common features and refined features in the $1^{\mathrm {st}}$ and $2^{\mathrm {nd}}$ levels/stages, respectively. To reveal the performance of proposed method, a set of evaluations were conducted and the results show that, the proposed method is more promising than the fashion neural networks such as Bert (Bidirectional Encoder Representations from Transformers) in terms of effectiveness and efficiency.

Trading strategies are usually employed for finding trading signals for increasing returns as well as reducing risks. As a result, many approaches have been proposed for obtaining trading strategy portfolio. The group trading strategy portfolio (GTSP) optimization approaches that can be used to provide various trading strategy portfolios were also proposed. Because different criteria should be considered to derive GTSPs, a MOGA (multi-objective genetic algorithm) based approach has been presented for searching non-dominated solutions. In this paper, to extract a better set of non-dominated solutions, we propose a SPEA-based algorithm for deriving GTSPs with two objective functions. Since the goal of trading is to get profit, the first objective function is utilized to evaluate the return and risk of a candidate GTSP. The second objective function is used to evaluate whether the numbers of strategies between groups are similar and weights of groups as well. Experiments were conducted on a financial dataset to show the effectiveness of the proposed approach and comparison results of the proposed approach and the previous approach.

Data mining is most commonly used in attempts to induce association rules from transaction data. In the past, we used the fuzzy and GA concepts to discover both useful fuzzy association rules and suitable membership functions from quantitative values. The evaluation for fitness values was, however, quite time-consuming. Due to dramatic increases in available computing power and concomitant decreases in computing costs over the last decade, learning or mining by applying parallel processing techniques has become a feasible way to overcome the slow-learning problem. In this paper, we thus propose a parallel genetic-fuzzy mining algorithm based on the master-slave architecture to extract both association rules and membership functions from quantitative transactions. The master processor uses a single population as a simple genetic algorithm does, and distributes the tasks of fitness evaluation to slave processors. The evolutionary processes, such as crossover, mutation and production are performed by the master processor. It is very natural and efficient to run the proposed algorithm on the master-slave architecture. The time complexities for both sequential and parallel genetic-fuzzy mining algorithms have also been analyzed, with results showing the good effect of the proposed one. When the number of generations is large, the speed-up can be nearly linear. The experimental results also show this point. Applying the master-slave parallel architecture to speed up the genetic-fuzzy data mining algorithm is thus a feasible way to overcome the low-speed fitness evaluation problem of the original algorithm. (C) 2013 Elsevier Ltd. All rights reserved.

Many fuzzy data mining approaches have been proposed for finding fuzzy association rules with the predefined minimum support from quantitative transaction databases. Since each item has its own utility, utility itemset mining has become increasingly important. However, common problems with existing approaches are that an appropriate minimum support is difficult to determine and that the derived rules usually expose common-sense knowledge, which may not be interesting from a business point of view. This study thus proposes an algorithm for mining high-coherent-utility fuzzy itemsets to overcome problems with the properties of propositional logic. Quantitative transactions are first transformed into fuzzy sets. Then, the utility of each fuzzy itemset is calculated according to the given external utility table. If the value is larger than or equal to the minimum utility ratio, the itemset is considered as a high-utility fuzzy itemset. Finally, contingency tables are calculated and used for checking whether a high-utility fuzzy itemset satisfies four criteria. If so, it is a high-coherent-utility fuzzy itemset. Experiments on the foodmart and simulated datasets are made to show that the derived itemsets by the proposed algorithm not only can reach better profit than selling them separately, but also can provide fewer but more useful utility itemsets for decision-makers.

In this paper, we discuss the scheduling problem of assigning jobs on multiple parallel machines with mold constraints. The mold constraint specifies that each job needs to be processed with specific molds on a machine and there is an arbitrary amount for each type of molds. Besides, different machines can mount different molds. Setup time is also considered when a first job in a machine starts or when a machine changes molds. A GA-based scheduling algorithm is thus proposed for dealing with the above scheduling problem. Experimental results are also given to verify the effectiveness of the proposed algorithm.

In this paper, a type-2 genetic-fuzzy mining algorithm is proposed for mining a set of type-2 membership functions for mining fuzzy association rules. It first encodes the type-2 membership functions of each item into a chromosome. The quantitative transactions are then transformed into fuzzy values according to the type-2 membership functions. Each chromosome is then evaluated by the number of large 1-itemsets and the suitability factor. The suitability factor consists of three sub-factors - coverage, overlap and difference which are used to avoid three bad types of membership functions. Experiments on a simulated dataset are also conducted to show the effectiveness of the proposed approach.

In this paper, we address a dynamic scheduling problem in real world applications. To deal with it, we extend our previous work by modifying the processes of sorting jobs in mold groups. Moreover, an additional condition is considered which requests the mold for the dynamically inserted jobs is the same as an online mold. A strategy that the inserted jobs are performed on the machine mounted with the mold adaptable for them is used. Finally, a simulation for a real-world scheduling problem is made to show the effectiveness of the proposed approach. © 2013 ICIC International.

In real-world applications, transactions usually consist of quantitative values. Many fuzzy data mining approaches have thus been proposed for finding fuzzy association rules with the predefined minimum support from the give quantitative transactions. However, the common problems of those approaches are that an appropriate minimum support is hard to set, and the derived rules usually expose common-sense knowledge which may not be interesting in business point of view. In this paper, an algorithm for mining fuzzy coherent rules is proposed for overcoming those problems with the properties of propositional logic. It first transforms quantitative transactions into fuzzy sets. Then, those generated fuzzy sets are collected to generate candidate fuzzy coherent rules. Finally, contingency tables are calculated and used for checking those candidate fuzzy coherent rules satisfy the four criteria or not. If yes, it is a fuzzy coherent rule. Experiments on the foodmart dataset are also made to show the effectiveness of the proposed algorithm.

This study proposes a yield-to-maturity (YTM)-based genetic portfolio selection model with user defined constraints, namely YTMGPSM. A set of real numbers are encoded into a chromosome to form a possible portfolio, which presents whether buy or not buy and purchased units of assets. The fitness value of a chromosome is evaluated by return on investment, value at risk and suitability of the respective portfolio. The suitability of a chromosome consists of portfolio penalty and investment capital penalty that are used to reflect the satisfactions of user predefined maximum investment and maximum number of companies, respectively. Experiments on real dataset are made to show the merits of the proposed approach.

In this paper, we propose an algorithm for mining high coherent utility fuzzy itemsets (HCUFI) from quantitative transactions with the properties of propositional logic. It first transforms quantitative transactions into fuzzy sets. Then, utility of each fuzzy itemsets is then calculated according to the given external utility table. If the value is large than or equals to the minimum utility ratio, it will be considered as a High Utility Fuzzy Itemset (HUFI). Finally, contingency tables are calculated and used for checking those HUFI satisfy specific four criteria or not. If yes, it is a High Coherent Utility Fuzzy Itemsets (HCUFI). Experiments on the foodmart dataset are also made to show the effectiveness of the proposed algorithm.

In this paper, we consider the scheduling problems with redundant-molds issue. We will heuristically solve the scheduling problem with tasks needing an arbitrary mold in its specified set of mold types to be performed while the number of each mold type is arbitrary as well and the mold set is independent of the machines. A bio-inspired approach with some greedy mold-selection skills is designed to solve the above problem.

Data mining is most commonly used in attempts to induce association rules from transaction data. Since transactions in real-world applications usually consist of quantitative values, many fuzzy association-rule mining approaches have been proposed on single-or multiple-concept levels. However, the given membership functions may have a critical influence on the final mining results. In this paper, we propose a multiple-level genetic-fuzzy mining algorithm for mining membership functions and fuzzy association rules using multiple-concept levels. It first encodes the membership functions of each item class (category) into a chromosome according to the given taxonomy. The fitness value of each individual is then evaluated by the summation of large 1-itemsets of each item in different concept levels and the suitability of membership functions in the chromosome. After the GA process terminates, a better set of multiple-level fuzzy association rules can then be expected with a more suitable set of membership functions. Experimental results on a simulation dataset also show the effectiveness of the algorithm.

Many fuzzy data mining approaches have been proposed for finding fuzzy association rules with the predefined minimum support from the give quantitative transactions. However, some comment problems of those approaches are that (1) a minimum support should be predefined, and it is hard to set the appropriate one, and (2) the derived rules usually expose common-sense knowledge which may not be interested in business point of view. In this paper, we thus proposed an algorithm for mining fuzzy coherent rules to overcome those problems with the properties of propositional logic. It first transforms quantitative transactions into fuzzy sets. Then, those generated fuzzy sets are collected to generate candidate fuzzy coherent rules. Finally, contingency tables are calculated and used for checking those candidate fuzzy coherent rules satisfy four criteria or not. Experiments on the foodmart dataset are also made to show the effectiveness of the proposed algorithm.

In this paper, we propose a multiple-level genetic-fuzzy mining algorithm for mining membership functions and fuzzy association rule on multiple-concept levels. It first encodes the membership functions of each item class (category) into a chromosome according to the given taxonomy. The fitness value of each individual is then evaluated by the summation of large 1 itemsets of each item in different concept levels and the suitability of membership functions in the chromosome. After the GA process terminates, a better set of multiple-level fuzzy association rules can then be expected with a more suitable set of membership functions. Experimental results on a simulation dataset also show the effectiveness of the algorithm.

In this paper, we use dynamic mutation rates in gene-set genetic algorithms to increase the number of offspring when the gene-set size is large. Experiments on three problems are made to show the effectiveness of the genetic algorithm with dynamic mutation rates. From the experimental results, the proposed algorithm can get better convergence effects than the one with fixed mutation rates and than the simple GA, but spends only a little more computational time.

In this paper, we introduce a fuzzy mining algorithm for discovering generalized association rules with multiple supports of items for extracting implicit knowledge from quantitative transaction data. The proposed algorithm first adopts the fuzzy-set concept to transform quantitative values in transactions into linguistic terms. Besides, each primitive item is given its respective predefined support threshold. The minimum support for an item at a higher taxonomic concept is set as the minimum of the minimum supports of the items belonging to it and the minimum support for an itemset is set as the maximum of the minimum supports of the items contained in the itemset. An example is also given to demonstrate that the proposed mining algorithm can derive the generalized association rules under multiple minimum supports in a simple and effective way.

In wireless sensor networks, minimizing power consumption to prolong network lifetime is very crucial. In the past, Pan et al. proposed two algorithms to find the optimal locations of base stations in two-tiered wireless sensor networks. Their approaches assumed the initial energy and the energy-consumption parameters were the same for all application nodes. If any of the above parameters were not the same, their approaches could not work. Recently, the PSO technique has been widely used in finding nearly optimal solutions for optimization problems. In this paper, an algorithm based on particle swarm optimization (PSO) is thus proposed for general power-consumption constraints. The proposed approach can search for nearly optimal BS locations in heterogeneous sensor networks, where application nodes may own different data transmission rates, initial energies and parameter values. Experimental results also show the good performance of the proposed PSO approach and the effects of the parameters on the results. The proposed algorithm can thus help find good BS locations to reduce power consumption and maximize network lifetime in two-tiered wireless sensor networks.