International Journal of Information Technology & Decision Making

Fuzzy set theory has attracted many researchers’ interests and many efficient variants have been implemented in support system, decision-making and other fields. Inspired by the idea of variable weight analysis, in this study, we investigate state variable weight vector and its properties, propose two kinds of variable weight aggregation operators such as variable weight averaging (VWA) operator and variable weight geometric (VWG) operator based on three types of fuzzy attribute values. Finally, we apply in ship evaluation and economy collaboration evaluation tasks and make comparison analysis to illustrate the effectiveness of our proposed technique.

Lung cancer is known to be one of the leading causes of death worldwide. There is a chance of increasing the survival rate of the patients if detected at an early stage. Computed Tomography (CT) scans are prominently used to detect and classify lung cancer nodules/tumors in the thoracic region. There is a need to develop an efficient and reliable computer-aided diagnosis model to detect lung cancer nodules accurately from CT scans. This work proposes a novel kernel-based active-contour (KAC) SegNet deep learning model to perform lung cancer nodule detection from CT scans. The active contour uses a snake method to detect internal and external boundaries of the curves, which is used to extract the Region Of Interest (ROI) from the CT scan. From the extracted ROI, the nodules are further classified into benign and malignant using a Dense AlexNet deep learning model. The key contributions of this work are the fusion of an edge detection method with a deep learning segmentation method which provides enhanced lung nodule segmentation performance, and an ensemble of state-of-the-art deep learning classifiers, which encashes the advantages of both DenseNet and AlexNet to learn better discriminative information from the detected lung nodules. The experimental outcome shows that the proposed segmentation approach achieves a Dice Score Coefficient of 97.8% and an Intersection-over-Union of 92.96%. The classification performance resulted in an accuracy of 95.65%, a False Positive Rate, and False Negative Rate values of 0.0572 and 0.0289. The proposed model is robust compared to the existing state-of-the-art methods.

Predicting software defects is an important task during software testing phase, especially for allocating appropriate resources and prioritizing testing tasks. Typically, classification algorithms are used to accomplish this task by using previously collected datasets. However, these datasets suffer from imbalanced label distribution where clean modules outnumber defective modules. Traditional classification algorithms cannot handle this nature in defect datasets because they assume the datasets are balanced. Failing to address this problem, the classification algorithm will produce a prediction biased towards the majority label. In the literature, there are several techniques designed to address this problem and most of them focus on data re-balancing. Recently, ensemble class imbalance techniques have emerged as an opposing approach to data rebalancing approaches. Regarding the software defect prediction, there are no studies examining the performance of ensemble class imbalance learning against data re-balancing approaches. This paper investigates the efficiency of ensemble class imbalance learning for software defect prediction. We conducted a comprehensive experiment that involved 12 datasets, six classifiers, nine class imbalance techniques, and 10 evaluation metrics. The experiments showed that ensemble approaches, particularly the Under Bagging technique, outperform traditional data re-balancing approaches, particularly when dealing with datasets that have high defect ratios.

With Company2Vec, the paper proposes a novel application in representation learning. The model analyzes business activities from unstructured company website data using Word2Vec and dimensionality reduction. Company2Vec maintains semantic language structures and thus creates efficient company embeddings in fine-granular industries. These semantic embeddings can be used for various applications in banking.

Direct relations between companies and words allow semantic business analytics (e.g., top-n words for a company). Furthermore, industry prediction is presented as a supervised learning application and evaluation method. The vectorized structure of the embeddings allows measuring companies’ similarities with the cosine distance. Company2Vec hence offers a more fine-grained comparison of companies than the standard industry labels (NACE). This property is relevant for unsupervised learning tasks, such as clustering. An alternative industry segmentation is shown with k-means clustering on the company embeddings. Finally, this paper proposes three algorithms for (1) firm-centric, (2) industry-centric and (3) portfolio-centric peer-firm identification.

Recent advances in Internet technology have shifted the focus of end-users from the usage of traditional mobile applications to the Internet of Things (IoT)-based service-oriented smart applications (SAs). These SAs use edge devices to obtain different types of Fog services and provide their real-time response to the end-users. The Fog computing environment extends its services to the edge network layer and hosts SAs that require low latency. Further, a growing number of latency-aware SAs imposes the issue of effective allocation of resources in the Fog environment. In this paper, we have proposed an effective multi-criteria decision-making (MCDM) based solution for resource ranking and resource allocation in the Fog environment. The Proposed algorithms implement the modified edition of the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) and Analytical Hierarchical Process (AHP) and consider Quality of Experience parameters (QoE), i.e., network bandwidth, average latency, and cores for ranking and mapping of resources. The obtained results reveal that the proposed approach utilizes 70% resources, and reduces the response time by an average of 7.5s as compared to the Cloud model and the Fog model, respectively. Similarly, the completion time of the proposed framework is minimum in comparison with the cloud and Fog models with a difference of 9s and 16s.

The exponentially increasing amount of data generated by the public on social media platforms is a precious source of information. It can be used to find the topics and analyze the comments. Some researchers have extended the Latent Dirichlet Allocation (LDA) method by adding a sentiment layer to simultaneously find the topics and their related sentiments. However, most of these approaches do not achieve admirable accuracy in Topic Sentiment Analysis (TSA), particularly when there is insufficient training data or the texts are complex, ambiguous, and short. In this paper, a self-supervised novel approach called SSTSA is proposed for TSA that extracts the hidden topics and analyzes the total sentiment related to each topic. The SSTSA proposes a new method called Pseudo-label Generator. For this purpose, first, it employs semantic similarity and Word Mover’s Distance (WMD) measures. Then, the document embedding technique is employed to semantically estimate the sentiment orientation of samples and generate the pseudo-labels (positive or negative). Afterward, a hybrid classifier composed of a pre-trained Robustly Optimized BERT (RoBERTa) and a Long Short-Term Memory (LSTM) model is trained to predict the sentiment of unseen data. The evaluation results on different datasets of various domains demonstrate that the SSTSA outperforms similar unsupervised/self-supervised methods.

The transit-oriented development (TOD) and arts and culture-led urban development (AUD) have been evolved as two of primary strategies for sustainable urban revitalization. Ex-ante sustainability evaluation has emerged as a crucial procedure in the field of urban renewal to prevent non-sustainable redevelopment projects. However, in the ex-ante evaluation of urban renewal projects, TOD and AUD have ambiguous indicators, imprecise weights, and undetermined evaluation methodologies. To fill these gaps, this work combines GIS, fuzzy theory, and decision-making trial and evaluation laboratory (DEMATEL) to build an ex-ante evaluation model for evaluating the sustainability potential of urban renewal projects. Three areas in Guangzhou that are undergoing reconstruction and development are used as empirical instances in this study. This study provides a hierarchical structure of the evaluation framework which contains three dimensions, five criteria, and twenty-seven indicators, and also obtains the influential relationships among five criteria. In the empirical scenario, the Guangzhou Steel New Town area (GSNT) is reflected in the large potential benefits in both directions (i.e., TOD and AUD). In contrast, the existing urban renewal development plan does not adequately utilize the potential of the Shiqiao (SQ) area. This study, therefore, proposes that to increase land-use efficiency and subsequently economic development, the SQ area should either start from the current conditions or adapt its current strategy to renewal. With the help of this study, local decision-makers may examine the viability of urban renewal initiatives and gauge the possibility for three crucial Guangzhou urban renewal areas to flourish sustainably. This study also offers a decision-base for prospective future improvement in response to the evaluation outcomes.

Last-mile logistics poses a pivotal challenge for the sustainable prosperity of fresh food e-commerce. However, there has been insufficient research attention towards optimizing the last-mile vehicle routing from three sustainable dimensions simultaneously based on triple-bottom-line. To narrow this gap, this paper proposes a multi-objective last-mile vehicle routing model for fresh food e-commerce, which takes the three sustainable dimensions as independent objectives. The economic and environment objectives are minimizing the total cost and carbon emission, respectively. For social dimension, a nonlinear function is proposed based on the Prospect theory, which quantifies customers’ satisfaction when they perceive delivery time. Then the social objective is described as maximizing customers’ satisfaction. Subsequently, the model is solved by the nondominated sorting genetic algorithm II and validated by a numerical experiment. Based on the experiment results, this paper recommends that logistics enterprises should prioritize the trade-off among the three sustainable dimensions.

The rapid development of the transportation industry benefits from the consumption of energy, but the excessive dependence on petroleum fuels makes it a major source of air pollution. In order to achieve green and high-quality development of the transportation industry, many countries are committed to scientifically evaluating the utilization efficiency of clean energy, which has attracted wide attention from the whole society. Significantly, without considering the diversity and complexity of pollutants, indicators used in previous studies were unable to cover all pollutants when establishing the evaluation index system. Meanwhile, as an efficient tool, data envelopment analysis (DEA) is extensively used when it comes to efficiency evaluation. However, the absolute preference of existing benevolent and aggressive cross-efficiency models limits its application scenarios. To address the challenges above, an improved flexible cross-efficiency DEA model is proposed considering both same and different benevolence coefficients of decision-making units (DMUs) on the basis of pointing out the inadequacy of the previous model. The concepts of consensus coefficient and group preference are introduced in the aggregation of cross-efficiency. Besides, based on the theory of undesirable output, the consumption of nonclean energy is taken into account as the input indicator to characterize the degree of pollution. The results show that the obtained cross-efficiency value and efficiency ranking of clean transportation energy change sensitively under various benevolent coefficients. There is an important practical significance to consider the independent preference information of DMUs for the evaluation and ranking of cross-efficiency.

In August 2015, the State Council of the People’s Republic of China listed China’s capital market for property-rights exchange as the capital market along with the Chinese stock market. Consequently, China’s capital market for property-rights exchange is an integral part of the country’s multilayered capital market. The COVID-19 pandemic has had significant effects on the capital markets. Since China’s capital market for property-rights exchange mainly serves nonlisted companies, it is complicated to obtain its exchange data to perform COVID-19’s effect analysis. This study investigates COVID-19’s effect on China’s capital market for property-rights exchange. In this paper, we collected the online property rights-exchange data from 2017 to 2020 of an electric trading platform. The functional principal component analysis method is innovatively introduced to explore the online property rights-exchange fluctuation to get an insight into COVID-19’s effect on China’s capital market for property-rights exchange. Based on the principal component scores, COVID-19’s effect on different property rights-exchange institutions are divided into two categories using principal component clustering. A time-series model is used to quantify the effects in the two categories. The research results finally show that online property rights-exchange can reduce the negative effect of COVID-19 on China’s capital market for property-rights exchange, which encourages property rights-exchange institutions to accelerate the use of the online platform to overcome the challenges of the pandemic.