Towards building an intelligent decision support system for project management

Management of large projects, especially the ones in which a major component of R&D is involved and those requiring knowledge from diverse specialised and sophisticated fields, may be classified as semi-structured problems. In these problems, there is some knowledge about the nature of the work involved, but there are also uncertainties associated with emerging technologies. In order to draw up a plan and schedule of activities of such a large and complex project, the project manager is faced with a host of complex decisions that he has to take, such as, when to start an activity, for how long the activity is likely to continue, etc. An Intelligent Decision Support System (IDSS) which aids the manager in decision making and drawing up a feasible schedule of activities while taking into consideration the constraints of resources and time, will have a considerable impact on the efficient management of the project. This report discusses the design of an IDSS that helps in project planning phase through the scheduling phase. The IDSS uses a new project scheduling tool, the Project Influence Graph (PIG).     

火电厂智能化远程管理云平台系统设计

为优化火力发电的生产,解决传统服务器在存储和挖掘大数据能力上的不足,该文采用云存储和云计算技术,将爆发式增长的火电机组生产数据存储在云端,通过对云端数据库的访问,搭建在线的火电厂远程管理平台,对生产数据进行远程监督和规范化存储。智能化云平台系统通过果蝇算法优化的广义回归神经网络(FOA-GRNN),设计一种锅炉热效率实时软测量模型。通过实验验证,云平台相比于传统服务器,在保证预测精度的前提下,有着更加高效的数据处理能力。     

Efficient classification of chronic kidney disease by using multi-kernel support vector machine and fruit fly optimization algorithm

In recent days, the gigantic generation of medical data from smart healthcare applications requires the development of big data classification methodologies. Medical data classification can be utilized for visualizing the hidden patterns and finding the presence of disease from the medical data. In this article, we present an efficient multi-kernel support vector machine (MKSVM) and fruit fly optimization algorithm (FFOA) for disease classification. Initially, FFOA is employed to choose the finest features from the available set of features. The selected features from the medical dataset are processed and provided to the MKSVM for medical data classification purposes. The proposed chronic kidney disease (CKD) classification method has been simulated in MATLAB. Next, testing of the dataset takes place using the own benchmark CKD dataset from UCI machine learning repositories such as Kidney chronic, Cleveland, Hungarian, and Switzerland. The performance of the proposed CKD classification method is elected by accuracy, sensitivity, specificity, positive predictive value, negative predictive value, false positive rate, and false negative rate. The investigational outcome specifies that the proposed CKD classification method achieves maximum classification precision value of 98.5% for chronic kidney dataset, 90.42904% for Cleveland, 89.11565% for Hungarian, and 86.17886% for Switzerland dataset than existing hybrid kernel SVM, fuzzy min-max GSO neural network, and SVM methods.     

An architecture for IoT-enabled intelligent process-aware cloud production platform: a case study in a networked cloud clinical laboratory

Cloud production is an emerging paradigm that supports co-designing and co-producing integrated solutions with customers. The realisation of this paradigm requires integrated platforms that enable parties collaborating within a production ecosystem to inter-operate networked business processes. Previous research has proposed different architectures for cloud production platforms from different perspectives like virtualiseng and servitiseng manufacturing resources, distributed and networked sensing supported by IoT technologies, and service-oriented and process-centred computing to compose and enact networked production services. However, an integrated architecture that brings together insights from service-oriented cloud manufacturing, IoT-enabled intelligence, and networked process-centred service composition and enactment has not been sufficiently addressed in previous research. In order to incorporate insights from the mentioned different perspectives, in this paper architectural analysis, synthesis, and evaluation steps are conducted to propose a conceptual architecture for IoT-enabled intelligent process-aware cloud production platforms. This architecture describes design-time and run-time components of a cloud production platform that can sense and intelligently respond to events within a value network. To evaluate the applicability of the proposed architecture within real-life scenarios, a case study is conducted in a cloud clinical laboratory in Tehran, Iran. Within this case study, a concrete cloud clinical laboratory platform has been instantiated.     

Design and development of an intelligent context-aware decision support system for real-time monitoring of container terminal operations

This paper describes a case study of the research and development of an intelligent context-aware decision support system (ICADSS) prototype for real-time monitoring of container terminal operations in Hong Kong. We present the system design and development of the prototype system, and discuss the experiences and lessons learned. To the best of our knowledge, this study is the first identifiable application of an intelligent context-aware decision support system for the real-time monitoring of container terminal operations reported in the academic literature. The intelligent context-aware decision support system employs ZigBee-based ubiquitous sensor network (USN) technology. In this study, an ICADSS prototype was built and implemented in a real world setting. The results of the system prototype evaluation are satisfactory and support the contention that it is more effective in supporting the real-time tracking and tracing of container trucks, quay cranes, and rubber-tired gantry cranes in a container terminal. The results also validate the practical viability of the proposed system architecture. Given the contextual details of the study, we present the lessons learned from developing and operating the system in a container terminal and provide suggestions for further research. We hope that the proposed system architecture and developed prototype system can help both practitioners and academics in the further use and research of intelligent context-aware decision support systems.     

An optimization based decision support system for integrated planning and scheduling on dedicated freight corridors

Empty wagon redistribution, train formation, routing and scheduling are complex problems for large railways, many of which currently have or are planning dedicated freight railway corridors (DFC). DFC operations due to their unique characteristics require research and new models for better operations planning. The rolling-stock, being expensive assets, need to be utilised in an optimal manner while meeting service quality levels. Motivated by Indian DFC, we present an integer programming formulation of the dynamic problem of empty distribution and train scheduling in DFC and discuss associated modelling issues. By unifying the separate problems into a single and dynamic model, we have developed a framework for more effective rolling stock utilisation. Based on this optimization model, an interactive decision support system is proposed for better decision-making on rolling-stock allocation and train scheduling. Extensive experiments and systematic analyses for a case of Indian DFC highlight the potentialities and effectiveness of the proposed DSS for DFC operations planning and management.     

An intelligent mining system for diagnosing medical images using combined texture‐histogram features

The aim of this article is to design an expert system for medical image diagnosis. We propose a method based on association rule mining combined with classification technique to enhance the diagnosis of medical images. This system classifies the images into two categories namely benign and malignant. In the proposed work, association rules are extracted for the selected features using an algorithm called AprioriTidImage, which is an improved version of Apriori algorithm. Then, a new associative classifier CLASS_Hiconst ( CL assifier based on ASS ociation rules with Hi gh Con fidence and S uppor t ) is modeled and used to diagnose the medical images. The performance of our approach is compared with two different classifiers Fuzzy‐SVM and multilayer back propagation neural network (MLPNN) in terms of classifier efficiency with sensitivity, specificity, accuracy, positive predictive value, and negative predictive value. The experimental result shows 96% accuracy, 97% sensitivity, and 96% specificity and proves that association rule based classifier is a powerful tool in assisting the diagnosing process. © 2013 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 23, 194–203, 2013     

Maximum conservative management for patients with chronic kidney disease stage 5

Following the expansion of dialysis services for patients with chronic kidney disease, an increasing number of elderly patients with varying degrees of frailty and additional comorbidities have been offered treatment. Life expectancy is somewhat limited in this group of patients, and initiation of dialysis may not necessarily improve quality of life. As such, an increasing number of centers are offering conservative care for patients who have made an informed decision not to have dialysis. As conservative care includes active treatment of anemia, volume overload, blood pressure control, and management of uremic symptoms, including pruritus, we term this approach as maximal conservative management of chronic kidney disease. We describe our experience of maximum conservative management, which although may not prolong life, can maintain the quality of life and functional ability until the final illness in the majority of patients. Although these patients do not go to the hospital on a regular basis, coordinated support from the hospital, the community, and the care giver/relative is required for successful care of the patient. Appropriate end of life planning can then be made according to the wishes of the patient.     

An integrated probabilistic risk analysis decision support methodology for systems with multiple state variables

Probabilistic risk analysis (PRA) methods have been proven to be valuable in risk and reliability analysis. However, a weak link seems to exist between methods for analysing risks and those for making rational decisions. The integrated decision support system (IDSS) methodology presented in this paper attempts to address this issue in a practical manner. In consists of three phases: a PRA phase, a risk sensitivity analysis (SA) phase and an optimisation phase, which are implemented through an integrated computer software system. In the risk analysis phase the problem is analysed by the Boolean representation method (BRM), a PRA method that can deal with systems with multiple state variables and feedback loops. In the second phase the results obtained from the BRM are utilised directly to perform importance and risk SA. In the third phase, the problem is formulated as a multiple objective decision making problem in the form of multiple objective reliability optimisation. An industrial example is included. The resultant solutions of a five objective reliability optimisation are presented, on the basis of which rational decision making can be explored.     

Intelligent decision support system for the adaptive control of a flexible manufacturing system with machine and tool flexibility

This paper describes an intelligent decision support system (IDSS) for real time control of a flexible manufacturing system (FMS). The controller is capable of classifying symptoms in developing the control policies on FMSs with flexibility in operation assignment and scheduling of multi-purpose machining centres which have different tools with their own efficiency. The proposed system is implemented by coupling of rule-based IDSS, simulation block and centralised simulation optimiser for elicitation of shop floor control knowledge. This posteriori adaptive controller uses a new bilateral mechanism in simulation optimiser block for offline training of IDSS based on multi-performance criteria simulation optimisation. The proposed intelligent controller receives online information of the FMS current state and trigger appropriate control rule within real-time simulation data exchange. Finally the FMS intelligent controller is validated by a benchmark test problem. Application of this adaptive controller showed that it could be an effective approach for real time control of various flexible manufacturing systems.     

An integrated decision support system for strategic supply chain optimisation in process industries: the case of a zinc company

We introduce a menu-driven user-friendly decision support system (DSS) for supply chain planning based on optimisation. The DSS is based on a multi-source (supplier), multi-destination (warehouse) network having multiple manufacturing facilities, with multiple materials and multiple storage areas. This integrated supply chain model performs multiple period planning. The use of this DSS requires little knowledge of management sciences tools. We discuss the need for an integrated approach towards supply chain modelling for the process industry. We present the integrated model in the form of a database structure. We validate the model with the real data of a zinc company and demonstrate the impact of optimisation in terms of percentage improvement. The result shows that it is possible to improve unit contribution to profit from 1.89 to 4.66%.     

Anti‐thrombotic therapy for atrial fibrillation in patients with chronic kidney disease: Current views

Chronic kidney disease (CKD) occurs in approximately one‐third of patients with non‐valvular atrial fibrillation (AF). The presence of CKD, particularly advanced CKD, confers increased risk of both thromboembolism and major bleeding in this group of patients who are already at risk for ischemic stroke and systemic embolism and at risk of bleeding due to anticoagulation. Studies assessing the effect of warfarin on risk of ischemic stroke, systemic embolism, and major bleeding have produced disparate results, particularly in patients with advanced CKD including those treated with hemodialysis. The direct oral anticoagulants (DOAC's) have been studied in patients with stage III (moderate) CKD and appear to be as effective or more effective (dabigatran 150 mg twice daily) than warfarin in preventing ischemic stroke or embolism in this group. Two of the DOAC's, apixaban and edoxaban, confer lower risk of major bleeding than warfarin with appropriate dose adjustments. Substantial gaps exist in our knowledge of anti‐thrombotic therapy in patients with AF and CKD, primarily due to exclusion of patients with advanced CKD from randomized controlled trials comparing DOAC's with warfarin.     

Late acceleration of glomerular filtration rate decline is a risk for hemodialysis catheter use in patients with established nephrology chronic kidney disease care

Chronic kidney disease (CKD) patients with established nephrology care have a high rate of tunneled dialysis catheters (TDC) as first vascular access when transitioning to hemodialysis (HD). We sought to identify factors associated with this problem. Patients who started HD and had prior CKD care within our renal clinic were categorized according to access type at incident HD. Clinical factors, all estimated glomerular filtration rates (eGFR), renal clinic attendance records, hospital admissions in the 6 months preceding HD start, and patient participation in predialysis education course were analyzed. Three hundred thirty‐eight patients initiated HD, 107 received pre‐HD CKD care within our clinics. Seventy patients started with a TDC. All groups started HD at similar eGFR values. The trajectory of eGFR decline in the 6 months prior to HD start was significantly more rapid in the TDC group. Patients in the TDC group had more acute health events in the prior 6 months. Multivariate modeling showed that failure to attend a predialysis education course and having a more rapid rate of eGFR decline in the 6 months prior to dialysis initiation were both associated with TDC use. Patients with CKD nephrology care who initiated HD with a TDC as first vascular access had a more rapid rate of decline in eGFR in the months preceding dialysis start and were less likely to have attended our predialysis education course. This appears to correspond with the observed increased number of emergency and hospital visits in the 6 months prior to end‐stage renal disease.