This page has only limited features, please log in for full access.
Though American sign language (ASL) has gained recognition from the American society, few ASL applications have been developed with educational purposes. Those designed with real-time sign recognition systems are also lacking. Leap motion controller facilitates the real-time and accurate recognition of ASL signs. It allows an opportunity for designing a learning application with a real-time sign recognition system that seeks to improve the effectiveness of ASL learning. The project proposes an ASL learning application prototype. The application would be a whack-a-mole game with a real-time sign recognition system embedded. Since both static and dynamic signs (J, Z) exist in ASL alphabets, Long-Short Term Memory Recurrent Neural Network with k-Nearest-Neighbour method is adopted as the classification method is based on handling of sequences of input. Characteristics such as sphere radius, angles between fingers and distance between finger positions are extracted as input for the classification model. The model is trained with 2600 samples, 100 samples taken for each alphabet. The experimental results revealed that the recognition rate for 26 ASL alphabets yields an average of 99.44% accuracy rate and 91.82% in 5-fold cross-validation with the use of leap motion controller.
C.K.M. Lee; Kam K.H. Ng; Chun-Hsien Chen; H.C.W. Lau; S.Y. Chung; Tiffany Tsoi. American sign language recognition and training method with recurrent neural network. Expert Systems with Applications 2020, 167, 114403 .
AMA StyleC.K.M. Lee, Kam K.H. Ng, Chun-Hsien Chen, H.C.W. Lau, S.Y. Chung, Tiffany Tsoi. American sign language recognition and training method with recurrent neural network. Expert Systems with Applications. 2020; 167 ():114403.
Chicago/Turabian StyleC.K.M. Lee; Kam K.H. Ng; Chun-Hsien Chen; H.C.W. Lau; S.Y. Chung; Tiffany Tsoi. 2020. "American sign language recognition and training method with recurrent neural network." Expert Systems with Applications 167, no. : 114403.
With the increasing use of emergency departments, many public hospitals experience bottlenecks that hinder patient flow within the health system. Mitigating bottlenecks can enhance workflow efficiency and reduce patient wait‐time. Yet given the complexity of health services, current techniques have a limited capacity to address this issue. This article introduces an innovative generic cost‐optimization model based on genetic algorithm to alleviate bottlenecks without the need for complex mathematical analysis. A case study is presented to validate its feasibility, demonstrating an evidence‐based, pragmatic way to alleviate bottlenecks that practitioners can readily implement.
Henry Lau; Ann Dadich; Dilupa Nakandala; Huntley Evans; Li Zhao. Development of a cost-optimization model to reduce bottlenecks: A health service case study. Expert Systems 2018, 35, e12294 .
AMA StyleHenry Lau, Ann Dadich, Dilupa Nakandala, Huntley Evans, Li Zhao. Development of a cost-optimization model to reduce bottlenecks: A health service case study. Expert Systems. 2018; 35 (6):e12294.
Chicago/Turabian StyleHenry Lau; Ann Dadich; Dilupa Nakandala; Huntley Evans; Li Zhao. 2018. "Development of a cost-optimization model to reduce bottlenecks: A health service case study." Expert Systems 35, no. 6: e12294.
For enterprises, it is imperative that the trade-off between the cost of inventory and risk implications is managed in the most efficient manner. To explore this, we use the common example of a wholesaler operating in an environment where suppliers demonstrate heterogeneous reliability. The wholesaler has partial orders with dual suppliers and uses lateral transshipments. While supplier reliability is a key concern in inventory management, reliable suppliers are more expensive and investment in strategic approaches that improve supplier performance carries a high cost. Here we consider the operational strategy of dual sourcing with reliable and unreliable suppliers and model the total inventory cost where the likely scenario lead-time of the unreliable suppliers extends beyond the scheduling period. We then develop a Customized Integer Programming Optimization Model to determine the optimum size of partial orders with multiple suppliers. In addition to the objective of total cost optimization, this study takes into account the volatility of the cost associated with the uncertainty of an inventory system.
Dilupa Nakandala; Henry Lau; Jingjing Zhang; Angappa Gunasekaran. A pragmatic decision model for inventory management with heterogeneous suppliers. Enterprise Information Systems 2018, 12, 603 -619.
AMA StyleDilupa Nakandala, Henry Lau, Jingjing Zhang, Angappa Gunasekaran. A pragmatic decision model for inventory management with heterogeneous suppliers. Enterprise Information Systems. 2018; 12 (5):603-619.
Chicago/Turabian StyleDilupa Nakandala; Henry Lau; Jingjing Zhang; Angappa Gunasekaran. 2018. "A pragmatic decision model for inventory management with heterogeneous suppliers." Enterprise Information Systems 12, no. 5: 603-619.
Since inventory costs account for half of logistics costs, optimal inventory management to minimise total inventory costs remains a sustainable competitive advantage. Lateral transshipment (LT) is evidently a proven strategy to minimise total inventory costs. The additional LT costs are more than compensated by lowering the stock-out costs. Previous LT models have not been applied to perishable products. Our proposed LT model embodies spoilage costs in the total inventory costs function with the other cost components (purchase from a regular supplier, LT, backordering and holding), and optimises the trade-off among these five key cost components. Numerical examples from a supermarket chain case study demonstrate that, as compared against the no or lower spoilage costs scenarios, lower LT costs are required to trigger the decision point for implementing LT in the higher spoilage costs scenario. However, common to both the with and without spoilage costs scenarios, LT is still the preferred strategy to minimise total inventory costs, given the decision rules are satisfied.
Dilupa Nakandala; Henry Lau; Paul K.C. Shum. A lateral transshipment model for perishable inventory management. International Journal of Production Research 2017, 55, 5341 -5354.
AMA StyleDilupa Nakandala, Henry Lau, Paul K.C. Shum. A lateral transshipment model for perishable inventory management. International Journal of Production Research. 2017; 55 (18):5341-5354.
Chicago/Turabian StyleDilupa Nakandala; Henry Lau; Paul K.C. Shum. 2017. "A lateral transshipment model for perishable inventory management." International Journal of Production Research 55, no. 18: 5341-5354.
Purpose – Strategic analysis of customer profitability for assessing market segmentation and reconfiguring customer relationship management (CRM) activities remains the key factor for achieving high return on CRM investment. The purpose of this paper is to map the profit-based ranking of corporate customers into the current market segments, with a view of determining the relative profitability of each market segment. Design/methodology/approach – This study develops a novel model that combines activity-based costing (ABC), CRM, fuzzy analytic hierarchy process (AHP), and technique for order preference by similarity to ideal solution (TOPSIS) methods to evaluate strategically customer profitability and prioritizing corporate accounts. This case study airline company has invested heavily in CRM over the past seven years on integrating multi-functional departments that touch customers. The airline operations management and marketing functions provide key inputs. Results of the hybrid model validate feasibility of the proposed model. Findings – The airline management makes use of the ranking results to optimize customer profitability by reconfiguring marketing programs, integrated schedule design, fleet assignment, maintenance routing, crew scheduling, and real-time optimization of schedule recovery in the aftermath of disruptions or irregularities. The proposed model also directs the marketing function to customize service offerings and introduce appropriate service levels to engage customers of different segments for the purpose of maximizing corporate profitability. Research limitations/implications – Significant amount of investment is necessary to design and implement the extensive CRM database and systems to assure customer data quality and availability so as to bear fruits in the proposed hybrid model. These data requirements can especially be a critical barrier for small to medium-sized companies. Practical implications – This hybrid model is able to capitalize on the benefits of the ABC, CRM, fuzzy AHP, and TOPSIS methods and offset their deficiencies. Most importantly, it can be applied to various industries without complex modification. Originality/value – This study represents the first move to adopt the fuzzy AHP and TOPSIS methods to analyze the ABC and CRM data inputs of an airline company. In mapping the profit-based ranking of corporate customers into the current market segments, the relative profitability of each market segment can be determined.
Henry Lau; Dilupa Nakandala; Premaratne Samaranayake; Paul Shum. A hybrid multi-criteria decision model for supporting customer-focused profitability analysis. Industrial Management & Data Systems 2016, 116, 1105 -1130.
AMA StyleHenry Lau, Dilupa Nakandala, Premaratne Samaranayake, Paul Shum. A hybrid multi-criteria decision model for supporting customer-focused profitability analysis. Industrial Management & Data Systems. 2016; 116 (6):1105-1130.
Chicago/Turabian StyleHenry Lau; Dilupa Nakandala; Premaratne Samaranayake; Paul Shum. 2016. "A hybrid multi-criteria decision model for supporting customer-focused profitability analysis." Industrial Management & Data Systems 116, no. 6: 1105-1130.
This paper demonstrates how a fuzzy analytic hierarchy process approach can be used to determine technology management strategies for firms in partnerships that result in their sustained technological development. Firms with resource constraints tend to form venture partnerships with technologically advanced partners for indirect strategic benefits. In such partnerships, technology management strategies of host firms need to be manoeuvred strategically as they build local capabilities. Selection of technology management strategy is generally based on subjective judgements that use fuzzy data analysed under multiple decision criteria. Considering the degree of technological contribution from the source firm, technological competency of the host firm, and dominance of the partners as well as the clarity of roles between partners as decision factors, this paper demonstrates how to determine the optimal technology management strategy. The different technological stages of a real firm are analysed in order to illustrate the application of the proposed approach.
Dilupa Nakandala; Henry Lau. A technology management strategy selection method for firms in joint venture partnerships. International Journal of Management and Decision Making 2015, 14, 112 .
AMA StyleDilupa Nakandala, Henry Lau. A technology management strategy selection method for firms in joint venture partnerships. International Journal of Management and Decision Making. 2015; 14 (2):112.
Chicago/Turabian StyleDilupa Nakandala; Henry Lau. 2015. "A technology management strategy selection method for firms in joint venture partnerships." International Journal of Management and Decision Making 14, no. 2: 112.
Purpose – The purpose of this paper is to investigate the total cost function of an inventory system with a reorder point/order quantity policy where the lead time is controllable based on the cost paid by the buyer for the service. Design/methodology/approach – Cost functions are presented to investigate how the changes in lead time affect different components of inventory cost in the present of random demand. Two methods including an iteration technique and Simulated Annealing (SA) algorithm are presented to deal with the cost optimization issue. The application of proposed model is illustrated using numerical case scenarios. Findings – The cost functions show that besides ordering cost, change in stochastic demand during lead time is the major factor that affects the other cost components such as holding and penalty costs. This finding is validated by numerical study. Results also show that performance of SA algorithm is highly similar to iteration methodology, while the former one is easier in application. Practical implications – This paper develops less complex, more pragmatic methods, easily adoptable by logistics managers for cost minimization. This paper also analyzes and highlights the unique characteristics and features of these two approaches that can help practitioners in making the right choice when faced with the identified logistics issue. Originality/value – This research explicitly investigate impacts of changing lead time on inventory cost components which enables informed decision making and inventory system planning for cost optimization by logistics practitioners. Two methodologies that can be easily used by practitioners without deep mathematical analysis and is cost effective are introduced to solve the optimization problem. Detailed roadmaps of how to implement proposed approaches have been illustrated by different case scenarios.
Dilupa Nakandala; Henry Lau; Jingjing Zhang. Optimization model for transportation planning with demand uncertainties. Industrial Management & Data Systems 2014, 114, 1229 -1245.
AMA StyleDilupa Nakandala, Henry Lau, Jingjing Zhang. Optimization model for transportation planning with demand uncertainties. Industrial Management & Data Systems. 2014; 114 (8):1229-1245.
Chicago/Turabian StyleDilupa Nakandala; Henry Lau; Jingjing Zhang. 2014. "Optimization model for transportation planning with demand uncertainties." Industrial Management & Data Systems 114, no. 8: 1229-1245.