Adaptive Management of Multimodal Biometrics—A Deep Learning and Metaheuristic Approach
مدیریت تطبیقی بیومتریک چند حالته - یادگیری عمیق و رویکرد فرا مکاشفه ای-2021
This paper introduces the framework for adaptive rank-level biometric fusion: a new approach towards personal authentication. In this work, a novel attempt has been made to identify the optimal design parameters and framework of a multibiometric system, where the chosen biometric traits are subjected to rank-level fusion. Optimal fusion parameters depend upon the security level demanded by a particular biometric application. The proposed framework makes use of a metaheuristic approach towards adaptive fusion in the pursuit of achieving optimal fusion results at varying levels of security. Rank-level fusion rules have been employed to provide optimum performance by making use of Ant Colony Optimization technique. The novelty of the reported work also lies in the fact that the proposed design engages three biometric traits simultaneously for the first time in the domain of adaptive fusion, so as to test the efficacy of the system in selecting the optimal set of biometric traits from a given set. Literature reveals the unique biometric characteristics of the fingernail plate, which have been exploited in this work for the rigorous experimentation conducted. Index, middle and ring fingernail plates have been taken into consideration, and deep learning feature-sets of the three nail plates have been extracted using three customized pre-trained models, AlexNet, ResNet-18 and DenseNet-201. The adaptive multimodal performance of the three nail plates has also been checked using the already existing methods of adaptive fusion designed for addressing fusion at the score-level and decision- level. Exhaustive experiments have been conducted on the MATLAB R2019a platform using the Deep Learning Toolbox. When the cost of false acceptance is 1.9, experimental results obtained from the proposed framework give values of the average of the minimum weighted error rate as low as 0.0115, 0.0097 and 0.0101 for the AlexNet, ResNet-18 and DenseNet-201 based experiments respectively. Results demonstrate that the proposed system is capable of computing the optimal parameters for rank-level fusion for varying security levels, thus contributing towards optimal performance accuracy.© 2021 Elsevier B.V. All rights reserved.
Keywords: Adaptive Biometric Fusion | Ant Colony Optimization | Deep Learning | Fingernail Plate | Multimodal Biometrics | Rank-level Adaptive Fusion
A multi-objective fuzzy robust stochastic model for designing a sustainable-resilient-responsive supply chain network
یک مدل تصادفی محکم فازی چند هدفه برای طراحی یک شبکه زنجیره تأمین پایدار ، قابل انعطاف و پاسخگو-2021
This study proposes a multi-objective mixed-integer programming model to configure a sustainable supply chain network while considering resilience and responsiveness measures. The model aims at minimizing the total costs and environmental damages while maximizing the social impacts, as well as the responsiveness and resilience levels of the supply chain network. An improved version of the fuzzy robust stochastic optimization approach is proposed to tackle the uncertain data arising in the dynamic business environment. Furthermore, a new version of meta-goal programming named the multi-choice meta-goal programming associated with a utility function is developed to solve the resulting multi-objective model. A case study in the water heater industry is investigated to illustrate the application of the proposed model and its solution approach. The numerical results validate the proposed model and the developed solution method. Finally, interactions between the sustainability, responsiveness, and resilience dimensions are investigated and several sensitivity analyses are performed on critical parameters by which useful managerial insights are provided.
Keywords: Supply chain network design | Sustainability | Resilience | Responsiveness | Fuzzy robust stochastic optimization | Multi-choice meta-goal programming
Conceptual MINLP approach to the development of a CO2 supply chain network – Simultaneous consideration of capture and utilization process flowsheets
رویکرد مفهومی MINLP برای توسعه یک شبکه زنجیره تامین CO2 - در نظر گرفتن همزمان صفحه های جریان فرآیند ضبط و استفاده-2021
A large fraction of anthropogenic CO2 emissions comes from large point sources such as power plants, petroleum refineries, and large industrial facilities. A significant decrease of these CO2 emissions can be achieved with CO2 capture, utilization, and storage (CCUS) technologies. This study proposes a conceptually simplified model for the optimization of combined CO2 supply networks and capture and utilization technologies by the mixed-integer non-linear programming (MINLP) approach. The objective is to maximize the profit of CCUS technologies, considering chemisorption using methyl-diethanolamine (MDEA) as a capture technology and conversion of CO2 to CH3OH as a utilization technology. Additionally, avoided tax from reduced CO2 emissions is considered as a revenue. A hypothetical case study of five larger point sources of CO2 was investigated, namely coal power plants, biogas plant, aluminium production plant and two cement plants. Two scenarios were considered: i) Scenario A considering different values of the CO2 tax, and ii) Scenario B considering different flue gas flowrates at different values of the CO2 tax. The results show the potential of model-based optimization in reducing the amount of CO2 in the atmosphere by CCUS technology. Furthermore, the results in Scenario A show that CCUStechnology is only profitable if the price of CO2 emissions is higher than 110 €/t emitted CO2. Moreover, the results in Scenario B show that both the profit and the production of CH3OH depend to a large extent on the flue gas flow.
KEYWORDS: Point sources of CO2 | Carbon capture | Storage and utilization (CCUS) | Supply network optimization | Process optimization | MINLP approach
A detailed MILP formulation for the optimal design of advanced biofuel supply chains
یک فرمول دقیق MILP برای طراحی بهینه زنجیره های پیشرفته تأمین سوخت زیستی-2021
The optimal design of a biomass supply chain is a complex problem, which must take into account multiple interrelated factors (i.e the spatial distribution of the network nodes, the efﬁcient planning of logistics activities, etc.). Mixed Integer Linear Programming has proven to be an effective mathematical tool for the optimization of the design and the management strategy of Advanced Biofuel Supply Chains (ABSC). This work presents a MILP formulation of the economical optimization of ABSC design, comprising the deﬁnition of the associated weekly management plan. A general modeling approach is proposed with a network structure comprising two intermediate echelons (storage and conversion facilities) and accounts for train and truck freight transport. The model is declined for the case of a multi- feedstock ABSC for green methanol production tested on the Italian case study. Residual biomass feed- stocks considered are woodchips from primary forestry residues, grape pomace, and exhausted olive pomace. The calculated cost of methanol is equal to 418.7 V/t with conversion facility cost accounting for 50% of the fuel cost share while transportation and storage costs for around 15%. When considering only woodchips the price of methanol increases to 433.4 V/t outlining the advantages of multi-feedstock approach.© 2021 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC-NDlicense (http://creativecommons.org/licenses/by-nc-nd/4.0/).
Keywords: Residual biomass | Advanced biofuels | Supply chain design | Logistics network | MILP | Optimization
Deep belief network-based hybrid model for multimodal biometric system for futuristic security applications
مدل ترکیبی مبتنی بر باور عمیق برای سیستم بیومتریک چند حالته برای برنامه های امنیتی آینده-2021
Biometrics is the technology to identify humans uniquely based on face, iris, and fingerprints, etc. Biometric authentication allows the person recognition automatically on the basis of behavioral or physiological charac- teristics. Biometrics are broadly employed in several commercial as well as the official identification systems for automatic access control. This paper introduces the model for multimodal biometric recognition based on score level fusion method. The overall procedure of the proposed method involves five steps, such as pre-processing, feature extraction, recognition score using Multi- support vector neural network (Multi-SVNN) for all traits, score level fusion, and recognition using deep belief neural network (DBN). The first step is to input the training images into pre-processing steps. Thus, the pre-processing of three traits, like iris, ear, and finger vein is done. Then, the feature extraction is done for each modality to extract the features. After that, the texture features are extracted from pre-processed images of the ear, iris, and finger vein, and the BiComp features are acquired from individual images using a BiComp mask. Then, the recognition score is computed based on the Multi-SVNN classifier to provide the score individually for all three traits, and the three scores are provided to the DBN. The DBN is trained using the chicken earthworm optimization algorithm (CEWA). The CEWA is the integration of the chicken swarm optimization (CSO), and earthworm optimization algorithm (EWA) for the optimal authentication of the person. The analysis proves that the developed method acquired a maximal accuracy of 95.36%, maximal sensitivity of 95.85%, and specificity of 98.79%, respectively.
Keywords: Multi-modal Bio-metric system | Chicken Swarm Optimization | Earthworm Optimization algorithm | Deep Belief Network | Multi-SVNN
Pricing decisions in a decentralized biofuel supply chain with RIN mechanism considering environmental impacts
تصمیمات قیمت گذاری در زنجیره تأمین سوخت زیستی غیرمتمرکز با مکانیسم RIN با در نظر گرفتن تأثیرات زیست محیطی-2021
This study develops pricing models in a decentralized biofuel supply chain focusing on both economic and environmental aspects. Environmental impacts are used as a measure to reflect the environmental objective function calculated based on ReCiPe method. A bi-level multi-objective stackelberg game model considering farmers and biorefineries as followers and the blender as leader is proposed. An ε-constraint method is utilized to convert the multi-objective model to a single-objective one. The bi-level model is then transformed to a solvable integrated model. Finally, a real case study of switchgrass bioethanol is presented to illustrate the performance of the proposed model. Results show that focusing on environmental goals results in the increasement of selling prices and profits of farmers and biorefineries and decreasment of about %7 in economic profit of the blender. Therefore, tradeoff analyses are performed for objective functions leading to 10 Pareto optimal solutions which give managerial insights to the blender. Moreover, sensitivity analyses are provided with respects to price elasticity and final fuel’s price and results show logical trends in selling prices.
Keywords: Biofuel supply chain | Pricing | Decentralized decision making | Environmental impacts | Multi-objective optimization
Three-scale integrated optimization model of furnace simulation, cyclic scheduling, and supply chain of ethylene plants
سه سطح مقیاس مدل بهینه سازی شبیه سازی کوره ، برنامه ریزی چرخه ای ، و زنجیره تامین کارخانه های اتیلن-2021
In order to explore the potential of profit margin improvement, a novel three-scale integrated optimization model of furnace simulation, cyclic scheduling, and supply chain of ethylene plants is proposed and evaluated. A decoupling strategy is proposed for the solution of the three-scale model, which uses our previously proposed reactor scale model for operation optimization and then transfers the obtained results as a parameter table in the joint MILP optimization of plant-supply chain scale for cyclic scheduling. This optimization framework simplifies the fundamental MINLP into several sub-models, and improves the interpretability and extendibility. In the evaluation of an industrial case, a profit increase at a percentage of 3.25% is attained in optimization compared to the practical operations. Further sensitivity analysis is carried out for strategy evolving study when price policy, supply chain, and production requirement parameters are varied. These results could provide useful suggestions for petrochemical enterprises on thermal cracking production.
Keywords: three-scale integrated optimization | cyclic scheduling | supply chain | MILP | thermal cracking
A supply chain model with service level constraints and strategies under uncertainty
یک مدل زنجیره تامین با محدودیت ها و استراتژی های سطح خدمات تحت عدم قطعیت-2021
In the current socio-economic situation, the daily demand for essential goods in the business sector is always changing owing to various unavoidable reasons. As a result, choosing the right method for profitable business has become quite tricky. This study introduces different business strategies based on constant and fuzzy demands. There are two types of constraints considered in this model to avoid the backorder cost. However, combining the service-level constraints with the constant and fuzzy demand, this study compares the total costs, and finally, the best strategy is established. Moreover, investing a small amount, this model improves the quality of the products and reduces the vendor’s setup cost. Depending on the number of transported products, this model follows the transportation discount policy for hassle-free delivery of the products with a minimum delivery rate. The Kuhn-Tucker optimization technique is employed, and global optimality is verified numerically, analytically using the Hessian matrix. This model’s robustness is discussed through a comparative study, numerical examples, sensitivity analysis, graphical representation, and managerial insights. Finally, some concluding remarks along with future extensions are discussed.
KEYWORDS: Supply chain management (SCM) | Controllable lead time | Fuzzy demand | Transportation discounts | Distribution-free approach (DFA) | Service level constraints (SLC)
A multi-objective robust optimization model for upstream hydrocarbon supply chain
یک مدل بهینه سازی قوی چند هدفه برای زنجیره تأمین هیدروکربن بالادست-2021
The hydrocarbon supply chain (HCSC) is a significant part of the world’s energy sector. The energy market has experienced erratic behavior over the last few years results in financial risks such as exceeding certain limits of the budget or not achieving the desired levels of cash in-flow, i.e., revenue. In this work, robust optimization and multi-objective mathematical programming are used to develop a model that eliminates or at least mitigates the impact of uncertain market behavior. Robust optimization provides tactical plans that are feasible and robust over market scenarios. The model assesses the trade-offs between alternatives and guides the decision-maker towards the effective management of the HCSC. The economic objectives are to minimize total cost and maximize revenue, while the non-economic objective is to minimize the depletion rate. The model considers the environmental aspect by limiting the emission of CO2 and the sustainability aspect by reducing the depletion rate of natural resources. Uncertain behavior of the oil market is modeled on scenario representation. A case study based on real data from Saudi Arabia HCSC is provided to demonstrate the model’s practicality, and a sensitivity analysis is conducted to provide some managerial insights. The results indicate that Saudi Arabia can cover its entire expenditure, break-evenpoint, by producing oil at 7.18 MMbbld and gas at 3,543.48 MMcftd. Besides, the robust approach provides a preferred plan with the highest cash inflow and the lowest sustainability over other approaches, e.g., deterministic, stochastic, and risk-based. The differences show that the robust model increases oil production to compensate for the variability of the scenario.
KEYWORDS: Hydrocarbon supply chain | Multi-objective optimization | Robust optimization | Scenario-Based Optimization | Tactical planning
Multi-objective optimization modelling of sustainable green supply chain in inventory and production management
مدلسازی چند هدفه بهینه سازی زنجیره تأمین سبز پایدار در مدیریت موجودی و تولید-2021
The ever increasing pressure to conserve the environment from global warming cannot be overemphasized. Emission from the inventory and production process contributes immensely to global warming and hence, the need to device a sustainable green inventory by the operational managers. In this paper, a multi-item multi-objective inventory model with back-ordered quantity incorporating green investment in order to save the environment is proposed. The model is formulated as a multi-objective fractional programming problem with four objectives: maximizing profit ratio to total back-ordered quantity, minimizing the holding cost in the system, minimizing total waste produced by the inventory system per cycle and minimizing the total penalty cost due to green investment. The constraints are included with budget limitation, space restrictions, a constraint on cost of ordering each item, environmental waste disposal restriction, cost of pollution control, electricity consumption cost during production and cost of greenhouse gas emission in the production process. The model effectiveness is illustrated numerically, and the solution obtained to give a useful suggestion to the decision-markers in the manufacturing sectors.
KEYWORDS: Multi-objective fractional programming | Fuzzy goal programming | Sustainable green supply chain | Inventory and production management