Showing papers presented at "International Conference on Service Operations and Logistics, and Informatics in 2018"

A Deep Learning-Based Approach for Road Pothole Detection in Timor Leste

Abstract: This research proposes a low-cost solution for detecting road potholes image by using convolutional neural network (CNN). Our model is trained entirely on the image which collected from several different places and has variation such as in wet, dry and shady conditions. The experiment using the 500 testing images showed that our model can achieve (99.80 %) of Accuracy, Precision (100%), Recall (99.60%), and F-Measure (99.60%) simultaneously.

Blockchain-base structures for a secure and operate network of semi-autonomous Unmanned Aerial Vehicles

Abstract: Unmanned Aerial Vehicles — UAVs, or drones — are now being operated by several military forces and currently, to a more limited extent, by civilian organizations. These latter operations, however, may eventually expand to exceed, in number and diversity, those of the military. Further expected development in battery capacity, construction materials and software, especially regarding machine learning algorithms and drone integration, will definitely increase UAVs’ autonomous. Unique risks associated with UAVs like risk of hackers’ attacks to intercept the control are also increasing. More incidents likely will occur once regulations are finalized that encourage more use that is widespread. Such incidents could result in multi-million dollar claims against businesses, operators and manufacturers.Blockchain is the basis technology for cryptocurrencies. However, Blockchain can have far larger applications in the field of UAVs, because Blockchain is highly distributed and publically viewable system of sequentially linked cryptographically.This paper presents a concept of application, where each UAV in the UAVNet is a Blockchain node, has on-board functionality for creating and reading transactions from the block, as well as communication tools for exchanging transactions with other UAVs.

Automatic Conversion of Road Networks from OpenDRIVE to Lanelets

Abstract: Detailed road maps are an important building block for autonomous driving. They accelerate creating a semantic environment model within the vehicle and serve as a backup solution when sensors are occluded or otherwise impaired. Due to the required detail of maps for autonomous driving and virtual test drives, creating such maps is quite labor-intensive. While some detailed maps for fairly large regions already exist, they are often in different formats and thus cannot be exchanged between companies and research institutions. To address this problem, we present the first publicly available converter from the OpenDRIVE format to lanelets—both representations are among the most popular map formats. We demonstrate the capabilities of the converter by using publicly available maps.

An Automatic Survey System for Paved and Unpaved Road Classification and Road Anomaly Detection using Smartphone Sensor

Abstract: For developing countries like Timor-Leste, regular road surface monitoring is a major challenge not only for maintaining road quality but also for national plan of road network construction. In Timor-Leste nearly 50% of roads are still unpaved. For this reason, an automated system is required to do a survey of paved and unpaved roads. In this study, we present a new approach for the use of smartphones sensor to classify paved and unpaved roads, and anomaly detection. Although, the most remarkable factor to differentiate paved and unpaved road is based on amplitude of the vertical acceleration, each vehicle has a different type of suspension system. Therefore, we used high-dimensional features and state-of-the-art machine learning techniques to make the system robust for differences of vehicle and also smartphone type. This study divided into two stages such as paved and unpaved road classification and road anomaly detection such as pothole and bump. For paved and unpaved road classification, we tried to use the SVM, HMM and ResNet and compared the performance of these models. Of all comparison, the ResNet was the best choice in this study, because it outperformed the SVM and HMM on the all performance evaluation criteria. Furthermore, the KNN and DTW are applied for anomaly detection on the paved road. The KNN-DTW are also compared to the other machine learning techniques like SVM and classical KNN using same criteria. As a result of the comparison, the KNN-DTW and SVM performed better than classical KNN.

Anomaly Detection Methods for IIoT Networks

Abstract: IIoT networks are different from general IT networks such as office or business networks where multiple various types of applications, protocols and traffic profiles are presented, and the cyber security challenges are more on protecting data confidentiality and integrity than on network availability. IIoT networks have special features and face unique challenges in defending against cyber-attacks. This paper briefly describes the requirements and challenges in IIoT network security, and presents an overview of the existing network anomaly detection methods. The paper further presents other anomaly detection methods that are specifically applicable to IIoT networks, as those methods exploit the deterministic features of the physical world in detecting the anomalies in the observed behavior.

Sustainable value stream mapping and technologies of Industry 4.0 in manufacturing process reconfiguration: A case study in an apparel company

Abstract: To optimize resource use in production, Lean manufacturing is the most widely implemented method in the world. One of the most useful tools in Lean production is Value Stream Mapping (VSM). With focus on visualizing key data of a production process in a single picture, VSM attempts to reveal bottleneck steps in a process. As a consequence, industrial engineers can determine which stages of the process should be put emphasis on improving. However, VSM sole consideration is economics and other aspects of sustainability such as societal and environmental are neglected. With Sustainable Value Stream Mapping (SVSM), all necessary illustrations for a sustainable manufacturing process can be visualized, which leads to higher chances to identify potential problems in the efficiency of production processes beyond the ones identified using lean manufacturing. This research provides a case study where SVSM is applied in an apparel company in order to identify potential issues in the sustainability of their production process. Furthermore, this paper highlights several potential solutions such as Radio-frequency identification (RFID), big data and ergonomics improvement by discussing the impact of their implementation on the process sustainability. Finally, the conclusion section discusses limits in the solutions implementation and suggest future research.

Ensuring performance measurement integrity in logistics using blockchain

Abstract: Information and communication technology has been a positive dynamic force behind improving performance. Simultaneously enabling digital business ecosystems to become an increasingly popular concept for modelling and building distributed systems in heterogeneous, decentralized and open environments. These business solutions have created an opportunity for automated business relations and transactions as well as implementing blockchain based performance measurement systems (PMS), allowing PMS to be more advanced giving validation and verification of received data hence the indicators. This paper evaluates feasibility of blockchain based PMS for logistics industry. Today the performance of supply chain stakeholders including transport logistics is lacking transparency and restraining innovative digital improvements towards a connected, smart and efficient ecosystem. Current public blockchains are not feasible for given use case due to limited throughput, and transaction cost. In this paper we have evaluated different technological alternatives and found several new developments that make blockchain technology suitable for ensuring logistics sector performance measurement integrity. Validated indicators can add trustworthiness and visibility to management and process improvement decisions, as well as be subject to smart contracts and monetary transactions.

Real-time Pallet Localization with 3D Camera Technology for Forklifts in Logistic Environments

Abstract: This paper presents a novel approach for detection and localization of standardized euro pallets, which are orientated up to 90° in relation to the sensor plane. There is no a priori information about the pallets pose needed. We use a time-of-flight camera. Our algorithm is based on finding surfaces in the point cloud, which represent the three wooden blocks of a euro pallet. Different kinds of geometrical checks set up our detection pipeline, where no artificial markers on the pallets are needed. Since we perform the detection while driving a forklift, the algorithm must process the point cloud within a set time limit. The detection and localization result in the pallets position and orientation in relation to the camera coordinate system. This information can be provided to higher-level systems, like advanced driver assistance systems. The results show that the localization of pallets is possible in the scenario considered.

IoT based Omni-Channel Logistics Service in Industry 4.0

Abstract: Rapid change of sales and distribution channels in the last era with primary focus on customer centered shopping experience to the growing importance of more customized products and faster delivery has led the recent trend of the Omni-channel. The higher expectation for personalized products and service and the disruptive production and information technology are driving the improvement on production and service systems. Framework of human centered IoT based logistics service for Omni-channel has been proposed in the research and the proposed framework does not only involve the new logistics distribution approach generative quick delivery with latest Internet of Things (IoT) technology, but also realize the need of dynamic order fulfillment in the new paradigm shift of manufacturing. This study is expected to become a role model in the change from manufacturing oriented business to service based industry. The proposed IoT based logistics system has the potential to be a disruptive and novel logistics system by providing an integrated seamless Omni-channel journey for modern shoppers.

A Blockchain Aided Metric for Predictive Delivery Performance in Supply Chain Management

Abstract: The topic of blockchain has been inundated with the fanaticism of cryptocurrencies’ enthusiasts in recent years. In fact, the theory of blockchain and technologies behind are more worthy to be discussed to bring revolution to nowadays business operation. In this paper, we conduct an interdisciplinary study on business logistics as well as the cutting edge information technologies. We discuss the ongoing projects of blockchain in business industry, and then we propose our assessment model and blockchain framework to seek an enhanced metric for delivery performance with real-time feature and higher accuracy. Based on the our analysis, we identify the shortcomings of traditional assessment on delivery performance in contemporary global supply chain management and we discuss the potential benefits brought by adoption of our proposed framework.

Automated Guided Vehicle: the Direction of Intelligent Logistics

Abstract: Intelligent Logistics is one of the most important strategic directions for the development of modern logistics industry. Automated guided vehicle (AGV) is the key equipment the benchmark for the development of Intelligent Logistics. This paper analyzes the development history of AGV and their current application status, both at home and abroad. It also points out AGV’s new direction for the development and advancement of China’s Intelligent Logistics where we should focus on the research and promotion of AGV since they are artificial intelligence-oriented and based on the needs of Intelligent Logistics. In the future, the combination of robot and autopilot technology will greatly enhance the application and service levels of AGV to Intelligent Logistics, reduce the logistics costs of trunk transportation and "the last mile", improve the efficiency of logistics transportation and distribution, and promote user’s experience.

Analysis of key dimension and sub-dimension for Supply Chian of Industry to fourth Industry Performance Measurement

Abstract: In 2013 Germany, a world leader’s Industrializes nation published its "Industry 4.0" strategic plan. This strategic plan motivated many countries in the world to develop their own industry. Thailand is one developing country that invest in this strategy. As we know Thailand food industry is the most important and need to be change. The food industry can answer human behavior and have variety. With changing of human behavior, Enterprise should invest and upgrading and improving in production. In industry 4.0 perspective, it is possible that the global industry should focus on and be ready to adapt to the industry 4.0. This paper will present performance measurement by assessing readiness and Maturity Model in part of selecting dimension and sub-dimension.

A Solution for Internet of Things based on Blockchain Technology

Abstract: Blockchain technology is a generic term for data organization structures, cryptography algorithms, distributed consensus mechanisms, and peer-to-peer communications that are used to implement distributed ledgers. Its core value lies in the establishment of mutual trust between non-coordinated participants. However, the current blockchain applications are inclined towards software and network, missing strong connection with the real world. The Internet of Things technology connects various smart devices and sensors to Internet to facilitate recognition and management of information. This paper presents a blockchain-based Internet of Things solution, where RFID chips with built-in asymmetric encryption algorithm and scanners uploading information directly to blockchain. Compared to traditional Internet of Things designs, the proposed solution combines the advantages of both decentralized blockchain, and the Waltonchain implementation demonstrates such advantages with both data security and application flexibility.

Design and Fabrication of Embroidered RFID Antennas for Wearable Applications

Abstract: With advances in materials and fabrication methods, wireless communication devices are widely employed in Internet-of-Things (IOT) and human wearable applications. In this paper, we present a set of RFID labels using embroidered yarns that can be seamlessly integrated into clothing or textiles in fabrication processes. Detailed embroidery methods based on conductive yarns and textile substrates are proposed. The simulation and measurement results show that textile-based RFID antennas can provide stable electromagnetic performances and compete with the metallic counterparts.

A routing model for emergency vehicles using the real time traffic data

Abstract: In India, many semi-government emergency medical services (EMS) exist; one of them is 108 which operate in several states of the country. The efficiency of EMS depends on its timely responsiveness to the demand and the integration of available real time travel/traffic data into the vehicle scheduling and routing model. This paper focuses on designing the routes for emergency vehicles by developing an optimization model based on the available knowledge of real time traffic information using the Google Maps Distance Matrix API. The heuristic approach involves formulation of the vehicle routing problem as an integer programming model and optimizing it by integrating with Google API. The main components of the model are incident location, vehicle tracking, shortest path finding and dispatch optimization. This simulation strategy is validated by various samples and a series of tests.

Faster Number Theoretic Transform on Graphics Processors for Ring Learning with Errors Based Cryptography

Abstract: The Number Theoretic Transform (NTT) has been revived recently by the advent of the Ring-Learning with Errors (Ring-LWE) Homomorphic Encryption (HE) schemes. In these schemes, the NTT is used to calculate the product of high degree polynomials with multi-precision coefficients in quasilinear time. This is known as the most time-consuming operation in Ring–based HE schemes. Therefore; accelerating NTT is key to realize efficient implementations. As such, in its current version, a fast NTT implementation is included in cuHE, which is a publicly available HE library in Compute Unified Device Architecture (CUDA). We analyzed cuHE NTT kernels and found out that they suffer from two performance pitfalls: shared memory conflicts and thread divergence. We show that by using a set of CUDA tailored-made optimizations, we can improve on the speed of cuHE NTT computation by 20%-50% for different problem sizes.

The Study for Refurbishing Process of Packaging Material in E-commerce Logistics

Abstract: Many companies are focusing on reverse logistics (RL) network currently, especially in the growth of e-commerce markets around the world. Due to the convenience and fast delivery of e-commerce service, consumer behavior changes to online shopping. However, each of delivery packed by packaging material, which cause large scale of the packaging material waste. In this paper, we propose two simulation structures and develop the routing selection strategies of them. One structure simulates the full loaded cars whether decrease the cost of distribution. The other structure simulates that recycling of return of packaging material whether is reusable and redistributable. Our results provide useful framework that can benefit e-commerce practitioners for building their RL network.

An Overview of Warehousing Applications based on Cable Robot Technology in Logistics

Abstract: Robotics belongs to the megatrends radically changing the logistics industry which has long time been reluctant to the adoption of technological innovation. Facing aggravated competition by ever new and stronger actors in the industry, labor shortage due to demographic shifts, and constant cost pressure, logistics robots are considered as an effective means to tackle those problems. By taking a look at the market of logistics robots, the market condition for cable-driven parallel robots for storage purposes can be studied and a successful introduction into the market of material handling devices initiated. Hence, this paper examines the prevalence of robotics solutions in general and cable-robot applications in particular in the logistics industry.

Servitization as a key driver for Digital Transformation of manufacturing companies’ Spare Parts Service

Abstract: The increasing service orientation of manufacturing companies places new requirements on traditional business areas such as the Spare Parts Service. The development of Servitization is a driver of Digital Transformation, especially in the After Sales Service. For the front-end processes between customer and customer service, the Digital Transformation acts as a technological vehicle that makes it possible to satisfy the new requirements demanded by the customer. For the back-end processes between Customer Service and Spare Parts Service, on the other hand, the Digital Transformation is an opportunity to face the internal efficiency and cost pressure resulting from Servitization in line with requirements. Especially the selection of implementation projects of the technologies of Digital Transformation with regard to high investment costs as well as a vague benefit transparency face companies with huge challenges. Against this background, 743 use cases are analyzed on the basis of a network analysis in order to identify possible causal chains between target values, process characteristics and technologies used. On this basis, target figure profiles are derived that can help manufacturing companies in the Spare Parts Service to select and implement technologies that meet their individual goals in order to meet the challenges of Servitization.

Beam Scanning UHF RFID Reader Antenna Design for Metal Environment Application (Invited paper)

Abstract: A two-dimensionally scanning (2D) antenna array and polling beam scanning antenna array is designed in UHF RFID system with high stability and reliability in metal environment. The two-dimensionally scanning (2D) antenna array is composed of 3×3 antenna array, a feeding network and switches. The measured -10dB impedance bandwidth is around 30MHz. The scanning beam directions covers ±60° and scanning direction gain is 9~10dBi, respectively. The polling beam scanning antenna array is composed of three 1×2 planar inverted-F antenna (PIFA) arrays and polling beam scanning feeding network consisting switch and control module. The measured bandwidth is 50MHz (895–945MHz) under the condition of VSWR less than 2, covering Chinese, Canadian, Korean, and Australian standard of frequency ranges. The steering radiation pattern is -20°, 0°, and +25° in xoz-plane. The read rate achieve 100% in the metal environment.

Cross-Correlation Based Efficient Technique For Vehicle Occupancy Detection using Magnetoresistive Sensors

Abstract: An efficient method to determine the occupancy state of a parking lot by determining the arrival and departure of vehicles from the perturbations in the magnetic field, is proposed. The method is based on cross-correlation of the magnetic field data with a suitable reference signal as template. The resulting correlation coefficient determines arrival and departure events and hence the occupancy state of parking lots. Results show that 2-axis magnetometer would suffice for accurate state-change detection. With threshold based conditions on the change in the signal, to determine when the correlation computation needs to be carried out, leads to efficient implementation of the algorithm in low-power sensor nodes. Investigation of placement location of the sensor nodes show that the sensor can be placed in between the parking lots, potentially reducing the number of required sensors to half the number of parking lots.

Theoretical analysis on the characterization of imaging systems using Euclid distance

Abstract: The Euclid distance derived from the spatial domain distribution function for the performance characterization of imaging systems is presented and theoretically analyzed. The two-dimensional distribution functions of the objects and images, usually quadratically integrable, are investigated. The Euclid distance between the practical image and the ideal image is utilized to comprehensively characterize the imaging system performance. Moreover, the amplitude ratio and the fidelity are defined from the distribution functions of the practical and the ideal image and are related to the Euclid distance, revealing its physical meaning and merits. The geometrical representation of the Euclid distance is also derived and presented. The Euclid distance is monotonous to the performance of imaging systems, thus it can be used readily in the design and optimization of the imaging systems along with its intuitionistic and scalar features.

Real-time Electric Vehicle Load Forecast to Meet Timely Energy Dispatch

Abstract: Electric vehicles are more eco-friendly and energy efficient than the conventional internal combustion engine vehicles. This technology adds new challenge to the existing energy distribution network. Specifically, electric vehicles are allowed to start charging their batteries the moment they are parked into a charging lot which creates a unpredictable load on the energy distribution network. Ideally, the energy supply system must always be in a state where the amount of energy consumed is equal to the amount of energy produced. This priori is also for the reduction of energy wastage. Hence, load forecasting serves as an estimated preemption for the supply system. In this paper, time series techniques for electric vehicles’ load forecasting are proposed. Experiments are given using Singapore’s energy dispatch system. A framework to provide the relevant electric vehicles’ load forecast to fulfill the timing criteria is also proposed.

Satellite Spot Beam and Decollision Algorithm for Pure Collective Aloha MAC Protocol

Abstract: Modern satellite random access protocols require advanced medium access control (MAC) protocols to achieve high system throughput. There are both asynchronous and synchronous satellite MAC protocols in the literature. The former MAC protocols do not require packet slot boundaries alignment using a synchronization mechanism. Here, our key contributions are a proposed Pure Collective Aloha MAC protocol with Decollision Algorithm (DA) and Spot Beam (SB) (PCA-DA-SB) and its closed-form throughput formulation. This is an asynchronous MAC protocol. A batch of packets is buffered before being transmitted sequentially into the channel for this proposed MAC protocol and both the DA and the SB technologies are utilized to enhance the system throughput. The analytical formulation of the proposed MAC protocol is derived in detail. The numerical results, using the closed-form formulation and the computer simulations, show that the peak throughput of the proposed MAC protocol is up to 90% exceeding that of a Pure Aloha (PA) MAC protocol with the DA and the SB technologies.

UN SDGs Shaping Sustainable Supply Chains: The Case of Apparel Manufacturers in Developing Countries

Abstract: Social sustainability dimension in the supply chains has been addressed scarcely and very differently across the time in Sustainable Supply Chain Management (SSCM) literature. Hence, the necessity of addressing social sustainability in different supply chains has been addressed by the scholars over the years. Meanwhile, the United Nations expect sustainable development across the globe by 2035 by introducing the Sustainable Development Goals (UN SDGs) in 2015. As a result, the tremendous responsibility falls upon the shoulders of the actors of supply chains spread across the globe since businesses play a major role towards the development of the world. Hence, this research attempts at studying how the integration of UN SDGs and supply chain practices of the suppliers in the developing countries lead to better sustainable apparel supply chains. A systematic literature review followed by interviews with experts in the apparel supply chains were conducted to gather data in this study. As a result, 11 sub-topics were identified under the social sustainability dimension of sustainable supply chains followed by best practices of the Sri Lankan apparel manufacturers who also played a major role as suppliers in the ethical global apparel supply chain. Hence this study presents social sustainability practices in depth from the perspective of UN SDGs setting example for any other labor-intensive supply chains.

Video Analytics for Indoor Crowd Estimation

Abstract: This paper demonstrates the usage of security camera footages with deep convolutional neural networks to provide cabin-level crowd density estimates in the video frames. Some applications for this include cabin-level crowd density estimates of incoming trains. With this information, train passengers may choose to board the trains at less crowded cabins, potentially decreasing the dwell time of trains at stations and experiencing a more pleasant commute overall. In a way, the crowd level estimation information will also help to maximize the train and platform capacity. Leveraging on the security camera footages would also serve as a cost-effective solution to the train operator as compared to installing new sensing equipment in the trains. Due to privacy and security concerns of publishing train cabin video frames, this paper will present the experiment results on an indoor pedestrian dataset.

Vessel Spare Parts Distribution Center Location Decision Model for Ship Maintenance Supply Chain

Abstract: Facility Location Decision (FLD) modelling is a strategic level assessment technique which can be considered as one of the most critical aspects when designing a supply chain. In the maritime industry, an efficient supply chain of vessel spare-parts is vital to maintain uninterrupted operational activities of a shipping line. Thus, storing vessel spare parts in a strategic location and distribution of spares is considered as an important feature in a Ship Maintenance Supply Chain (SMSC). The intermittent nature of demand for vessel spare parts and restrictions to store them on board create the need of locating a Distribution Centre (DC) at a suitable on shore location. Finding a strategic location for a vessel spare parts DC has been given top priority by the decision makers involved in the logistics process. As a timely research, this study has attempted to develop a model to locate a vessel spare parts DC, while carrying out a feasibility analysis to find the most suitable location for a vessel spare-parts DC in Sri Lanka.Purpose: Identify the major factors affecting a FLD in SMSC through evaluation of site alternatives to find the most suitable vessel spare parts DC location in Sri Lanka and to develop a FLD model for SMSC in Sri Lankan context.Methodology: A mixed approach was used for this study where both quantitative and qualitative data was collected. The initial literature review, interviews carried out with industry professionals, survey questionnaires and collection of secondary data from official industry records were the main data sources. Analytical Hierarchy Process (AHP) and Factor Rating Method were used as data analytic tools to derive the best location. In conclusion, the proposed FLD model was developed using the identified factors and the developed indices for each location alternative.

Automated Multi-Plant Scheduling of Ready-Mixed Concrete Trucks

Abstract: Ready-Mixed Concrete (RMC) is a perishable product; hence, specifications such as ASTM C94 recommend the delivery of RMC under 1.5 hours to ensure the quality. It is known that certain scheduling practices and driving behaviors lead to operational inefficiencies and poor-quality RMC. We propose a model to schedule RMC trucks while maximizing both the job coverage and profit, as well as meeting constraints such as ASTM C94 and continuous casting. The proposed solution consists of a rule checker and a scheduler. Rule checker enforces constraints such as deadlines, working hours, travel time. The scheduler uses simulated annealing to assign as many jobs as possible while maximizing the overall profit. We consider scenarios where trucks are attached to a given RMC plant, as well as allowed to move across plants as per the job requirements Using a workload derived from an actual RMC delivery company; we demonstrate that the proposed solution has good coverage of jobs while maximizing the overall profit. For example, compared to the manual job allocation, proposed solution increases the average job coverage and profit by 13% and 9%, respectively. When trucks are allowed to move across plants, job coverage and profit increase to 16% and 14%, respectively. By automatically adjusting the first unload time by a few 10s of minutes to reduce job conflicts we further enhanced above numbers by 21% and 13%, respectively.

Ranking of Influential users based on User-Tweet bipartite graph

Abstract: Today, even if we are still geographically situated, but real-time news and trends are able to reach us no matter how far we are or how huge is the time difference. This is due to Social Networks Services and the strong involvement of people to them through posting, sharing and interacting online with information. Therefore, we propose a study on patterns of information diffusion on Twitter during global scale events. We also introduce a method for identifying influencers and quantify popularity of Tweets on the Network based on a user-tweet bipartite graph.