Search results for: Overhead gantry crane.

Authors: Emmanuel D. Buedi, K. O. Boateng, Griffith S. Klogo

Abstract:

Electrical distribution networks are prone to power quality disturbances originating from the complexity of the distribution network, mode of distribution (overhead or underground) and types of loads used by customers. Data on the types of disturbances present and frequency of occurrence is needed for economic evaluation and hence finding solution to the problem. Utility companies have resorted to using secondary power quality devices such as smart meters to help gather the required data. Even though this approach is easier to adopt, data gathered from these devices may not serve the required purpose, since the installation of these devices in the electrical network usually does not conform to available PQM placement methods. This paper presents a design of a PQM that is capable of integrating into an existing DAS infrastructure to take advantage of available placement methodologies. The monitoring component of the design is implemented and installed to monitor an existing LV network. Data from the monitor is analyzed and presented. A portion of the LV network of the Electricity Company of Ghana is modeled in MATLAB-Simulink and analyzed under various earth fault conditions. The results presented show the ability of the PQM to detect and analyze PQ disturbance such as voltage sag and overvoltage. By adopting a placement methodology and installing these nodes, utilities are assured of accurate and reliable information with respect to the quality of power delivered to consumers.

Keywords: Power quality, remote monitoring, distributed automation system, economic evaluation, LV network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1140

Authors: M. Santhalakshmi, P Suganthi

Abstract:

Wireless Sensor Networks (WSNs) have many advantages. Their deployment is easier and faster than wired sensor networks or other wireless networks, as they do not need fixed infrastructure. Nodes are partitioned into many small groups named clusters to aggregate data through network organization. WSN clustering guarantees performance achievement of sensor nodes. Sensor nodes energy consumption is reduced by eliminating redundant energy use and balancing energy sensor nodes use over a network. The aim of such clustering protocols is to prolong network life. Low Energy Adaptive Clustering Hierarchy (LEACH) is a popular protocol in WSN. LEACH is a clustering protocol in which the random rotations of local cluster heads are utilized in order to distribute energy load among all sensor nodes in the network. This paper proposes Connected Dominant Set (CDS) based cluster formation. CDS aggregates data in a promising approach for reducing routing overhead since messages are transmitted only within virtual backbone by means of CDS and also data aggregating lowers the ratio of responding hosts to the hosts existing in virtual backbones. CDS tries to increase networks lifetime considering such parameters as sensors lifetime, remaining and consumption energies in order to have an almost optimal data aggregation within networks. Experimental results proved CDS outperformed LEACH regarding number of cluster formations, average packet loss rate, average end to end delay, life computation, and remaining energy computation.

Keywords: Wireless sensor network, connected dominant set, clustering, data aggregation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1132

Authors: K. C. Iyer, T. Gupta, Y. M. Bindal

Abstract:

Head office overhead (HOOH) is an indirect cost and is recovered through individual project billings by the contractor. Delay in a project impacts the absorption of HOOH cost allocated to that particular project and thus diminishes the expected profit of the contractor. This unabsorbed HOOH cost is later claimed by contractors as damages. The subjective nature of the available formulae to compute unabsorbed HOOH is the difficulty that contractors and owners face and thus dispute it. The paper attempts to bring together the rationale of various HOOH formulae by gathering contractor’s HOOH cost data on all of its project, using case study approach and comparing variations in values of HOOH using scenario analysis. The case study approach uses project data collected from four construction projects of a contractor in India to calculate unabsorbed HOOH costs from various available formulae. Scenario analysis provides further variations in HOOH values after considering two independent situations mainly scope changes and new projects during the delay period. Interestingly, one of the findings in this study reveals that, in spite of HOOH getting absorbed by additional works available during the period of delay, a few formulae depict an increase in the value of unabsorbed HOOH, neglecting any absorption by the increase in scope. This indicates that these formulae are inappropriate for use in case of a change to the scope of work. Results of this study can help both parties in deciding on an appropriate formula more objectively, considering the events on a project causing the delay and contractor's position in respect of obtaining new projects.

Keywords: Absorbed and unabsorbed overheads, head office overheads, scenario analysis, scope variation

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 829

Authors: M. Jayekumar, V. Nagarajan

Abstract:

Wireless sensor network finds role in environmental monitoring, industrial applications, surveillance applications, health monitoring and other supervisory applications. Sensing devices form the basic operational unit of the network that is self-battery powered with limited life time. Sensor node spends its limited energy for transmission, reception, routing and sensing information. Frequent energy utilization for the above mentioned process leads to network lifetime degradation. To enhance energy efficiency and network lifetime, we propose a modified energy optimization and node recovery post failure method, Energy-Link Failure Recovery Routing (E-LFRR) algorithm. In our E-LFRR algorithm, two phases namely, Monitored Transmission phase and Replaced Transmission phase are devised to combat worst case link failure conditions. In Monitored Transmission phase, the Actuator Node monitors and identifies suitable nodes for shortest path transmission. The Replaced Transmission phase dispatches the energy draining node at early stage from the active link and replaces it with the new node that has sufficient energy. Simulation results illustrate that this combined methodology reduces overhead, energy consumption, delay and maintains considerable amount of alive nodes thereby enhancing the network performance.

Keywords: Actuator node, energy efficient routing, energy hole, link failure recovery, link utilization, wireless sensor network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1197

Authors: Balimu Mwiya, Mundia Muya, Chabota Kaliba, Peter Mukalula

Abstract:

Factors affecting construction unit cost vary depending on a country’s political, economic, social and technological inclinations. Factors affecting construction costs have been studied from various perspectives. Analysis of cost factors requires an appreciation of a country’s practices. Identified cost factors provide an indication of a country’s construction economic strata. The purpose of this paper is to identify the essential factors that affect unit cost estimation and their breakdown using artificial neural networks. Twenty five (25) identified cost factors in road construction were subjected to a questionnaire survey and employing SPSS factor analysis the factors were reduced to eight. The 8 factors were analysed using neural network (NN) to determine the proportionate breakdown of the cost factors in a given construction unit rate. NN predicted that political environment accounted 44% of the unit rate followed by contractor capacity at 22% and financial delays, project feasibility and overhead & profit each at 11%. Project location, material availability and corruption perception index had minimal impact on the unit cost from the training data provided. Quantified cost factors can be incorporated in unit cost estimation models (UCEM) to produce more accurate estimates. This can create improvements in the cost estimation of infrastructure projects and establish a benchmark standard to assist the process of alignment of work practises and training of new staff, permitting the on-going development of best practises in cost estimation to become more effective.

Keywords: Construction cost factors, neural networks, roadworks, Zambian Construction Industry.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3831

Authors: Rafsan Al Mamun, Md. Motaharul Islam, Rabana Tajrin, Nabiha Noor, Shafinaz Qader

Abstract:

In an attempt to enrich the lives of billions of people by providing proper information, security and a way of communicating with others, the need for efficient and improved satellites is constantly growing. Thus, there is an increasing demand for better error detection and correction (EDAC) schemes, which are capable of protecting the data onboard the satellites. The paper is aimed towards detecting and correcting such errors using a special algorithm called the Hamming Code, which uses the concept of parity and parity bits to prevent single-bit errors onboard a satellite in Low Earth Orbit. This paper focuses on the study of Low Earth Orbit satellites and the process of generating the Hamming Code matrix to be used for EDAC using computer programs. The most effective version of Hamming Code generated was the Hamming (16, 11, 4) version using MATLAB, and the paper compares this particular scheme with other EDAC mechanisms, including other versions of Hamming Codes and Cyclic Redundancy Check (CRC), and the limitations of this scheme. This particular version of the Hamming Code guarantees single-bit error corrections as well as double-bit error detections. Furthermore, this version of Hamming Code has proved to be fast with a checking time of 5.669 nanoseconds, that has a relatively higher code rate and lower bit overhead compared to the other versions and can detect a greater percentage of errors per length of code than other EDAC schemes with similar capabilities. In conclusion, with the proper implementation of the system, it is quite possible to ensure a relatively uncorrupted satellite storage system.

Keywords: Bit-flips, Hamming code, low earth orbit, parity bits, satellite, single error upset.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 916

Authors: A. Almaneea, N. Kapur, J. L. Summers, H. M. Thompson

Abstract:

Meeting the growth in demand for digital services such as social media, telecommunications, and business and cloud services requires large scale data centres, which has led to an increase in their end use energy demand. Generally, over 30% of data centre power is consumed by the necessary cooling overhead. Thus energy can be reduced by improving the cooling efficiency. Air and liquid can both be used as cooling media for the data centre. Traditional data centre cooling systems use air, however liquid is recognised as a promising method that can handle the more densely packed data centres. Liquid cooling can be classified into three methods; rack heat exchanger, on-chip heat exchanger and full immersion of the microelectronics. This study quantifies the improvements of heat transfer specifically for the case of immersed microelectronics by varying the CPU and heat sink location. Immersion of the server is achieved by filling the gap between the microelectronics and a water jacket with a dielectric liquid which convects the heat from the CPU to the water jacket on the opposite side. Heat transfer is governed by two physical mechanisms, which is natural convection for the fixed enclosure filled with dielectric liquid and forced convection for the water that is pumped through the water jacket. The model in this study is validated with published numerical and experimental work and shows good agreement with previous work. The results show that the heat transfer performance and Nusselt number (Nu) is improved by 89% by placing the CPU and heat sink on the bottom of the microelectronics enclosure.

Keywords: CPU location, data centre cooling, heat sink in enclosures, Immersed microelectronics, turbulent natural convection in enclosures.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2177

Authors: Mawloud Mosbah, Bachir Boucheham

Abstract:

Color Histogram is considered as the oldest method used by CBIR systems for indexing images. In turn, the global histograms do not include the spatial information; this is why the other techniques coming later have attempted to encounter this limitation by involving the segmentation task as a preprocessing step. The weak segmentation is employed by the local histograms while other methods as CCV (Color Coherent Vector) are based on strong segmentation. The indexation based on local histograms consists of splitting the image into N overlapping blocks or sub-regions, and then the histogram of each block is computed. The dissimilarity between two images is reduced, as consequence, to compute the distance between the N local histograms of the both images resulting then in N*N values; generally, the lowest value is taken into account to rank images, that means that the lowest value is that which helps to designate which sub-region utilized to index images of the collection being asked. In this paper, we make under light the local histogram indexation method in the hope to compare the results obtained against those given by the global histogram. We address also another noteworthy issue when Relying on local histograms namely which value, among N*N values, to trust on when comparing images, in other words, which sub-region among the N*N sub-regions on which we base to index images. Based on the results achieved here, it seems that relying on the local histograms, which needs to pose an extra overhead on the system by involving another preprocessing step naming segmentation, does not necessary mean that it produces better results. In addition to that, we have proposed here some ideas to select the local histogram on which we rely on to encode the image rather than relying on the local histogram having lowest distance with the query histograms.

Keywords: CBIR, Color Global Histogram, Color Local Histogram, Weak Segmentation, Euclidean Distance.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1734

Authors: Saeid Khajehmandali, Fattah Mollakarimi, Zohreh Seyf

Abstract:

There was a high rate of corrosion in Pyrolysis Gasoline Hydrogenation (PGH) unit of Arak Petrochemical Company (ARPC), and it caused some operational problem in this plant. A commercial chemical had been used as anti-corrosion in the depentanizer column overhead in order to control the corrosion rate. Injection of commercial corrosion inhibitor caused some operational problems such as fouling in some heat exchangers. It was proposed to replace this commercial material with another more effective trouble free, and well-known additive by R&D and operation specialists. At first, the system was simulated by commercial simulation software in electrolytic system to specify low pH points inside the plant. After a very comprehensive study of the situation and technical investigations ,ammonia / monoethanol amine solution was proposed as neutralizer or corrosion inhibitor to be injected in a suitable point of the plant. For this purpose, the depentanizer column and its accessories system was simulated again in case of this solution injection. According to the simulation results, injection of new anticorrosion substance has no any side effect on C5 cut product and operating conditions of the column. The corrosion rate will be cotrolled, if the pH remains at the range of 6.5 to 8 . Aactual plant test run was also carried out by injection of ammonia / monoethanol amine solution at the rate of 0.6 Kg/hr and the results of iron content of water samples and corrosion test coupons confirmed the simulation results. Now, ammonia / monoethanol amine solution is injected to a suitable pint inside the plant and corrosion rate has decreased significantly.

Keywords: Corrosion, Pyrolysis Gasoline, Simulation, Corrosion test copoun.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2371

Authors: C. Paramasivam, K. B. Jayanthi

Abstract:

An innovative approach to develop modified scaling free CORDIC based two parallel pipelined Multipath Delay Commutator (MDC) FFT and IFFT architectures for radix 2² FFT algorithm is presented. Multipliers and adders are the most important data paths in FFT and IFFT architectures. Multipliers occupy high area and consume more power. In order to optimize the area and power overhead, modified scaling-free CORDIC based complex multiplier is utilized in the proposed design. In general twiddle factor values are stored in RAM block. In the proposed work, modified scaling-free CORDIC based twiddle factor generator unit is used to generate the twiddle factor and efficient switching units are used. In addition to this, four point FFT operations are performed without complex multiplication which helps to reduce area and power in the last two stages of the pipelined architectures. The design proposed in this paper is based on multipath delay commutator method. The proposed design can be extended to any radix 2ⁿ based FFT/IFFT algorithm to improve the throughput. The work is synthesized using Synopsys design Compiler using TSMC 90-nm library. The proposed method proves to be better compared to the reference design in terms of area, throughput and power consumption. The comparative analysis of the proposed design with Xilinx FPGA platform is also discussed in the paper.

Keywords: Coordinate Rotational Digital Computer(CORDIC), Complex multiplier, Fast Fourier transform (FFT), Inverse fast Fourier transform (IFFT), Multipath delay Commutator (MDC), modified scaling free CORDIC, complex multiplier, pipelining, parallel processing, radix-2^2.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1824

Authors: Isam A. H. Al Zubaidi

Abstract:

Low sulfur diesel like fuel oil was produced from a quick remediation process of waste oil sludge (WOS). This quick process will reduce the volume of the WOS in petroleum refineries as well as oil fields by transferring the waste to more beneficial product. The practice includes mixing process of WOS with commercial diesel fuel. Different ratios of WOS to diesel fuel were prepared ranging 1:1 to 20:1 by mass. The mixture was continuously mixed for 10 minutes using a bench-type overhead stirrer, and followed by the filtration process to separate the soil waste from filtrate oil product. The quantity and the physical properties of the oil filtrate were measured. It was found that the addition of up to 15% WOS to diesel fuel was accepted without dramatic changes to the properties of diesel fuel. The amount of WOS was decreased by about 60% by mass. This means that about 60% of the mass of sludge was recovered as light fuel oil. The physical properties of the resulting fuel from 10% sludge mixing ratio showed that the specific gravity, ash content, carbon residue, asphaltene content, viscosity, diesel index, cetane number, and calorific value were affected slightly. The color was changed to light black. The sulfur content was increased also. This requires another process to reduce the sulfur content of resulting light fuel. A desulfurization process was achieved using adsorption techniques with activated biomaterial to reduce the sulfur content to acceptable limits. Adsorption process by ZnCl2 activated date palm kernel powder was effective for improvement of the physical properties of diesel like fuel. The final sulfur content was increased to 0.185 wt%. This diesel like fuel can be used in all tractors, buses, tracks inside and outside the refineries. The solid remaining seems to be smooth and can be mixed with asphalt mixture for asphalting the roads or can be used with other materials as asphalt coating material for constructed buildings. Through this process, valuable fuel has been recovered, and the amount of waste material had decreased.

Keywords: Oil sludge, diesel fuel, blending process, filtration process.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 352

Authors: Thomas Meier

Abstract:

One of the major challenges for sustainable smart building systems is to support device interoperability, i.e. connecting sensor or actuator devices from different vendors, and present their functionality to the external applications. Furthermore, smart building systems are supposed to connect with devices that are not available yet, i.e. devices that become available on the market sometime later. It is of vital importance that a sustainable smart building platform provides an appropriate external interface that can be leveraged by external applications and smart services. An external platform interface must be stable and independent of specific devices and should support flexible and scalable usage scenarios. A typical approach applied in smart home systems is based on a generic device interface used within the smart building platform. Device functions, even of rather complex devices, are mapped to that generic base type interface by means of specific device drivers. Our new approach, presented in this work, extends that approach by using the smart building system’s rule engine to create complex virtual devices that can represent the most diverse properties of real devices. We examined and evaluated both approaches by means of a practical case study using a smart building system that we have developed. We show that the solution we present allows the highest degree of flexibility without affecting external application interface stability and scalability. In contrast to other systems our approach supports complex virtual device configuration on application layer (e.g. by administration users) instead of device configuration at platform layer (e.g. platform operators). Based on our work, we can show that our approach supports almost arbitrarily flexible use case scenarios without affecting the external application interface stability. However, the cost of this approach is additional appropriate configuration overhead and additional resource consumption at the IoT platform level that must be considered by platform operators. We conclude that the concept of complex virtual devices presented in this work can be applied to improve the usability and device interoperability of sustainable intelligent building systems significantly.

Keywords: Complex virtual devices, device integration, device interoperability, Internet of Things, smart building platform.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 758

Authors: H. Ferfera-Harrar, T. Benhalima, D. Lerari

Abstract:

Contamination of water, due to the discharge of untreated industrial wastewaters into the ecosystem, has become a serious problem for many countries. In this study, bioadsorbents based on chitosan-g-poly(acrylamide) and montmorillonite (MMt) clay (CTS-g-PAAm/MMt) hydrogel nanocomposites were prepared via free‐radical grafting copolymerization and crosslinking of acrylamide monomer (AAm) onto natural polysaccharide chitosan (CTS) as backbone, in presence of various contents of MMt clay as nanofiller. Then, they were hydrolyzed to obtain highly functionalized pH‐sensitive nanomaterials with uppermost swelling properties. Their structure characterization was conducted by X-Ray Diffraction (XRD) and Scanning Electron Microscopy (SEM) analyses. The adsorption performances of the developed nanohybrids were examined for removal of methylene blue (MB) cationic dye from aqueous solutions. The factors affecting the removal of MB, such as clay content, pH medium, adsorbent dose, initial dye concentration and temperature were explored. The adsorption process was found to be highly pH dependent. From adsorption kinetic results, the prepared adsorbents showed remarkable adsorption capacity and fast adsorption rate, mainly more than 88% of MB removal efficiency was reached after 50 min in 200 mg L^-1 of dye solution. In addition, the incorporating of various content of clay has enhanced adsorption capacity of CTS-g-PAAm matrix from 1685 to a highest value of 1749 mg g^-1 for the optimized nanocomposite containing 2 wt.% of MMt. The experimental kinetic data were well described by the pseudo-second-order model, while the equilibrium data were represented perfectly by Langmuir isotherm model. The maximum Langmuir equilibrium adsorption capacity (q_m) was found to increase from 2173 mg g⁻¹ until 2221 mg g⁻¹ by adding 2 wt.% of clay nanofiller. Thermodynamic parameters revealed the spontaneous and endothermic nature of the process. In addition, the reusability study revealed that these bioadsorbents could be well regenerated with desorption efficiency overhead 87% and without any obvious decrease of removal efficiency as compared to starting ones even after four consecutive adsorption/desorption cycles, which exceeded 64%. These results suggest that the optimized nanocomposites are promising as low cost bioadsorbents.

Keywords: Chitosan, clay, dye adsorption, hydrogels nanocomposites.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1020

Authors: Omar F. Hamad, T. Marwala

Abstract:

With optimized bandwidth and latency discrepancy ratios, Node Gain Scores (NGSs) are determined and used as a basis for shaping the max-heap overlay. The NGSs - determined as the respective bandwidth-latency-products - govern the construction of max-heap-form overlays. Each NGS is earned as a synergy of discrepancy ratio of the bandwidth requested with respect to the estimated available bandwidth, and latency discrepancy ratio between the nodes and the source node. The tree leads to enhanceddelivery overlay multicasting – increasing packet delivery which could, otherwise, be hindered by induced packet loss occurring in other schemes not considering the synergy of these parameters on placing the nodes on the overlays. The NGS is a function of four main parameters – estimated available bandwidth, Ba; individual node's requested bandwidth, Br; proposed node latency to its prospective parent (Lp); and suggested best latency as advised by source node (Lb). Bandwidth discrepancy ratio (BDR) and latency discrepancy ratio (LDR) carry weights of α and (1,000 - α ) , respectively, with arbitrary chosen α ranging between 0 and 1,000 to ensure that the NGS values, used as node IDs, maintain a good possibility of uniqueness and balance between the most critical factor between the BDR and the LDR. A max-heap-form tree is constructed with assumption that all nodes possess NGS less than the source node. To maintain a sense of load balance, children of each level's siblings are evenly distributed such that a node can not accept a second child, and so on, until all its siblings able to do so, have already acquired the same number of children. That is so logically done from left to right in a conceptual overlay tree. The records of the pair-wise approximate available bandwidths as measured by a pathChirp scheme at individual nodes are maintained. Evaluation measures as compared to other schemes – Bandwidth Aware multicaSt architecturE (BASE), Tree Building Control Protocol (TBCP), and Host Multicast Tree Protocol (HMTP) - have been conducted. This new scheme generally performs better in terms of trade-off between packet delivery ratio; link stress; control overhead; and end-to-end delays.

Keywords: Overlay multicast, Available bandwidth, Max-heapform overlay, Induced packet loss, Bandwidth-latency product, Node Gain Score (NGS).

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1574

Authors: Jaeyoung Lee

Abstract:

Autonomous driving systems require high reliability to provide people with a safe and comfortable driving experience. However, despite the development of a number of vehicle sensors, it is difficult to always provide high perceived performance in driving environments that vary from time to season. The image segmentation method using deep learning, which has recently evolved rapidly, provides high recognition performance in various road environments stably. However, since the system controls a vehicle in real time, a highly complex deep learning network cannot be used due to time and memory constraints. Moreover, efficient networks are optimized for GPU environments, which degrade performance in embedded processor environments equipped simple hardware accelerators. In this paper, a semantic segmentation network, matrix multiplication accelerator network (MMANet), optimized for matrix multiplication accelerator (MMA) on Texas instrument digital signal processors (TI DSP) is proposed to improve the recognition performance of autonomous driving system. The proposed method is designed to maximize the number of layers that can be performed in a limited time to provide reliable driving environment information in real time. First, the number of channels in the activation map is fixed to fit the structure of MMA. By increasing the number of parallel branches, the lack of information caused by fixing the number of channels is resolved. Second, an efficient convolution is selected depending on the size of the activation. Since MMA is a fixed, it may be more efficient for normal convolution than depthwise separable convolution depending on memory access overhead. Thus, a convolution type is decided according to output stride to increase network depth. In addition, memory access time is minimized by processing operations only in L3 cache. Lastly, reliable contexts are extracted using the extended atrous spatial pyramid pooling (ASPP). The suggested method gets stable features from an extended path by increasing the kernel size and accessing consecutive data. In addition, it consists of two ASPPs to obtain high quality contexts using the restored shape without global average pooling paths since the layer uses MMA as a simple adder. To verify the proposed method, an experiment is conducted using perfsim, a timing simulator, and the Cityscapes validation sets. The proposed network can process an image with 640 x 480 resolution for 6.67 ms, so six cameras can be used to identify the surroundings of the vehicle as 20 frame per second (FPS). In addition, it achieves 73.1% mean intersection over union (mIoU) which is the highest recognition rate among embedded networks on the Cityscapes validation set.

Keywords: Edge network, embedded network, MMA, matrix multiplication accelerator and semantic segmentation network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 469