Traffic Density Classification for Multiclass Vehicles Using Customized Convolutional Neural Network for Smart City

The concept of smart transportation systems is increasingly becoming critical in addressing the challenges posed by an increasing number of mega cities in both developed and developing regions in maintaining safety, smooth traffic flow, and an environmentally friendly and sustainable urban environment. The Government of Zimbabwe deregulated its transport sector in the early 1990s. This development ushered in the informal public transport operators, locally referred to as ‘kombis'. Major cities such as Harare are characterised by a disjointed and chaotic urban public transport system. The major problems are the impacts this has on the quality of the environment. Currently, the urban public transport system is contributing greatly to both air and noise pollution within the confines of the city, especially in the Central Business Districts. The problem is further exacerbated by the massive importation of used vehicles from outside the country. These developments have resulted in high emission rates of major air pollutants resulting in a deterioration of the ambient air quality especially in the major cities such as Harare. Transportation is a major source of air pollutants. Vehicles are probably the largest single source of pollutants such as hydrocarbons, nitrogen dioxide and carbon monoxide. Other harmful emissions include as lead, benzene, arsenic, aldehydes, sulphates, particulate matter and the secondary creation of ozone. In Harare the number of registered vehicles increased from 192 901 in 1994 to 292 862 and by August 1999 showing that the increase in the number of vehicles is mostly in the cities. This chapter seeks to explore how smart transportation system can be adopted in Harare, the capital city of Zimbabwe. Harare was purposefully selected as it is experiencing rapid urbanization and motorization in the country. Using documentary analysis, discourse analysis and textual analysis, the chapter also describes and examines the challenges, constraints and opportunities of adopting smart urban transportation system in Harare. From this chapter the major conclusions are that the main problem associated with this rapid growth in vehicle population in the major cities is increase concentration of line and area emission sources due to traffic congestion at peak times. The stock of vehicles is quite old and they lack emission control equipment. Major constraints and limitations are observed in the current pieces of legislation. For example, the current Atmospheric Pollution Prevention Act (1971) does not require vehicles to be fitted with emission control equipment. Most of the vehicles use leaded fuel resulting in emission of the dangerous lead particulate matter in the urban areas. There is therefore an urgent need to design and implement air pollution control measures in the urban areas of the country. It is also critical to develop smart and eco-friendly transportation infrastructures so as to achieve sustainable urban communities. The integration of transportation, land use and decision making is also critical in the achievement of smart transport.

SummaryMany e‐business or social network servers have been constructed on cloud. On such open environments, private data of massive users have to be protected by encrypting, such as using Advanced Encryption Standard (AES), and furthermore, this process must be finished in a short time for users' better experience. This gives huge pressure on cloud servers, especially common servers, such as web servers. We urgently need an inexpensive and highly efficient method to relieve cloud servers' pressure. Fortunately, many cores of a graphics processing unit (GPU) can undertake this hard mission because of stronger computing power and lower price. The GPU environments can be virtualized on demand by cloud through the vCUDA technology. Of course, for those clouds not equipped with a GPU, a central processing unit (CPU) can still work as multithreads in parallel. Thus, in a cloud, AES can be parallelized using many cores of a GPU or multicores of a CPU with high efficiency and low cost. For typical cloud applications, such as web services, there are massive users and each one has short plaintext. If we simply parallelize AES in such an application, we cannot obtain better performance because of the GPU's extra data transferring cost. Thus, we coalesce the massive users' data and cut these data into same‐length slices for improving the performance of parallel AES as much as possible. So we design six parallel AES algorithms using GPU parallelism or CPU parallelism, which differ in parallel scope and whether data are coalesced or cut to slices. Specifically, they are coalescent and sliced GPU (GCS), coalescent and unsliced GPU, uncoalescent GPU, coalescent and sliced CPU, coalescent and unsliced CPU, and uncoalescent CPU. Moreover, we implement them on two representative platforms and evaluate their performance. Through comparing their performance, GCS has the best performance among these algorithms. In a cloud with Nvidia GPUs, GCS is a more powerful algorithm for massive users' data encrypting, relatively. Copyright © 2015 John Wiley & Sons, Ltd.

Graphics processing units function well as high performance computing devices for scientific computing. The non-standard processor architecture and high memory bandwidth allow graphics processing units (GPUs) to provide some of the best performance in terms of FLOPS per dollar. Recently these capabilities became accessible for general purpose computations with the CUDA programming environment on NVIDIA GPUs and ATI Stream Computing environment on ATI GPUs. Many applications in computational science are constrained by memory access speeds and can be accelerated significantly by using GPUs as the compute engine. Using graphics processing units as a compute engine gives the personal desktop computer a processing capacity that competes with supercomputers. Graphics Processing Units represent an energy efficient architecture for high performance computing in flow simulations and many other fields. This document reviews the graphic processing unit and its features and limitations.

In recent days number of vehicles is increasing day by day, especially in metropolitan cities. As vehicles increases, traffic density also increases on the road, that results us in slowing the speed, it takes more time to reach the destination, increases in vehicle queuing. If there is no control over traffic signals there may chance of getting accidents also. Improvement in the traffic control is required to overcome all these problems. Traditional traffic control system is not enough to control the current traffic density; traffic control system requires some enhancement to the existing system to avoid the traffic congestion. In the proposed work Intelligent Traffic Control System using Global System for Mobile communication (GSM) is used to overcome the congestion on the roads. The density of the vehicles is obtained by connecting the IR sensors. And depending on the density of the vehicles the traffic light signals are controlled by the microcontroller. The vehicles can also change the route if the traffic is heavy in the current route and information regarding heavy traffic is provided to vehicles in advance through the GSM.

Implementation of Image Enhancement Algorithms and Recursive Ray Tracing using CUDA

The Smith Waterman algorithm for sequence alignment is one of the main tools of bioinformatics. It is used for sequence similarity searches and alignment of similar sequences. The high end Graphical Processing Unit (GPU), used for processing graphics on desktop computers, deliver computational capabilities exceeding those of CPUs by an order of magnitude. Recently these capabilities became accessible for general purpose computations thanks to CUDA programming environment on Nvidia GPUs and ATI Stream Computing environment on ATI GPUs. Here we present an efficient implementation of the Smith Waterman algorithm on the Nvidia GPU. The algorithm achieves more than 3.5 times higher per core performance than previously published implementation of the Smith Waterman algorithm on GPU, reaching more than 70% of theoretical hardware performance. The differences between current and earlier approaches are described showing the example for writing efficient code on GPU.

Network coding has recently been widely applied in various networks for system throughput improvement and/or resilience to network dynamics. However, the computational overhead introduced by the network coding operations is not negligible and has become the cornerstone for real deployment of network coding. In this paper, we exploit the computing power of contemporary Graphic Processing Units (GPUs) to accelerate the network coding operations. We proposed three parallel algorithms that maximize the parallelism of the encoding and decoding processes, i.e., the power of GPUs is fully utilized. This paper also shares our optimization design choices and our workarounds to the challenges encountered in working with GPUs. With our implementation of the algorithms, we are able to achieve up to 12 times of speedup over the highly optimized CPU counterpart, using the NVIDIA GPU and the Computer Unified Device Architecture (CUDA) programming model.

In the process of electromagnetic interference sources imaging using parabolic reflection, the existing equipment can only collect the electromagnetic intensity information but it is difficult to directly obtain the phase information. In this paper, we have implemented the combination of the gerchberg-saxton algorithm and the transport-of-intensity equation algorithm for wideband phase retrieval on a NVIDIA's graphics processing unit(GPU) with MATLAB to achieve speedup in computation. The efficiency of GPU based implementation is measured and compared with the algorithm on CPU. The results with GPU show performance enhancement over a factor of 9.07 compared with CPU for an image of size 2048×2048 sampling points.

A Lattice-Boltzmann solver for 3D fluid simulation on GPU

In this paper we evaluate the potential for using an NVIDIA graphics processing unit (GPU) to accelerate high precision integer multiplication, addition, and subtraction. The reported peak vector performance for a typical GPU appears to offer good potential for accelerating such a computation. Because of limitations in the on-chip memory, the high cost of kernel launches, and the nature of the architecture's support for parallelism, we used a hybrid algorithmic approach to obtain good performance on multiplication. On the GPU itself we adapt the Strassen FFT algorithm to multiply 32KB chunks, while on the CPU we adapt the Karatsuba divide-and-conquer approach to optimize application of the GPU's partial multiplies, which are viewed as "digits" by our implementation of Karatsuba. Even with this approach, the result is at best a factor of three increase in performance, compared with using the GMP package on a 64-bit CPU at a comparable technology node. Our implementations of addition and subtraction achieve up to a factor of eight improvement. We identify the issues that limit performance and discuss the likely impact of planned advances in GPU architecture.

Background/Objectives: Scalability in the Internet of Things is meant for future extension in Internet connected devices. The scalability can be classified into two broad sense in terms of future flexibility i.e., vertical and horizontal scalability and in terms of infrastructure of the Internet of things i.e., device, communication, gateway, and server levels. Novelty: In this article, a novel taxonomy of scalability is proposed and presented according to infrastructure and it is categorized into four levels i.e., device, gateway, communication,and server levels. Moreover, a performance analysis of vertical scalability is conducted at the server level for a smart campus transportation system on a custom-based emulator developed in Visual Studio. Findings: From the results,it is observed that by increasing the load the response time of the server increases. And by scaling up, response time decreases. By scaling up at a certain limit and increasing the load, response time again increases. It is strongly believed that this research will help in assessing the capacity of present and future smart systems. Keywords: Internet of things; vertical scalability; horizontal scalability; smart campus; smart transport system

Abstract- With the rapid growth of urban populations and the increasing number of vehicles on the road, traffic congestion has become a significant problem in metropolitan areas. Conventional traffic control systems, which rely on pre-set signal timers, often fail to address real-time traffic conditions effectively, leading to inefficient traffic flow, increased fuel consumption, and environmental degradation. The paper “Smart Traffic Control System Based on Traffic Density Using YOLO” introduces a novel approach to address this issue by integrating artificial intelligence and computer vision into traffic management. The proposed system utilizes the YOLO (You Only Look Once) object detection algorithm to detect and classify vehicles in real-time from live video feeds captured at intersections. YOLO, known for its speed and accuracy in object detection tasks, calculates the vehicle density in each direction. Based on the detected density, the system dynamically adjusts the green light duration for each lane, ensuring that the direction with higher traffic receives longer green light periods. This method aims to optimize signal switching and minimize overall vehicle wait time. The paper outlines the complete architecture of the system, which includes modules for video input processing, vehicle detection using YOLO, traffic density computation, and adaptive signal timing control. By leveraging deep learning, the system enhances decision-making capabilities without relying on costly hardware like inductive loops or infrared sensors. This review evaluates the effectiveness and innovation of the proposed system, comparing it with traditional and sensor-based models. It highlights the advantages of using YOLO, such as real-time processing, high accuracy, and scalability. Additionally, the review discusses the system’s limitations, such as dependency on video clarity and environmental conditions, and proposes areas for future enhancement, including integration with cloud computing and edge AI for broader deployment. Keywords- Smart Traffic Control System, YOLO Object Detection, Traffic Density Estimation, Real-Time Traffic Monitoring, Adaptive Traffic Signal Control, Vehicle Classification ( Cars, Bikes, Buses, Trucks, Rikshaws), Intelligent Transportation System.

We propose the first graphics processing unit (GPU) solution to compute the 2D constrained Delaunay triangulation (CDT) of a planar straight line graph (PSLG) consisting of points and edges. There are many existing CPU algorithms to solve the CDT problem in computational geometry, yet there has been no prior approach to solve this problem efficiently using the parallel computing power of the GPU. For the special case of the CDT problem where the PSLG consists of just points, which is simply the normal Delaunay triangulation (DT) problem, a hybrid approach using the GPU together with the CPU to partially speed up the computation has already been presented in the literature. Our work, on the other hand, accelerates the entire computation on the GPU. Our implementation using the CUDA programming model on NVIDIA GPUs is numerically robust, and runs up to an order of magnitude faster than the best sequential implementations on the CPU. This result is reflected in our experiment with both randomly generated PSLGs and real-world GIS data having millions of points and edges.

Modern computing paradigms, such as cloud computing, are increasingly adopting GPUs to boost their computing capabilities primarily due to the heterogeneous nature of AI/ML/deep learning workloads. However, the energy consumption of GPUs is a critical problem. Dynamic Voltage Frequency Scaling (DVFS) is a widely used technique to reduce the dynamic power of GPUs. Yet, configuring the optimal clock frequency for essential performance requirements is a non-trivial task due to the complex nonlinear relationship between the application’s runtime performance characteristics, energy, and execution time. It becomes more challenging when different applications behave distinctively with similar clock settings. Simple analytical solutions and standard GPU frequency scaling heuristics fail to capture these intricacies and scale the frequencies appropriately. In this regard, we propose a data-driven frequency scaling technique by predicting the power and execution time of a given application over different clock settings. We collect the data from application profiling and train the models to predict the outcome accurately. The proposed solution is generic and can be easily extended to different kinds of workloads and GPU architectures. Furthermore, using this frequency scaling by prediction models, we present a deadline-aware application scheduling algorithm to reduce energy consumption while simultaneously meeting their deadlines. We conduct real extensive experiments on NVIDIA GPUs using several benchmark applications. The experiment results have shown that our prediction models have high accuracy with the average RMSE values of 0.38 and 0.05 for energy and time prediction, respectively. Also, the scheduling algorithm consumes 15.07% less energy as compared to the baseline policies.

Convolutional Neural Networks (CNNs) require massive parallelism due to the high-precision floating-point arithmetic operations they perform. So, demand of processing power in them is significantly higher than what a standard CPU can offer. This has traditionally made CNNs more suited for running on a Graphics Processing Unit (GPU). However, GPUs consume much more power than CPUs, rendering the former impractical for implementing CNNs in Edge AI (Artificial Intelligence), where restraining power consumption is paramount. On the other hand, FPGAs (Field Programmable Gate Arrays) are more suited for AI computing at the edge as they consume much lesser power than GPUs and even CPUs. Additionally, GPUs and CPUs are not suited for real-time AI applications, which require both high throughput and low latency at the same time and FPGAs excel at all these requirements. The purpose of this paper is to provide a study of the performance of FPGA as the most suitable platform for AI-based computing at the edge. To achieve this, we chose AlexNet, a popular CNN image classifier, for which we present a case study on four different platforms: CPU, GPU, embedded RISC core, and FPGA fabric. Then, we quantitatively measure and compare the performance in terms of inference time (time needed to classify an image) on all these platforms. Inference time using FPGA is reduced by almost 64, 1.6, and 1.1 times compared to a dual-core ARM, an i5-6400 CPU, and an Nvidia GPU, respectively.