Using Generative Module and Pruning Inference for the Fast and Accurate Detection of Apple Flower in Natural Environments

Apple flower detection is an important project in the apple planting stage. This paper proposes an optimized detection network model based on a generative module and pruning inference. Due to the problems of instability, non-convergence, and overfitting of convolutional neural networks in the case of insufficient samples, this paper uses a generative module and various image pre-processing methods including Cutout, CutMix, Mixup, SnapMix, and Mosaic algorithms for data augmentation. In order to solve the problem of slowing down the training and inference due to the increasing complexity of detection networks, the pruning inference proposed in this paper can automatically deactivate part of the network structure according to the different conditions, reduce the network parameters and operations, and significantly improve the network speed. The proposed model can achieve 90.01%, 98.79%, and 97.43% in precision, recall, and mAP, respectively, in detecting the apple flowers, and the inference speed can reach 29 FPS. On the YOLO-v5 model with slightly lower performance, the inference speed can reach 71 FPS by the pruning inference. These experimental results demonstrate that the model proposed in this paper can meet the needs of agricultural production.

Planning for alternative road development connecting East Balikpapan - North Balikpapan

Balikpapan City is one of the largest cities in the East Kalimantan region and a city that is developing quite rapidly. These developments include a high population number accompanied by a large number of new activity growths which create a considerable traffic pull around the city center. According to the 2012-2032 City Spatial Plan for Balikpapan City, the priority plan for road development is on Outer Ring Road III and other alternative roads which will become new activity centers in Karang Joang and Manggar sub-districts in Balikpapan City. The road network currently has the highest volume of 4288 pcu / hour with an average speed of 42 km / h and reaches a VCR of 0.8 which has 35 existing roads and 17 intersections. This study intends to improve traffic performance and aims to plan an alternative road network connecting East Balikpapan with North Balikpapan. Simulation analysis uses Visum software to produce the best conditions for handling traffic in Balikpapan City arteries, collectors and local roads where the current condition of the traveler has to go through the East, South, Central and North Balikpapan District network. The method used is the calculation of existing traffic performance and simulation to determine network volume, network speed, total distance and total travel time. The simulation results with the Visum model are the best conditions of traffic performance with an average volume of 762 pcu / hour, an average network speed of 42 km / hour, a total distance of 148487 km, and a total travel time of 3369 hours.

Grounded Speed and the Soft Temporality of Network Infrastructure

This chapter offers a descriptive view of cable temporality from the perspective of network operators and those involved in system maintenance and repair. Examining the “soft temporalities” of these operators’ labor, the chapter illustrates a tension at the heart of media’s infrastructures: in many places, slowness, stability, embeddedness, and fixity of infrastructures are what enable speed and acceleration. After describing the “grounded speed” of the cable network, the chapter turns to the phenomemon of temporal irruptions: moments when the assemblage of temporal processes that enable network operation and network speed suddenly and radically changes the network.

Constructing a model for the automated operative planning of local operations at railroad technical stations

This paper has investigated the technology of forwarding local wagons at railroad technical stations and established the need to improve it given the extra downtime of local wagons. The main issue relates to the considerable combinatorial complexity of the tasks of operational planning. Another problem is that as part of the conventional approach, planning a station operation and planning a local operation at it is considered separately. Another planning issue is the lack of high-quality models for the preparation of initial data, in particular, data on the duration of technological operations, such as, for example, shunting operations involving local wagons forwarding. To resolve these issues, a new approach has been proposed, under which the tasks of operative planning of a technical station’s operation and its subsystem of local operations are tackled simultaneously, based on a single model. To this end, a mathematical model of vector combinatoric optimization has been built, which uses the criteria of total operating costs and wagon-hours spent at a station when forwarding local wagon flows, in the form of separate objective functions. Within this model, a predictive model was constructed in the form of a fuzzy inference system. This model is designed to determine the duration of shunting half-runs when executing the spotting/picking operations for delivering local wagons to enterprises’ goods sheds. The model provides for the accuracy level that would suffice at planning, in contrast to classical methods. A procedure has been devised for optimizing the planning model, which employs the modern genetic algorithm of vector optimization NSGA-III. This procedure is implemented in the form of software that makes it possible to build a rational operative plan for the operation of a technical station, including a subsystem of local operations, in graphic form, thereby reducing the operating costs by 5 % and the duration of maintenance of a local wagon by 8 %. The resulting effect could reduce the turnover time of a freight car in general on the railroad network, speed up the delivery of goods, and reduce the cost of transportation

Adaptive Streaming Server dengan FFMPEG dan Golang

Quality of experience (QoE) when accessing video streaming becomes a challenge in varieties of network bandwidth/speed. Adaptive streaming becomes an answer to gain good QoE. An architecture system of the adaptive streaming server with Dynamic Adaptive Streaming over HTTP (DASH) was proposed. The system was consists of two services e.g transcoding and streaming. Transcoding service encodes an audio file, multi-bitrates video files, and manifest.mpd files. Streaming service serves client streaming requests that appropriate to client network profiles. The system is built using the Golang programming environment and FFMPEG. Transcoding service has some execution mode (serial and concurrent) and passing mode (1 pass and 2 passes). The transcoding service test results show that concurrent execution is faster 11,5% than the serial execution and transcoding using 1 pass is faster 46,95% than 2 passes but the bitrate of output video lower than the determinate bitrate parameter. The streaming service has a good QoE. In the 5 scenarios, buffer level=0 happens 5 times, and its total duration is 64 seconds. Buffer level=0 happens when extreme changes happen in network speed from fast to too slow.

Influence of traffic flow intensity on environmental noise pollution

The modern urban environment, with the development of industry, the growth of the vehicle's number on the roads, and the increase in the density of buildings, is increasingly capable of negatively affect the health and well-being of the city's population. Among the factors influencing the environment is noise pollution, namely man-made noise - unwanted and harmful sounds created as a result of human activities. Today, noise is one of the most common factors of pollution among all others. The most common source of noise pollution is transport, including cars and trucks, buses, railways, airplanes, etc. The negative phenomenon of traffic noise is that almost everyone is greatly affected. This can often be accompanied by other harmful factors, such as vibration. According to scientific researches, noise can cause irritation under constant acoustic exposure. As a result, there are sleep disorders, decreased mental capacity, and the development of stress, and stress development in humans. Traffic noise is created from the operation of engines, the friction of wheels with the road surface, brakes, and aerodynamic features of vehicles, etc. In general, the level of traffic noise depends on such basic indicators as the intensity, speed, and composition of the traffic flow. Therefore, an important task is the study of traffic noise, its measurement, the establishment of appropriate dependencies, and further evaluation of the results. Knowing the level of noise generated by vehicles, further measures to reduce it are possible, such as redistribution of traffic flows on the road network, speed limits, improving the quality of the road surface, the use of basic means of reducing noise pollution, the use of noise protection devices, etc. Based on this, the negative impact of this phenomenon on the human body and the environment, in general, can be reduced.

Optimization of IoT-Based Sporting Goods Consumer Service Management System

With the rapid development of computer technology and information industry technology, the use of these technologies has been deeply applied to the management of various industries. Data time-sharing transmission can solve the problem that the system is not affected by the network; that is, it makes good use of the network and is not bound by the network. Even when the network speed is low or the network is not smooth, the system of each store can run normally, and when the network is smooth, the data will be uploaded in packets and automatically received by the server. The system is well designed with functional modules’ management, including sports goods import and export management, inventory management, membership management, and ledger management. System operation can well solve the coordination work between the head office and stores; the head office can master the operation of each store, check the generated ledger at any time, form statistical reports, and guide the operation status of each store so that the stores can adjust their operation methods and learn from each other at any time. The system network management can make valuable data information aggregated, rather than single data. The head office can make overall data backup promptly to provide good logistic support for each store.

Macroscopic Traffic Simulation of Autonomous Vehicle Effects

The increasing worldwide demand on urban road transportation systems requires more restrictive measures and policies to reduce congestion, time delay and pollution. Autonomous vehicle mobility services, both shared and private, are possibly a good step towards a better road transportation future. This article aims to study the expected impact of private autonomous vehicles on road traffic parameters from a macroscopic level. The proposed methodology focuses on finding the different effects of different combinations of autonomous vehicle penetration and Passenger Car Units (PCU) on the chosen road traffic model. Four parameters are studied: traveled daily kilometers, daily hours, total daily delay and average network speed. The analysis improves the four parameters differently by implementing autonomous vehicles. The parameter total delay has the most significant reduction. Finally, several mathematical models are developed for the percentage of improvement for each chosen parameter.

Improving Efficiency By Using Synchronised Parallel Data Transmission Over Wsn

As the data transmission speed and the efficiency over the wireless network depend on the network or transfer device bandwidth. After physical implementation of wireless network which is difficult to dynamically control transfer in order to get high or low data transfer rate. Dedicating the fixed network for such a dynamic requirement network is not feasible. Many researchers are trying to enhance the wireless network speed by joining the transfer speed of multiple lines which will result in to asynchronous data transfer and data leakage. Hence the proposed system is to design and implements a dynamically controllable wireless network using the multiple radio frequency wireless devices. Here the proposed system will use multiple wireless devices and transfer data over multiple line depending upon the user configuration and synchronize the data over the receiving end. It will let the user control the wireless data transmission speed as per the requirement.