Abstract:To detect the occurrence of ionospheric scintillation in the equatorial region, a coherent/non-coherent integration method is adopted on the accumulation of intermediate frequency (IF) signal and local code, in the process of signal acquisition based on software receiver. The processes of polynomial fitting and sixth-order Butterworth filtering are introduced to detrend the tracking results. Combining with ionospheric scintillation detection algorithm and preset thresholds, signal acquisition and tracking, scintillation detection, positioning solution are realized under the influence of strong iono-spheric scintillation. Under the condition that the preset threshold of amplitude and carrier phase scintillation indices are set to 0.5 and 0.15, and the percentage of scintillation occurrence is 50%, respectively, PRN 12 and 31 affected by strong amplitude scintillation are detected effectively. Results show that the positioning errors in the horizontal direction are below 5m approximately. The software receiver holds performances of accurate acquisition, tracking and positioning on the strong ionospheric scintillation conditions, which can provide important basis and helpful guidance for relevant research on ionospheric scintillation, space weather and receiver design with high performance.

Abstract:Classification of garbage is of paramount importance prior to process them to categorise physically and this process helps to manage wastes by maintaining pollution free environment. Many systems that have capability segregate garbage are on the rise, but efficient and accurate segmentation with recognition mechanisms draw the attention of researchers. A computer vision approach for classifying garbage into respective recyclable categories could be one of the effective and economical ways of processing waste. This project mainly focused on capturing real-time images of a single piece of garbage and classifying it into three divisions: paper, or metal, or biodegradable (food) waste. Each garbage class contains around 2000 images obtained from an open-source dataset and images collected from Google and personally collected custom images. The developed intelligent models provide the effectiveness of the machine and deep learning in classification with structural and nonstructural data. The model used was a Convolutional Neural Network (CNN) named YOLOv5. The project showcased vision based approach capable of maintaining an accuracy of 61%. The CNN was not trained to its maximum capacity due to the difficulty of finding optimal hyperparameters, as most of the images were gathered from Google Images.

Abstract:According to recent research statistics, approximately 30% of people who experienced falls are over the age of 65. Therefore, it is meaningful research to detect it in time and take appropriate measures when falling behavior occurs. In this paper, a fall detection model based on improved human posture estimation algorithm is proposed. The improved human posture estimation algorithm is implemented on the basis of Openpose. An improved strategy based on depthwise separable convolution combined with HDC structure is proposed. The depthwise separable convolution is used to replace the convolution neural network structure, which makes the network lightweight and reduces the re-dundant layer in the network. At the same time, in order to ensure that the image features are not lost and ensure the accuracy of detecting human joint points, HDC structure is introduced. Experiments show that the improved algorithm with HDC structure has higher accuracy in joint point detection. Then, human posture estimation is applied to fall detection research, and fall event modeling is carried out through fall feature extraction. The designed convolution neural network model is used to classify and distinguish falls. The experimental results show that our method achieves 98.53%, 97.71% and 97.20% accuracy on three public fall detection data sets. Compared with the experimental results of other methods on the same data set, the model designed in this paper has a certain improvement in system accuracy. The sensitivity is also improved, which will reduce the error detection probability of the system. In addition, this paper also verifies the real-time performance of the model. Even if researchers are experimenting with low-level hardware, it can ensure a certain detection speed without too much delay.

Abstract:Guillotine machines are used to cut bulk quantities of paper, often thousands at a time. More the number of papers to be cut at once, more load is required to cut. This machine undergoes a frequent failure of one of its hinges, which prevents the operation of the machine. A combination of torsional forces and bending moments are acting on the hinge when operating. Torsional stresses induced due to the friction between the contacting surfaces of the crank rod and the hinge. The bending moment induced due to the alternating motion and the load acted upon the cutting mechanism. The crank transforms the rotational movement into a translational motion of the blade, which results in the formation of a cyclic load in the form of a sinusoidal with a mean value not equal to zero. This leads to fail the hinge in the mode of fatigue. Naked eye observations of the fracture surface reviled a clear failure initiation point and striation marks of crack propagation and a sudden fracture region which evident a fatigue failure due to cyclic loading. To redesign the failed hinged to avoid such failure, it is essential to, (i) define and evaluate the stresses developed by the combined loading condition (ii) understand the nature of the cyclic stress induced. The force acting on the hinge was calculated by the law of conservation of momentum created by the blades' inertia and its' supportive structure. It was understood that the mean stress value of the cyclic load is not equal to zero, the modified Goodman diagram is used. Computational simulations are conducted using Finite Element Analysis (FEA) on the ANSYS fatigue tool. By applying the fatigue analysis theories and conducting FEA for stress analysis, the reason for the failure is revealed and then necessary precautions could be taken to prevent such failures in the future.

Abstract:Building extraction from high resolution remote sensing image is a key technology of digital city construction[14]. In order to solve the problems of low efficiency and low precision of traditional remote sensing image segmentation, an improved U-Net network structure is adopted in this paper. Firstly, in order to extract efficient building characteristic information, FPN structure was introduced to improve the ability of integrating multi-scale information in U-Net model; Secondly, to solve the problem that feature information weakens with the deepening of network depth, an efficient residual block network is introduced; Finally, In order to better distinguish the target area and background area in the image and improve the precision of building target edge detection, the cross entropy loss and Dice loss were linearly combined and weighted. Experimental results show that the algorithm can improve the image segmentation effect and improve the image accuracy by 18%.

Abstract:This paper proposed an improved Naïve Bayes Classifier for sentimental analysis from a large-scale dataset such as in YouTube. YouTube contains large unstructured and unorganized comments and reactions, which carry important in-formation. Organizing large amounts of data and extracting useful information is a challenging task. The extracted information can be considered as new knowledge and can be used for decision-making. We extract comments from YouTube on videos and categorized them in domain-specific, and then apply the Naïve Bayes classifier with improved techniques. Our method provided a decent 80% accuracy in classifying those comments. This experiment shows that the proposed method provides excellent adaptability for large-scale text classification.

Abstract:2022 9th International Symposium on Test Automation & Instrumentation (ISTAI 2022) will be held in Beijing in October 2022, it is sponsored by both China Instrumentation & Control Society (CIS) and Beijing Information Science and Technology University. The Theme will be “Bionic perception, quantum sensing, intelligent service”. It aims to promote the development of automation technology with informatization and intelligence, and to enhance the exchanges and cooperation between domestic academia/industries and in-ternational counterparts. The symposium warmly welcomes scholars, students, academics, researchers to contribute, and participate in the symposium to exchange the latest achievements of testing and instrumen-tation technology with peers from all over the world. The accepted papers will be published on the IET open access research Journal of Engineering and in-cluded in both IET Digital Library and IEEE Xplore Digital Library, EI indexed.