Search

Deep neural networks have proven to excel classical medical image reconstruction techniques. Some networks are based on fully connected (FC) layers to achieve domain transformation such as from the data acquisition domain to the image domain. However, FC layers result in huge numbers of parameters which take a lot of GPU memory. Hence, they do not scale well, and the overall performance is limited. For ultrasound computed tomography (USCT) application, we propose a memory-efficient convolutional network that reconstructs images from the frequency domain to image domain with much less parameters compared with multilayer perceptron, by using data-driven learning. Extensive experiments demonstrate that our method achieves high reconstruction quality. It improves the structural similarity measure (SSIM) from 0.73 to 0.99 when compared with state-of-the-art reconstruction methods in this field while reduces 2/3 parameters when compared with deep neural network with FC layers to reconstruct images from frequency domain to image domain.

Network security has become an important issue in our work and life. Hackers' attack mode has been upgraded from normal attack to APT( Advanced Persistent Threat, APT) attack. The key of APT attack chain is the penetration and intrusion of active directory, which can not be completely detected via the traditional IDS and antivirus software. Further more, lack of security protection of existing solutions for domain control aggravates this problem. Although researchers have proposed methods for domain attack detection, many of them have not yet been converted into effective market-oriented products. In this paper, we analyzes the common domain intrusion methods, various domain related attack behavior characteristics were extracted from ATT&CK matrix (Advanced tactics, techniques, and common knowledge) for analysis and simulation test. Based on analyzing the log file generated by the attack, the domain attack detection rules are established and input into the analysis engine. Finally, the available domain intrusion detection system is designed and implemented. Experimental results show that the network attack detection method based on the analysis of domain attack behavior can analyze the log file in real time and effectively detect the malicious intrusion behavior of hackers , which could facilitate managers find and eliminate network security threats immediately.

Ultrasound Computed Tomography (USCT) is a new high resolution imaging method with high potential for breast cancer detection. USCT image reconstruction requires the iterative solution of a wave equation and its adjoint, being very time-consuming. To address this time consumption problem, a convolutional neural network with frequency pressure field as input is presented, outperforming classical iterative optimization strategies to solve the inverse problem. The Optical and Acoustic Breast Phantom Database (OA-Breast) is used to generate simulated USCT data using paraxial approximation forward model both for training and testing. Extensive experiments demonstrate that our neural network outperforms the classical strategies both in reconstruction time and quality.

Raw data of point cloud is often noisy and with\ud topological defects (such as holes), which cause problems including faulty connection and inaccurate structure. As\ud a result, the surface reconstruction of point cloud data is\ud a highly challenging problem. This work proposes a novel\ud method, which improves the surface quality compared with\ud existing methods. Our method combines both the local detailed\ud features and the global topological information during the\ud reconstruction process. To facilitate the feature refinement,\ud we first pre-process the point cloud data by relocating each\ud point, upsampling the point data, and optimizing normals to\ud enhance the features and geometric details. We then identify\ud the topological information by segmenting the geometry and\ud constructing curve skeletons for each part and guide the surface reconstruction with the skeletons by minimal user interaction. We demonstrate the effectiveness of our methods with various examples, where our reconstruction can fill out missing data and preserve sharp features.

Reducing energy consumption of buildings has become an effective way of mitigating carbon footprint because of the high energy intensity of the building sector. Retrofitting existing buildings to be more energy efficient is an integral part of an energy efficient building sector given the slow construction rate of new buildings. In this study, an optimization model for building envelope retrofit is presented to help decision makers to obtain an optimal retrofit plan with a given budget. The envelope components considered for retrofit are windows, walls and roof. Installation of a PV power supply system is also built into the optimization model in view of the rich solar resource in South Africa. An additional objective of this study is to obtain at least a grade D rating from the established energy performance certificate (EPC) program in South Africa to ensure the continued suitability of the building with respect of the EPC standard and green building policy. A case study of a public office building in South Africa is carried out to illustrate the effectiveness and benefits of the model presented.

To successfully prepare drug delivery system, nanoparticles (NPs) with simple and effective method avoiding use of potentially toxic solvent and components. Baicalin was chosen as a model low molecular weight chemotherapeutic drug and baicalin-loaded NPs were prepared with choosing baicalin as the parcel drugs, chitosan to pack and TPP to solidify. The resultant baicalin NPs had a spherical structure with a diameter about 316 nm. The encapsulation efficiency of baicalin NPs is 91.01 ± 2.13%. The loading capacity is 13.22 ± 1.28%.This study suggested that the NP will be used as a potential carrier of low molecular weight chemotherapeutic drug and has many advantages.

This paper proposes a novel feature fusion method for the protein subcellular multiple-site localization prediction. Several types of features are employed in this novel protein coding method. The first one is the composition of amino acids. The second is pseudo amino acid composition, which mainly extract the location information of each amino acid residues in protein sequence. Lastly, the information for local sequence of amino acids is taken into consideration in this research. Generally, k nearest neighbor, supporting vector machine and other methods, has been used in the field of protein subcellular localization prediction. In our research, the multi-label k nearest neighbor algorithm has been employed in the classification model. The overall accuracy rate may reach 66.7304% in Gnos-mploc dataset.

This paper focuses on using a TI's DSP to design an AC electricity acquisition module, which can accomplish the function of distributed synchronous AC electrical parameters sampling. The hardware diagram of the design used a DSP and other auxiliary devices to set up an AC electricity acquisition module with the ability of high frequency distributed simultaneous electrical parameters sampling. Specifically, a GPS was mounted on the module to synchronize sampling between different modules and a SD card was employed to store the collected data. Regarding the software design, a PC control/monitor program was developed. The electricity acquisition terminal is capable of 200KHz simultaneous sampling when it works without SD card while it is verified that the highest sample frequency is 10KHz when it works with a SD card.

The advances in the modeling and control methodologies of heavy haul trains are reviewed from energy efficiency perspective. The developments in railway systems are also reviewed as background of the train modeling and control problem. Until present, there exist two types of models: physical principle model and data-driving model. As far as the control methods are concerned, two different classifications are presented in this paper. One is to classify them into transient control and cruise control according to the focused process. The other is to classify them into switching control and action control according to the framework of the control methods.