Comparison of Pedestrian Detectors for LiDAR Sensor Trained on Custom Synthetic, Real and Mixed Datasets.

Deep learning algorithms for object detection used in autonomous vehicles require a huge amount of labeled data. Data collecting and labeling is time consuming and, most importantly, in most cases useful only for a single specific sensor application. Therefore, in the course of the research which is presented in this paper, the LiDAR pedestrian detection algorithm was trained on synthetically generated data and mixed (real and synthetic) datasets. The road environment was simulated with the application of the 3D rendering Carla engine, while the data for analysis were obtained from the LiDAR sensor model. In the proposed approach, the data generated by the simulator are automatically labeled, reshaped into range images and used as training data for a deep learning algorithm. Real data from Waymo open dataset are used to validate the performance of detectors trained on synthetic, real and mixed datasets. YOLOv4 neural network architecture is used for pedestrian detection from the LiDAR data. The goal of this paper is to verify if the synthetically generated data can improve the detector's performance. Presented results prove that the YOLOv4 model trained on a custom mixed dataset achieved an increase in precision and recall of a few percent, giving an F1-score of 0.84.

Removal of Pb(II), Cd(II) and Ni(II) Ions from Groundwater by Nonthermal Plasma.

The removal of Pb(II), Cd(II) and Ni(II) ions from aqueous solutions by means of nonthermal plasma with a dielectric barrier discharge is investigated. Aqueous solutions with metal ion concentrations from 10 to 100 mg/dm3 in spring water were used. In the first stage, the optimization of the solution flow rate, generator modulation frequency and duty cycle was made in terms of the removal efficiency of the considered metals. The removal was then investigated as a function of the number of passes of the solution through the cold plasma reactor. The effect of the initial concentration of ions in the solution was studied. Techniques such as composite central design, least squares method and Fourier transform infrared spectroscopy were used. The physical and chemical parameters of the solutions, such as electrical conductivity, pH, temperature, concentration of metal ions and the content of other substances (e.g., total organic carbon), were measured, and the presence of microorganisms was also examined. It was found that each pass of the solution through the cold plasma reactor causes a decrease in the concentration of Cd(II) and Ni(II); the concentration of Pb(II) drops rapidly after one pass, but further passes do not improve its removal. The removal percentage was 88% for Cd(II) after six passes and 72% for Pb(II) after one pass, whereas 19% for Ni(II). The purification mechanism corresponds to the precipitation of metal ions due to the increasing pH of the solution after exposure to cold plasma.

Multisensory Testing Framework for Advanced Driver Assistant Systems Supported by High-Quality 3D Simulation.

ADAS and autonomous technologies in vehicles become more and more complex, which increases development time and expenses. This paper presents a new real-time ADAS multisensory validation system, which can speed up the development and implementation processes while lowering its cost. The proposed test system integrates a high-quality 3D CARLA simulator with a real-time-based automation platform. We present system experimental verifications on several types of sensors and testing system architectures. The first, open-loop experiment explains the real-time capabilities of the system based on the Mobileye 6 camera sensor detections. The second experiment runs a real-time closed-loop test of a lane-keeping algorithm (LKA) based on the Mobileye 6 line detection. The last experiment presents a simulation of Velodyne VLP-16 lidar, which runs a free space detection algorithm. Simulated lidar output is compared with the real lidar performance. We show that the platform generates reproducible results and allows closed-loop operation which, combined with a real-time collection of event information, promises good scalability toward complex ADAS or autonomous functionalities testing.

MLK4 regulates DNA damage response and promotes triple-negative breast cancer chemoresistance.

Chemoresistance constitutes a major challenge in the treatment of triple-negative breast cancer (TNBC). Mixed-Lineage Kinase 4 (MLK4) is frequently amplified or overexpressed in TNBC where it facilitates the aggressive growth and migratory potential of breast cancer cells. However, the functional role of MLK4 in resistance to chemotherapy has not been investigated so far. Here, we demonstrate that MLK4 promotes TNBC chemoresistance by regulating the pro-survival response to DNA-damaging therapies. We observed that MLK4 knock-down or inhibition sensitized TNBC cell lines to chemotherapeutic agents in vitro. Similarly, MLK4-deficient cells displayed enhanced sensitivity towards doxorubicin treatment in vivo. MLK4 silencing induced persistent DNA damage accumulation and apoptosis in TNBC cells upon treatment with chemotherapeutics. Using phosphoproteomic profiling and reporter assays, we demonstrated that loss of MLK4 reduced phosphorylation of key DNA damage response factors, including ATM and CHK2, and compromised DNA repair via non-homologous end-joining pathway. Moreover, our mRNA-seq analysis revealed that MLK4 is required for DNA damage-induced expression of several NF-кB-associated cytokines, which facilitate TNBC cells survival. Lastly, we found that high MLK4 expression is associated with worse overall survival of TNBC patients receiving anthracycline-based neoadjuvant chemotherapy. Collectively, these results identify a novel function of MLK4 in the regulation of DNA damage response signaling and indicate that inhibition of this kinase could be an effective strategy to overcome TNBC chemoresistance.

Application of a Prototype Thermoplastic Treatment Line in Order to Design a Thermal Treatment Process of Forgings with the Use of the Heat from the Forging Process.

The global production of die forgings is an important branch of the motor industry for obvious reasons, resulting from the very good mechanical properties of the forged products. The expectations of the recipients, beside the implementation of the forging process, include also a range of supplementary procedures, such as finishing treatment including shot blasting, thermal treatment, and machining, in order to ensure the proper quality of the provided semi-product or the ready detail for the assembly line. Especially important in the aspect of the operational properties of the products is the thermal treatment of the forgings, which can be implemented in many variants, depending on the expected results. Unfortunately, a treatment of this type, realized separately after the forging process, is very time and energy-consuming; additionally, it significantly raises the production costs due to the increased energy consumption resulting from the necessity of repeated heating of the forgings for such thermal treatment. The article reviews the most frequently applied (separately, after the forging process) thermal treatments for die forgings together with the devices/lines assigned for them, as well as presents an alternative (thermoplastic) method of forging production with the use of the forging heat. The paper also presents a prototype semi-industrial controlled cooling line developed by the authors, which allows the development of the assumed heat treatment of forgings directly after forging with the use of forging heat, together with sample results of conducted tests.

[Brachial plexus tumors--neurosurgical treatment]. / Nowotwory splotu ramiennego--taktyka postepowania neurochirurgicznego.

Tumours of the brachial plexus according to present classification are included to soft tissue tumours. Because of rare occurrence of these tumours diagnostic and operative experience is relatively small. There is also a few number of publications regarding tumours of the brachial plexus. Therefore the aim of the study was to present our experience in the surgical treatment of tumours of the brachial plexus basing on the material of 5 cases treated in the years 1997-2001. There were 4 males and 1 female, age from 17 to 58 years old. Four patients were under 27 years old. In 3 cases tumours of the brachial plexus invaded the spinal canal through the intervertebral foramen and caused spinal cord compression (type A). In 2 cases tumours involved only plexus elements (type B). In 2 cases tumours were associated with neurofibromatosis type II. Five cases of neural sheath tumours included 2 schwannomas, 2 neurofibromas and 1 schwannoma malignum. All patients underwent surgery. In case of schwannomas and neurofibromas the surgical removal was radical without impairment of brachial plexus function. In case of a giant schwannoma malignum tumor, which caused flaccid paresis and symptoms of insufficient blood, supply with severe pain in the upper limb radical extirpation was also possible. In type A tumours in the first stage intraspinal part of the tumor was removed. Follow up observation lasted from 3 months to 4 years. The result of treatment of benign tumours was very good with complete function recovery of the upper limb, pain disappearance and no symptoms of recurrence in the long postoperative period. In case of malignant schwannoma in the early postoperative period both pain and symptoms of blood supply disturbances completely disappeared. The patient died 12 months after the operation because of tumor dissemination. Benign tumours of the brachial plexus can be effectively surgically treated using microsurgical techniques and, if necessary, nerve grafting. In case of malignant tumours many authors also recommend surgery with optimal sparing of the brachial plexus function and subsequent radio and chemotherapy. Low number A few cases in our series makes impossible to draw any epidemiological conclusions.