A Real-Time Vehicle Detection System under Various Bad Weather Conditions Based on a Deep Learning Model without Retraining.

Numerous vehicle detection methods have been proposed to obtain trustworthy traffic data for the development of intelligent traffic systems. Most of these methods perform sufficiently well under common scenarios, such as sunny or cloudy days; however, the detection accuracy drastically decreases under various bad weather conditions, such as rainy days or days with glare, which normally happens during sunset. This study proposes a vehicle detection system with a visibility complementation module that improves detection accuracy under various bad weather conditions. Furthermore, the proposed system can be implemented without retraining the deep learning models for object detection under different weather conditions. The complementation of the visibility was obtained through the use of a dark channel prior and a convolutional encoder-decoder deep learning network with dual residual blocks to resolve different effects from different bad weather conditions. We validated our system on multiple surveillance videos by detecting vehicles with the You Only Look Once (YOLOv3) deep learning model and demonstrated that the computational time of our system could reach 30 fps on average; moreover, the accuracy increased not only by nearly 5% under low-contrast scene conditions but also 50% under rainy scene conditions. The results of our demonstrations indicate that our approach is able to detect vehicles under various bad weather conditions without the need to retrain a new model.

Gaze Tracking and Point Estimation Using Low-Cost Head-Mounted Devices.

In this study, a head-mounted device was developed to track the gaze of the eyes and estimate the gaze point on the user's visual plane. To provide a cost-effective vision tracking solution, this head-mounted device is combined with a sized endoscope camera, infrared light, and mobile phone; the devices are also implemented via 3D printing to reduce costs. Based on the proposed image pre-processing techniques, the system can efficiently extract and estimate the pupil ellipse from the camera module. A 3D eye model was also developed to effectively locate eye gaze points from extracted eye images. In the experimental results, average accuracy, precision, and recall rates of the proposed system can achieve an average of over 97%, which can demonstrate the efficiency of the proposed system. This study can be widely used in the Internet of Things, virtual reality, assistive devices, and human-computer interaction applications.

Study of Postural Stability Features by Using Kinect Depth Sensors to Assess Body Joint Coordination Patterns.

A stable posture requires the coordination of multiple joints of the body. This coordination of the multiple joints of the human body to maintain a stable posture is a subject of research. The number of degrees of freedom (DOFs) of the human motor system is considerably larger than the DOFs required for posture balance. The manner of managing this redundancy by the central nervous system remains unclear. To understand this phenomenon, in this study, three local inter-joint coordination pattern (IJCP) features were introduced to characterize the strength, changing velocity, and complexity of the inter-joint couplings by computing the correlation coefficients between joint velocity signal pairs. In addition, for quantifying the complexity of IJCPs from a global perspective, another set of IJCP features was introduced by performing principal component analysis on all joint velocity signals. A Microsoft Kinect depth sensor was used to acquire the motion of 15 joints of the body. The efficacy of the proposed features was tested using the captured motions of two age groups (18-24 and 65-73 years) when standing still. With regard to the redundant DOFs of the joints of the body, the experimental results suggested that an inter-joint coordination strategy intermediate to that of the two extreme coordination modes of total joint dependence and independence is used by the body. In addition, comparative statistical results of the proposed features proved that aging increases the coupling strength, decreases the changing velocity, and reduces the complexity of the IJCPs. These results also suggested that with aging, the balance strategy tends to be more joint dependent. Because of the simplicity of the proposed features and the affordability of the easy-to-use Kinect depth sensor, such an assembly can be used to collect large amounts of data to explore the potential of the proposed features in assessing the performance of the human balance control system.

Learning-Directed Dynamic Voltage and Frequency Scaling Scheme with Adjustable Performance for Single-Core and Multi-Core Embedded and Mobile Systems.

Dynamic voltage and frequency scaling (DVFS) is a well-known method for saving energy consumption. Several DVFS studies have applied learning-based methods to implement the DVFS prediction model instead of complicated mathematical models. This paper proposes a lightweight learning-directed DVFS method that involves using counter propagation networks to sense and classify the task behavior and predict the best voltage/frequency setting for the system. An intelligent adjustment mechanism for performance is also provided to users under various performance requirements. The comparative experimental results of the proposed algorithms and other competitive techniques are evaluated on the NVIDIA JETSON Tegra K1 multicore platform and Intel PXA270 embedded platforms. The results demonstrate that the learning-directed DVFS method can accurately predict the suitable central processing unit (CPU) frequency, given the runtime statistical information of a running program, and achieve an energy savings rate up to 42%. Through this method, users can easily achieve effective energy consumption and performance by specifying the factors of performance loss.

The complete chloroplast genome sequence of Anoectochilus roxburghii.

The complete chloroplast sequence of the Anoectochilus roxburghii, a popular traditional Chinese medicine for the treatment of cancer, was determined in this study. The chloroplast genome (cpDNA)^ was 152,802 bp in length, containing a pair of inverted repeats of 52,728 bp separated by a large single-copy region and a small single-copy region of 82,641 bp and 17,433 bp, respectively. The chloroplast genome encodes 116 predicted functional genes, including 81 protein-coding genes, four ribosomal RNA genes, and 31 transfer RNA genes, 25 of which are duplicated in the inverted repeat regions. The cpDNA is GC-rich (36.9%).

An intelligent knowledge-based and customizable home care system framework with ubiquitous patient monitoring and alerting techniques.

This study develops and integrates an efficient knowledge-based system and a component-based framework to design an intelligent and flexible home health care system. The proposed knowledge-based system integrates an efficient rule-based reasoning model and flexible knowledge rules for determining efficiently and rapidly the necessary physiological and medication treatment procedures based on software modules, video camera sensors, communication devices, and physiological sensor information. This knowledge-based system offers high flexibility for improving and extending the system further to meet the monitoring demands of new patient and caregiver health care by updating the knowledge rules in the inference mechanism. All of the proposed functional components in this study are reusable, configurable, and extensible for system developers. Based on the experimental results, the proposed intelligent homecare system demonstrates that it can accomplish the extensible, customizable, and configurable demands of the ubiquitous healthcare systems to meet the different demands of patients and caregivers under various rehabilitation and nursing conditions.

Evaluation of high solids alkaline pretreatment of rice straw.

Fresh-harvested, air-dried rice straw was pretreated at a water content of 5 g H(2)O/g straw using sodium hydroxide (NaOH) and compared to pretreatment at 10 g H(2)O/g straw by hydrated lime (Ca(OH)(2)). Full factorial experiments including parallel wash-only treatments were completed with both sources of alkali. The experiments were designed to measure the effects of alkaline loading and pretreatment time on delignification and sugar yield upon enzymatic hydrolysis. Reaction temperature was held constant at 95 degrees C for lime pretreatment and 55 degrees C for NaOH pretreatment. The range of delignification was 13.1% to 27.0% for lime pretreatments and was 8.6% to 23.1% for NaOH pretreatments. Both alkaline loading and reaction time had significant positive effects (p < 0.001) on delignification under the design conditions, but only alkaline loading had a significant positive effect on enzymatic hydrolysis. Treatment at higher temperature also improved delignification; delignification with water alone ranged from 9.9% to 14.5% for pretreatment at 95 degrees C, but there was little effect observed at 55 degrees C. Post-pretreatment washing of biomass was not necessary for subsequent enzymatic hydrolysis. Maximum glucose yields were 176.3 mg/g dried biomass (48.5% conversion efficiency of total glucose) in lime-pretreated and unwashed biomass and were 142.3 mg/g dried biomass (39.2% conversion efficiency of total glucose) in NaOH-pretreated and unwashed biomass.