Crime is a major social problem in the United States, threatening public safety and disrupting the economy. Understanding patterns in criminal activity allows for the prediction of future high-risk crime “hot spots”...
详细信息
ISBN:
(纸本)9781538631218
Crime is a major social problem in the United States, threatening public safety and disrupting the economy. Understanding patterns in criminal activity allows for the prediction of future high-risk crime “hot spots” and enables police precincts to more effectively allocate officers to prevent or respond to incidents. With the ever-increasing ability of states and organizations to collect and store detailed data tracking crime occurrence, a significant amount of data with spatial and temporal information has been collected. How to use the benefit of massive spatial-temporal information to precisely predict the regional crime rates becomes necessary. The recurrent neural network model has been widely proven effective for detecting the temporal patterns in a time series. In this study, we propose the Spatio-Temporal neural network (STNN) to precisely forecast crime hot spots with embedding spatial information. We evaluate the model using call-for-service data provided by the Portland, Oregon Police Bureau (PPB) for a 5-year period from March 2012 through the end of December 2016. We show that our STNN model outperforms a number of classical machine learning approaches and some alternative neural network architectures.
The electrocardiogram (ECG) has become a standard tool to measure and record the electrical activities of the heart because of its low-cost and non-invasive characteristic. Applications running on smart phones or tabl...
详细信息
ISBN:
(纸本)9781467388450
The electrocardiogram (ECG) has become a standard tool to measure and record the electrical activities of the heart because of its low-cost and non-invasive characteristic. Applications running on smart phones or tablets have been widely used for collecting and processing ECG signals, with the prevalence and massive availability of health related mobile applications. However, these applications have the disadvantage of relative small mass storage and relative poor computing ability, especially in Human-computer interaction user experience. To achieve rapid Heart Rate Variability (HRV) analysis based on big physiological data, a novel HRV analysis system has been developed based on LeanCloud cloud platform and web application. The cloud platform can store and process mass raw ECG signals. Computing intensive signal processing tasks were implemented in Python code. The HRV analysis results displayed on the web achieve good interactivity by using Echarts. The preliminary results demonstrate that this system have strong computing ability and good Human-computer interaction user experience.
This paper studies the DC-DC buck converter response controlled by two second-order single-input control techniques: equivalent-control quantization sliding mode voltage control(QSMVC) and general sliding mode volta...
详细信息
ISBN:
(纸本)9781510842915
This paper studies the DC-DC buck converter response controlled by two second-order single-input control techniques: equivalent-control quantization sliding mode voltage control(QSMVC) and general sliding mode voltage control(SMVC). Simulations illustrate the behaviors of the equivalent-control based SMVC system under uniform and logarithmic quantized state feedback. The output voltage and inductor current of both models were studied and compared under normal conditions, load step change, load linear variation, and input voltage step change. It shows that the equivalent-control QSMVC system performs better than the general SMVC system in terms of robustness and stability. The equivalent-control QSMVC system prevents the sliding mode controller from operating at a frequency that is too high for the power switch to respond. Also, by setting the value of quantization parameters the output voltage value can be greater than 5.999 V with less than 0.17% deviation from 6V.
The demand for electricity has continued to outpace the supply side since 2005, considerably effecting all consumer sectors (residential, commercial & Industrial). Since 2012, the situation has been worsen resulti...
详细信息
ISBN:
(纸本)9781538636077
The demand for electricity has continued to outpace the supply side since 2005, considerably effecting all consumer sectors (residential, commercial & Industrial). Since 2012, the situation has been worsen resulting in load shedding for several hours. In rural as well as even in some underprivileged areas of big cities such as Lahore, brown-outs for 8-12 hours daily during summer can be observed. The shortage of electricity and higher fuel prices for generators shifted the trend towards alternate energy. For Lahore-Pakistan, solar photovoltaic (PV) is the most feasible energy source for alternate clean energy which is economically more viable than petrol generators. The general concept of high initial capital cost for PV system prevents the potential users to take an initiative, however, there are ways to economically design the alternate solar PV system for critical loads. In following case-study, the results for conversion of load on solar PV-Hybrid system with economic viability are presented. Energy audits and energy conservation methodologies to reduce the size of PV system as well as its capital and operational cost are also discussed. The study explains how retrofitting the existing load with energy efficient equipment not only reduces the active load and required size of solar system but also reduces the overall price of the system including the cost of retrofitting.
Films such as Robocop, The Matrix, and Pacific Rim have explored the possibilities of using Brain-computer Interfaces (BCIs) to control machines with only thought. In this paper, we enhance the power of thought throug...
详细信息
Locative gaming dates back to the early 2000s, and with the success of Ingress (2012) and Pokémon GO (2016), locative games have now entered the mainstream in a very serious way. However, while the genre holds co...
详细信息
ISBN:
(纸本)9781538644959
Locative gaming dates back to the early 2000s, and with the success of Ingress (2012) and Pokémon GO (2016), locative games have now entered the mainstream in a very serious way. However, while the genre holds considerable promise for cultural heritage, it has yet to make a real impact for this purpose. A particular challenge is to reconcile the two apparently conflicting concerns of ensuring immersion into the experience without compromising the audience's sense of presence in the physical space. For example, Ingress and Pokémon GO offer excellent immersion in the gameplay but at the cost of near-total loss of the player's sense of presence in the physical environment, even to the extent that accidents occur. For cultural heritage, presence is not only about safety, but also about the audience experiencing the site and not only the digital content. In this paper, we argue that for locative games to be successful for cultural heritage, they must bridge the design tension between offering immersion and presence. We use two of our own titles to shed light on the design concerns and show how careful use of locative game mechanics and narrative techniques can help reconcile these two design pressures and create a new type of engagement with cultural heritage.
As the key interconnection technique of system on Chip(SoC), Network on Chip(NoC) architecture is widely used in the high-throughput and low-latency image processing system designs. In addition to the bandwidth and la...
详细信息
As the key interconnection technique of system on Chip(SoC), Network on Chip(NoC) architecture is widely used in the high-throughput and low-latency image processing system designs. In addition to the bandwidth and latency, managing congestion resulted from imbalance network load is critical to improve the system performance. In this paper, one task decomposition exploration method on FPGA-based NoC is presented. According to different parallel properties of tasks of the application, subtask graphs are generated by taking advantage of different decomposition strategies. These subtask graphs are evaluated in timing latency and energy consumption based on FPGA-based NoC emulation platform. The experiments demonstrate that the proposed task decomposition exploration can help the designer select the most appropriate task decomposition scheme based on properties of the application to balance NoC net-work load and alleviate congestion.
The wireless networks are requiring higher transmission speed and more reliable QoS, especially the 5 G systems. Different network providers will run different quality of transmission services and the user could choos...
详细信息
The wireless networks are requiring higher transmission speed and more reliable QoS, especially the 5 G systems. Different network providers will run different quality of transmission services and the user could choose the suitable set. In this work, considering the varieties of transmission types and price, we propose a novel game theoretical solution of downlink resource allocation, the fusion of different types of transmission could significantly reduce the transmission price under the constraint of system Quality of service(QoS).Simulation results prove the fact that by using our proposed game theoretical method, the price of the downlink transmission could be reduced up to 37% under the constraint of QoS, the expense is the time consumption and the signal processing delay.
Cancer is considered as one of the undefeatable diseases around the world that occur due to the uncontrollable growth of abnormal cells [1]. In 2012, according to World Health Organization (WHO) and Cancer Research UK...
详细信息
This paper proposes a Quick Locale based Convolutional system strategy (Quick R-CNN) for question recognition. Quick R-CNN expands on past work to effectively characterize ob-ject recommendations utilizing profound co...
详细信息
ISBN:
(纸本)9781538618882
This paper proposes a Quick Locale based Convolutional system strategy (Quick R-CNN) for question recognition. Quick R-CNN expands on past work to effectively characterize ob-ject recommendations utilizing profound convolutional systems. Com-pared to past work, Quick R-CNN utilizes a few in-novations to enhance preparing and testing speed while likewise expanding identification precision. Quick R-CNN trains the profound VGG16 arrange 9 quicker than R-CNN, is 213 speedier at test-time, and accomplishes a higher Guide on PASCAL VOC 2012. Contrasted with SPPnet, Quick R-CNN trains VGG16 3 quicker, tests 10 speedier, and is more exact Quick R-CNN is actualized in Python and C++ (utilizing Caffe) and is accessible under the open-source MIT Permit.
暂无评论