Search

Human activity recognition (HAR) is a key technology in many applications, such as smart signage, smart healthcare, smart home, etc. In HAR, deep learning-based methods have been proposed to recognize activity data effectively from video streams. In this paper, the end-to-end model based on convolutional long short-term memory (LSTM) is proposed to recognize human activities. Convolutional LSTM can learn features of spatial and temporal simultaneously from video stream data. Also, the number of learning weights can be diminished by employing convolutional LSTM with an end-to-end model. The proposed HAR model was optimized with various simulation environments using activities data from the AI hub. From simulation results, it can be confirmed that the proposed model can be outperformed compared with the conventional model.

For decoding high-resolution image stored in external memory after lossless compression, it is inevitable necessary to allow variable-length data types and this may decreases the efficiency in real time read of arbitrary compressed macro block without burst-mode in memory. This paper proposes a cache architecture for a video decoder that has a burst mode capability for accessing lossless compressed frame data in the memory. In the proposed cache architecture, the write and read caches employ the concept of fixed-length burst groups, allowing efficient burst write and read operations. The experimental results show that the proposed cache architecture can decrease memory access times by an average of 70.92%

This study examined ethical ways to use welfare technology in a situation where the demand for non-face-to-face welfare services using Cloud based healthcare systems had increased rapidly in caring for elderly people who live alone. Through focus group interviews with social workers related to the care of elderly people who live alone, in-depth interviews were conducted on the current situation, problems, ethical issues, and development directions arising in the implementation of welfare technology. The main areas of interest were focused on improving safety in caring them using IoT technology and enhancing emotional support in preventing lonely deaths using companion robot and AI speaker. Issues such as the need for individualization, client-centeredness, privacy, self-determination, competence, informed consent, right to know, convenience, and advocacy were identified as important ethical considerations related to use of welfare technology. The research results suggested that various stakeholders should participate in the development of ethical indicators and welfare technology for the ethical use of welfare technology.

The development of wireless communication technology and mobile devices has brought about the advent of an era of sharing text data that overflows on social media and the web. In particular, social media has become a major source of storing people’s sentiments in the form of opinions and views on specific issues in the form of unstructured information. Therefore, the importance of emotion analysis is increasing, especially with machine learning for both personal life and companies’ management environments. At this time, data reliability is an essential component for data classification. The accuracy of sentiment classification can be heavily determined according to the reliability of data, in which case noise data may also influence this classification. Although there is stopword that does not have meaning in such noise data, data that does not fit the purpose of analysis can also be referred to as noise data. This paper aims to provide an analysis of the impact of profanity data on deep learning-based sentiment classification. For this purpose, we used movie review data on the Web and simulated the changes in performance before and after the removal of the profanity data. The accuracy of the model trained with the data and the model trained with the data before removal were compared to determine whether the profanity is noise data that lowers the accuracy in sentiment analysis. The simulation results show that the accuracy dropped by about 2% when judging profanity as noise data in the sentiment classification for review data.

We propose a multi-threaded algorithm that can improve the performance of geometric acoustic (GA)-based sound propagation algorithms in mobile devices. In general, sound propagation algorithms require high computational cost because they perform based on ray tracing algorithms. For this reason, it is difficult to operate sound propagation algorithms in mobile environments. To solve this problem, we processed the early reflection and late reverberation steps in parallel and verified the performance in four scenes based on eight sound sources. The experimental results showed that the performance of the proposed method was on average 1.77 times better than that of the single-threaded method, demonstrating that our algorithm can improve the performance of mobile devices.

In a computing environment, higher resolutions generally require more memory bandwidth, which inevitably leads to the consumption more power. This may become critical for the overall performance of mobile devices and graphic processor units with increased amounts of memory access and memory bandwidth. This paper proposes a lossless compression algorithm with a multiple differential pulse-code modulation variable sign code Golomb-Rice to reduce the memory bandwidth requirement. The efficiency of the proposed multiple differential pulse-code modulation is enhanced by selecting the optimal differential pulse code modulation mode. The experimental results show compression ratio of 1.99 for high-efficiency video coding image sequences and that the proposed lossless compression hardware can reduce the bus bandwidth requirement.

The importance of the IoT is increasing in every field of life, and it especially has a significant role in improving the efficiency of the healthcare system. Its demand further increased during COVID-19 to facilitate the patient remotely from their home digitally. Every time the COVID-19 patient visited the doctor for minor complications, it increased the risk of spreading the virus and the cost for the patient. Another alarming situation arose when a patient was in a critical position and may not claim an emergency service from the nearby healthcare system, increasing the death rate. The IoT uses healthcare services to properly monitor COVID-19 patients by using the interconnected network to overcome these issues. Through the IoT, the patient is facilitated by the health care system without spreading the virus, decreasing the death ratio during COVID-19. This paper aims to discuss different applications, technologies, and challenges of the IoT healthcare system, related to COVID-19. Different databases were searched using keywords in PubMed, ResearchGate, Scopus, ACM, Springer, Elsevier, Google Scholar, etc. This paper is trying to discuss, identify, and highlight the useful applications of the IoT healthcare system to provide guidelines to the researchers, healthcare institutions, and scientists to overcomes the hazards of COVID-19 pandemics. Hence, IoT is beneficial by identifying the symptoms of COVID-19 patients and by providing better treatments that use the healthcare system efficiently. At the end of the paper, challenges and future work are discussed, along with useful suggestions through which scientists can benefit from the IoT healthcare system during COVID-19 and in a severe pandemic. The survey paper is not limited to the healthcare system and COVID-19, but it can be beneficial for future pandemics or in a worse situation.

This paper proposes a high-throughput lossless image-compression algorithm based on Golomb–Rice coding and its hardware architecture. The proposed solution increases compression ratios (CRs) while preserving the throughput by taking advantage of a novel parallel variable-length sign coding (PVSC) algorithm that reduces the sign bits to achieve a higher CR. In addition, the proposed solution adopts and modifies the two existing compression algorithms to improve the overall compression performance. The experimental results show that the proposed solution yields an average CR of 3.12, which is higher than those achieved with the previous algorithms. The hardware implementation of the proposed solution for an $8 \times 8$ block unit achieves a throughput of 18 GBps and 24 GBps when encoding and decoding, respectively. This hardware performance is enough to handle $7680\times 4320$ @240-Hz image processing.

With the advancement of semiconductor and information and communication technologies, our computing environments are evolving into complex, large-scale, and high-performance platforms. Especially, this movement is characterized as hyper-connected society, in which IoT and cloud computing are core technologies. The Parse Server is a full feature, production ready Parse Platform on the Cloud. It could be an optimal platform for IoT service by providing open-source back-end services for developers with a set of tools to enable front-end development focus. In this paper, Parse Server is interoperable with an open source based game and a single board computer to develop use cases for the purpose of IoT programming education. This research aims to get insights of methodology for IoT programming with implementation of game ranking service and remote sensing systems. Implementation results were confirmed with Parse Dashboard and Rasberry Pi.

In this paper, we propose a lossless compression architecture with less memory bandwidth. For this purpose, the compression ratio is improved with the prediction function using multiple differential pulse-code modulation algorithm which performs the variable sign code Golomb-rice encoding algorithm with entropy coding. For performance evaluation, several experiments were performed on 4k image sequences on the proposed architecture. The results show that it achieved an average compression ratio of 1.67 on the benchmarks.

This paper proposes a novel object tracking and recognition system according to reliability assessment of learning in mobile environments. The proposed method is based on marker-less tracking, and the proposed system is composed of two main modules (detection and tracking). The detection module identifies an object to be matched on the current frame corresponding to the database, and then generates the standard object information that has the best reliability of learning. This module is able to re-detect the object when the object is missing in the frame. The tracking module traces the object of interest based on the extracted object information using feature points, descriptors, sub-window of object, and its histogram. Additionally, this module tries to select the reliable object between tracked object by Camshift and tracked object by Optical flow. Experimental results show that the proposed method is more robust than the traditional methods, and that it is able to recognize and track objects of interest with reliability assessment of learning for use with mobile environments.

Currently, the paradigm shift in our computing is dramatically moving from PC to mobile devices and many new services are emerging based on the development of broadband network and hardware technologies such as Cloud computing and Web of things. Especially, the popularity of smart devices has increased the demand for sharing multimedia contents at anywhere and on any of user devices with seamless display. In this paper, we introduce a prototype implementation of contents sharing service working on different devices with seamless connectivity. The purpose is that the proposed system allows users to share their media contents and play them continuously regardless of the situation of switching from one device to another. For example, N-screen services allow users to manage their active sessions among multiple devices having different capabilities and architectures. The system implemented has the basic sharing configuration of three devices: PC, Smartphone, and Tablets, and utilize an Open Service Platform based on RESTful Web Services. The prototype was successfully implemented and its performance was simulated with sample 3D videos with different file sizes to estimate load latencies while switching from one device to another. The result shows the feasibility of contents sharing system based on RESTful Web Services with low latency on Smartphone.

In recent years the global popularity of Korean Wave is increasing in entertainment areas and spreading to other regions of the world. As a result, there have been many organizations formed to support its creative industries; at the same time, the field of the satisfaction and perceived effectiveness of them has emerged as an important issue. This paper introduces a method of measuring the influence and marketing effect of organizations for Korean Wave Events and Festivals. For this purpose a classical test theory of Cronbach’s alpha is utilized. The feasibility of measuring results is also ensured by exploratory factor analysis. The result shows 0.7 or higher alpha values and could provide suggestions to establish a theory of events and festivals for organizations by active follow-up studies for resolving will-less different results in this field due to a lack of the proceeding research.

In this paper, we focus on a dynamically selective performance optimization method for mobile 3D graphics applications under n-screen service environment. Thus, an effective solution to enhance the performance is required to support real time processing under limited network bandwidth. This method can be employed to apply quality loss techniques that trade the quality within the range of tolerance over performance. First, we describe performance optimization methods for mobile graphics applications in 2 dimensions: Graphic Processing Unit (GPU) performance and image quality. Second, we present an adaptive level-of-detail (LOD) configuration method for graphics applications via OpenGL ES API level. Third, we show how OpenGL ES library hooking method can be employed to apply quality loss techniques that trade quality over performance. Last, we argue that OpenGL ES library hooking method is crucial to achieve higher performance, since it can be used in common android phones without any source code modification of applications. Overall, the experimental result shows that the proposed technique allows 24 % of performance improvement for all applied methodologies, and 4 % improvement for some selected methodologies while causing around 14 and 2 % of quality degradation, respectively. Thus, our approach can support an acceptable trade-off by determining the level of reduced quality that would lead to the desired performance improvements of the mobile GPU.

Stereo vision has become an important technical issue in the field of 3D imaging, machine vision, robotics, image analysis, and so on. The depth map extraction from stereo video is a key technology of stereoscopic 3D video requiring stereo correspondence algorithms. This is the matching process of the similarity measure for each disparity value, followed by an aggregation and optimization step. Since it requires a lot of computational power, there are significant speed-performance advantages when exploiting parallel processing available on processors. In this situation, multi-core CPU may allow many parallel programming technologies to be realized in users computing devices. This paper proposes parallel implementations for calculating disparity map using a shared memory programming and exploiting the streaming SIMD extension technology. By doing so, we can take advantage both of the hardware and software features of multi-core processor. For the performance evaluation, we implemented a parallel SAD algorithm with OpenMP and SSE2. Their processing speeds are compared with non parallel version on stereoscopic streaming video. The experimental results show that both technologies have a significant effect on the performance and achieve great improvements on processing speed.

Analysis of human emotion plays an important role in interaction between human and machine communication. The most expressive way to extract and understand of human emotion is by facial expression analysis. This paper proposes a novel recognition method of multiple emotions from facial expression running on mobile environments. Especially, we formulate the classification model of facial ambiguous emotions using a variance of the estimated facial feature points. First, we extract 65 landmark points from input stream using active appearance model, and we then analyze the changes of the values of the feature points to recognize a facial emotion by comparing with fuzzy k-NN classification. Finally, five types of the emotions are recognized and classified as a facial expression. To evaluate the proposed approach, we assess the ratio of success with iPhone camera views, and we achieve the best 93% accuracy in the experiments. The results show that the proposed method performed well in the recognition of facial emotion on mobile environments, and the implementation system can be represented by one of the example for augmented reality on displaying combination of real face video and virtual animation with user’s avatar.

In this paper, a new method is proposed for recognizing rotated objects based on extracted feature points from the Harris corner detector using object corner points at real time in a mobile environment. With this proposed method, corner points can be rapidly extracted from the input image and object recognition can be conducted by comparing existing feature points. Color values for corner pixels in the feature points of rotated objects are generally varied in accordance with the degree of object rotation. The color values of the feature points are affected by the degree of rotated objects; therefore, there is a possibility that these values can be mixed with nearby pixel values. By analyzing the color values of the rotated pixels, we can extract feature points of rotated objects and use them for object detection to be effectively applied for rotated object detection. Although overall recognition rate is somewhat degraded, using the proposed object recognition with corner information of feature points makes it possible to execute in real time in mobile environments by reducing the amount of computation. Accordingly, this method can be applied to recognizing rotated objects, even in a mobile environment with limited computing capabilities. Experimental results show that the proposed method can provide approximately 96 % accuracy and high performance compared to other methods. Therefore, the proposed method can be adapted to recognize any rotated object with performance and accuracy.

The main purpose of this research is to design a new memory architecture for NAND flash memory to provide XIP (execute in place) for code execution as well as overcome the biggest bottleneck for data execution. NOR flash for multimedia application is particularly well suited for code storage and execute-in-place (XIP) applications, which requires high-speed random access. While NAND flash provides high density and low cost data storage, it is not applicable to XIP applications due to the page access and long access latency. To overcome these limitations, NAND flash can be exploited as code memory for XIP by using SDRAM/SRAM buffer. In order to design the code memory, we proposed a NAND flash with a dual instruction buffer. Furthermore, another enhancement was proposed for the overall system performance by applying a data buffer system to the existing NAND flash memory to reduce the number of write and erase operations; otherwise which could be the biggest bottleneck in a flash memory system. In conclusion, the proposed NAND flash buffer system based on Harvard architecture is operated as main memory as well as the lowest storage device for mobile multimedia system. According to our simulation results, write and erase operations are approximately 60 % and 68 % less than other unified buffer systems, respectively, with two times more space. In addition, the average memory access time is improved by approximately 75 % compared with other unified buffer systems.

For the ubiquitous computing environment, an important assumption is that all the components in any specific environment are connected with each other. With this assumption, we introduce an effective scheme to provide a personalized service based on Virtual Personal World (VPW). Virtual Personal World (VPW) which is a model focused on service continuity with specially designed components. Previous ubiquitous frameworks have been concerned with the location where a user is provided any specific service. However those questions above are not the most important problems anymore in VPW. It concentrates on the point whether the services are successive or not, wherever a user goes to any place. Services are not regarded as a sum of functions which is embedded on any objects in any certain place. We conceptually define a resource management scheme based on a unified form of the object which participates in service provision, so called virtual object (VO). Thus the service can be described as the sum of functions of VOs. With our resource management scheme, users can utilize their required object as VO wherever it is located. And also, for better utilization of VPW service, we introduce a novel form of profiles and service provision scheme based on the polymorphism. Our simulation result shows that the Ratio of VPW pure service time is 0.15 % higher than conventional location based service. And also the possibility that users can meet adequate service he wants raised 29 % in our proposed VPW environment.

" # $ " % " $% # $ $ " " $ !& #" " ' ( ) *+,,- " . "% # " # # "/ # !" " #" "! " $ 0 ' $ ! $ # % " % % $ $ ! #! # 12 & Keywords : Image based Augmented Reailyt, Image Metadata, JPEG AR, Standard Metadata Format ※ 교신저자(Corresponding Author): Je-Ho Park 접수일:2013년 12월 05일, 수정일:2014년 02월 22일완료일:2014년 04월 21일* 극동대학교 스마트모바일학과 ** 단국대학교 컴퓨터과학과 Tel: +82-10-9031-9282 email: dk_jhpark@dankook.ac.kr*** 건국대학교 컴퓨터과학과 **** 남서울대학교 컴퓨터학과***** 단국대학교 전자전기공학부▣ 본 연구는 문화체육관광부 및 한국콘텐츠진흥원의 2012년 콘텐츠산업기술지원사업 지원에 의해 수행되었음. !"#$%&'( )*+ ,-., /0 12 3- 45627!89:; %?@A )*+89B C*+ D-.D6 2 45- 45627!EFGHI.+ JK( CLMNOPQRS TUV+ JK(WX #LYZPH[ #\]^_V`8aH@bcdA C*+ D-!Bef Cgh(ijkl+ ghQmFn o#f (. )*+ ,-!B*+gh+ JK(p ;= COP"#L:qr T ([@sE tQ un ?@bvdAHwE )*+Bxy\]^Cz{|}~(Hn ?# €w@‚: u #89FGH@bƒdA #\

In this study, an object contour tracking method is proposed for an object with large motion and irregular shape in image sequence. To track object contour accurately, an active contour model was used, and the initial snake point of the next frame is set by defining feature points with changing curvature in the object tracked from the previous frame and calculating an optical flow at the location. Here, any misled optical flow due to irregular changes in shape or fast motion was filtered by producing a difference edge map from the previous frame, and as a solution to the energy shortage of objects with complex contour, a method of adding snake points by partial curvature was applied. Findings from experiments with real image sequence showed that the contour of an object with large motion and irregular shapes was extracted in a relatively precise way.

Multimedia system-on-a-chip (SoC) platform designs nowadays are facing some conflicting issues regarding product development. One is induced by increasing design complexity and another is induced by decreasing time-to-market. Hence, designers are seeking a more efficient and reliable methodology in order to design complex multi-million gate SoC under such harsh conditions. In particular, the complexity of a generic pin control block in multimedia SoC which implements input/output (I/O) paths for off-chip communication has increased exponentially in recent years. Accordingly, the possibility of introducing human errors in designing such block has grown. Operation of generic-pin control block needs to be validated with a top-level RTL from the early stages of design, which correctly checks full-chip interface. However, generic-pin control block has inherent several design issues since function registers and multi-I/O paths are usually fixed in the relatively late stages of design. Also, the role of a generic pin control block that shares limited pins causes frequent changes in pin assignment. Therefore, current design approaches of a generic pin control block are no longer adequate to meet the challenges of design productivity, design reusability, and shorter time-to-market for design. And, this results in many possible human errors when using a traditional RTL description. As a response to this problem, this paper presents a design automation based approach to reduce the possibility of human errors. In the case study presented, we succeeded in auto-generating a generic pin control block in multimedia SoC platforms which has more than 300 general purpose I/O interfaces including both input and output, as well as 900 PAD pins. Ultimately, we reduced the amount of manual description for generating a generic pin control block by a whopping 97 %.

Detection of facial feature is fundamental for applications such as security, biometrics, 3D face modeling and personal authentication. Active Shape Model (ASM) is one of the most popular local texture models for face detection. This paper presents an issue related to face detection based on ASM, and proposes an efficient extraction algorithm for facial landmarks suitable for use on mobile devices. We modifies the original ASM to improve its performance with three changes; (1) Improving the initialization model using the center of the eyes by using a feature map of color information, (2) Constructing modified model definition and fitting more landmarks than the classical ASM, and (3) Extending and building a 2-D profile model for detecting faces in input image. The proposed method is evaluated on dataset containing over 700 images of faces, and experimental results reveal that the proposed algorithm exhibited a significant improvement of over 10.2 % in average success ratio, compared to the classic ASM, clearly outperforming on success rate and computing time.

The purpose of this research is to propose an efficient management scheme for Virtual Personal World (VPW) which is a model focused on service continuity of personal world. Previous ubiquitous frameworks have been concerned with where is the user is serviced and what services can be offered in that space. However those questions above are not the most important problems anymore in VPW. We also introduce a management scheme for the real world object based on the concept of Virtual Objects (VO). As users can use some services unique way with various VOs, VPW framework creates User-Generated services automatically. It helps users to satisfy their specific personalized services. Our proposed manage scheme of user-generated service increases generation of service about seven times than a scheme without generation. Consequently, we find generated services encourage user satisfaction. We simulate the possibility that a user takes proper service which is not needed generation newly.

In recent years, the significance of greenhouses has been increased greatly because the world has been facing serious problems with energy as its growing demand. At the same time, home automation systems have been steadily gaining popularity; growing toward smart home based on Cloud technology. This paper introduces a cost-effective home energy saving system based on a small embedded system with remote controlling feature. For this purpose, the system is composed of a wireless router based on embedded Linux for the platform to develop a low-cost energy control server and a smart phone for remote light control app. The prototype system was implemented by porting OpenWrt onto the wireless router which is connected with an interface board with LEDs attached. The remote access and GUI function were implemented by TCP/IP programming using Apple iPhone. The operation of the remote control system was verified by socket communication between the smart phone and the wireless router, and by USB communication between the wireless router and the interface board. The implementation result shows that an OpenWrt-based wireless router can give benefits of saving energy and safety through lighting control.

Many peer-to-peer (p2p) systems have been studied in distributed, ubiquitous computing environments. Distributed hash table (DHT)-based p2p systems can improve load-balancing even though locality utilization and user mobility are not guaranteed. We propose a mobile locality-based hierarchical p2p overlay network (MLH-Net) to address locality problems without any other services. MLH-Net utilizes mobility features in a mobile environment. MLH-Net is constructed as two layers, an upper layer formed with super-nodes and a lower layer formed with normal-nodes. The simulation results demonstrate that MLH-Net can decrease discovery routing hops by 13% compared with JXTA and 69% compared with Chord. It can decrease the discovery routing distance by 17% compared with JXTA and 83% compared with Chord depending on the environment.

The mVoIP service is the technology which focuses on the wireless data service as the IP network having the transmission rate of 100 Mbps classes on the high-speed middle of movement through the WiFi, WiBro and 3G mobile radio communication network, and etc. and is developed. Since 2010, the mVoIP (mobile VoIP) service shows the rapid growth due to 4G-LTE service seriously disclosed from July with the Smart phone and 2,011 it begins to be rapidly popularized. In this research, additionally the mVoIP service industry activation plan is presented with the trends of technology development including the chip-set/module/terminal, etc. based upon local and foreign market trend searchlight through the market demand analysis. The mVoIP service downloads App to the mobile apparatus and or can provide the service as the software through the WiFi network. Therefore, the change which is large in the products development aspect is to be have no. Expected to is being provided as the added service in the case of 4G-LTE as a matter of course, the service deployment where it is based on the market principle and demand needs is needed.

The objective of this research is to design a highperformance NAND flash memory system containing a buffer system. The proposed instruction buffer in the NAND flash memory consists of two parts, that is, a fully associative temporal buffer for temporal locality and a fully associative spatial buffer for spatial locality. A spatial buffer with a large fetching size turns out to be effective for serial instructions, and a temporal buffer with a small fetching size is devised for branch instructions. Simulation shows that the average memory access time of the proposed system is better than that of other buffer systems with four times more space. The average miss ratio is improved by about 70% compared with that of other buffer systems.

A noteworthy thing in desktop PCs is that they can provide a great opportunity to increase the performance of processing multimedia data by exploiting task- and data-parallelism with multi-core CPU and many-core GPU. This paper presents a high performance parallel implementation of 2D DCT on this heterogeneous computing environment. For this purpose, Intel TBB (threading building blocks) and OpenCL (Open Compute Language) are utilized for task- and data-parallelism, respectively. The simulation result shows that the parallel DCT implementations far the serial ones in processing speed. Especially, OpenCL implementation shows a linear speedup, a typical SIMD characteristic as the increase of 2D data sets.

In this paper, we propose a stack allocation technique of Android Java objects in order to reduce the number of garbage collection which is one of major reason on Android performance degradation when running applications. The proposed technique is to allocate Java objects into stack rather than heap memory. To do so, stacked objects could escape the garbage collection process. We experiment the proposed technique in the latest Android 2.3 version. For the simulation, we take advantage of the well known Java benchmark, Caffeinemark, and our own. The result shows the performance degradation of Dalvik Virtual Machine execution time caused by the stack allocation of Java objects is very slight and the proposed method considerably reduces the frequency of garbage collection. This will increase application performance and give better user interfaces to Android phone users.

The rapid advance of computer hardware and popularity of multimedia applications enable multi-core processors with sub-word parallelism instructions to become a dominant market trend in desk-top PCs as well as high end mobile devices. This paper presents an efficient parallel implementation of 2D convolution algorithm demanding high performance computing power in multi-core desktop PCs. It is a representative computation intensive algorithm, in image and signal processing applications, accompanied by heavy memory access; on the other hand, their computational complexities are relatively low. The purpose of this study is to explore the effectiveness of exploiting the streaming SIMD (Single Instruction Multiple Data) extension (SSE) technology and TBB (Threading Building Block) run-time library in Intel multi-core processors. By doing so, we can take advantage of all the hardware features of multi-core processor concurrently for data- and task-level parallelism. For the performance evaluation, we implemented a 3?×?3 kernel based convolution algorithm using SSE2 and TBB with different combinations and compared their processing speeds. The experimental results show that both technologies have a significant effect on the performance and the processing speed can be greatly improved when using two technologies at the same time; for example, 6.2, 6.1, and 1.4 times speedup compared with the implementation of either of them are suggested for 256?×?256, 512?×?512, and 1024?×?1024 data sets, respectively.

Chord is a peer-to-peer look up algorithm based on a distributed hash table protocol in wired IP networks, exploiting the advantage of scalability for large-scale of distributed applications. However, deploying Chord into mobile networks should be inherently accompanied with supplementary network traffics to maintain the hash key mapping rules because of a high rate of joining and leaving nodes. This paper proposes an enhanced reactive Chord for mobile networks, which can reduce network traffics and achieve fast lookup services. For this purpose, a conventional Chord is modified to act reactively, and then the table activity checking feature is devised into it, called enhanced reactive Chord. Simulation results show that the proposed Chord can decrease network traffics by an average of 41.3% maintaining same setup latency, compared with conventional Chord in mobile networks.

A DHT(Distributed Hash Table) based P2P is a method to overcome disadvantages of the existing unstructured P2P method. If a DHT algorithm is used, it can do a fast data search and maintain search efficiency independent of the number of peer. The peers in the DHT method send messages periodically to keep the routing table updated. In a mobile environment, the peers in the DHT method should send messages more frequently to keep the routing table updated and reduce the failure of a request. Therefore, this results in increase of network traffic. In our previous research, we proposed a method to reduce the update load of the routing table in the existing Chord by updating it in a reactive way, but the reactive method had a disadvantage to generate more traffic than the existing Chord if the number of requests per second becomes large. In this paper, we propose an adaptive method of routing table update to reduce the network traffic. In the proposed method, we apply different routing table update method according to the number of request message per second. If the number of request message per second is smaller than some threshold, we apply the reactive method. Otherwsie, we apply the existing Chord method. We perform experiments using Chord simulator (I3) made by UC Berkeley. The experimental results show the performance improvement of the proposed method compared to the existing methods.

In this paper, a new high performance data cache scheme that improves exploitation of both the spatial and temporal locality is proposed. The proposed data cache consists of a hardware prefetch unit and two sub-caches such as a direct-mapped (DM) cache with a large block size and a fully associative buffer with a small block size. Spatial locality is exploited by fetching and storing large blocks into a direct mapped cache, and is enhanced by prefetching a neighboring block when a DM cache hit occurs. Temporal locality is exploited by storing small blocks from the DM cache in the fully associative buffer according to their activity in the DM cache when they are replaced. Experimental results on Spec2000 programs show that the proposed scheme can reduce the average miss ratio by and the AMAT by compared to the previous schemes such as direct mapped cache, 4-way set associative cache and SMI(selective mode intelligent) cache[8].

A new scan partition architecture to reduce both the average and peak power dissipation during scan testing is proposed for low-power embedded systems. In scan-based testing, due to the extremely high switching activity during the scan shift operation, the power consumption increases considerably. In addition, the reduced correlation between consecutive test patterns may increase the power consumed during the capture cycle. In the proposed architecture, only a subset of scan cells is loaded with test stimulus and captured with test responses by freezing the remaining scan cells according to the spectrum of unspecified bits in the test cubes. To optimize the proposed process, a novel graph-based heuristic to partition the scan chain into several segments and a technique to increase the number of don’t cares in the given test set have been developed. Experimental results on large ISCAS89 benchmark circuits show that the proposed technique, compared to the traditional full scan scheme, can reduce both the average switching activities and the average peak switching activities by 92.37% and 41.21%, respectively.

This paper proposes an efficient caching mechanism appropriate for the integrated RFID middleware which can integrate wireless sensor networks (WSNs) and RFID (radio frequency identification) systems. The operating environment of the integrated RFID middleware is expected to face the situations of a significant amount of data reading from RFID readers, constant stream data input from large numbers of autonomous sensor nodes, and queries from various applications to history data sensed before and stored in distributed storages. Consequently, an efficient middleware layer equipping with caching mechanism is inevitably necessary for low latency of request-response while processing both data stream from sensor networks and history data from distributed database. For this purpose, the proposed caching mechanism includes two optimization methods to reduce the overhead of data processing in RFID middleware based on the classical cache implementation polices. One is data stream cache (DSC) and the other is history data cache (HDC), according to the structure of data request. We conduct a number of simulation experiments under different parameters and the results show that the proposed caching mechanism contributes considerably to fast request-response times.

A contents correction signature hashing scheme for fast string matching algorithm in high performance network intrusion detection systems is proposed. The objective is to design a highly scalable pattern matching system suitable for wide spreading similar varieties of malicious behaviors in network. Simulation results show the proposed method maintains the hash table evenly compared with general hash table and shows high scalability as the increase of signatures and 130% of performance gain compared with SNORT.

This paper proposes a data cache with small space for low power, but high performance on multimedia applications. The basic architecture is a split-cache consisting of a direct-mapped cache with small block size (DMC) and a fully-associative buffer with large block size (FAB). To overcome the disadvantage caused by small cache areas, two hardware mechanisms are enhanced considering the operational behaviors of multimedia applications: an adaptive multi-block prefetching to initiate various fetch sizes for FAB and an efficient block filtering to remove the data likely to be rarely reused for DMC. The simulations on MediaBench show that the proposed 5kB cache can achieve up to 57% and 50% of power saving while providing almost equal and better performance compared with the 16kB 4-way set associative cache and 17kB stream caches, respectively.

This paper proposes high performance coprocessor architecture for real time dense disparity computation based on a phase-based binocular stereo matching technique called local weighted phase-correlation(LWPC). The algorithm combines the robustness of wavelet based phase difference methods and the basic control strategy of phase correlation methods, which consists of 4 stages. For parallel and efficient hardware implementation, the proposed architecture employs SIMD(Single Instruction Multiple Data Stream) architecture for each functional stage and all stages work on pipelined mode. Such that the newly devised pipelined linear array processor is optimized for the case of row-column image processing eliminating the need for transposed memory while preserving generality and high throughput. The proposed architecture is implemented with Xilinx HDL tool and the required hardware resources are calculated in terms of look up tables, flip flops, slices, and the amount of memory. The result shows the possibility that the proposed architecture can be integrated into one chip while maintaining the processing speed at video rate.

Current rendering processors are aiming to process triangles as fast as possible and they have the tendency of equipping with multiple rasterizers to be capable of handling a number of triangles in parallel for increasing polygon rendering performance. However, those parallel architectures may have the consistency problem when more than one rasterizer try to access the data at the same address. This paper proposes a consistency-free memory architecture for sort-last parallel rendering processors, in which a consistency-free pixel cache architecture is devised and effectively associated with three different memory systems consisting of a single frame buffer, a memory interface unit, and consistency-test units. Furthermore, the proposed architecture can reduce the latency caused by pixel cache misses because the rasterizer does not wait until cache miss handling is completed when the pixel cache miss occurs. The experimental results show that the proposed architecture can achieve almost linear speedup upto four rasterizers with a single frame buffer.

This paper introduces a prototype design and implementation of contents sharing service application on networked heterogeneous devices. This is because users need to share their media contents and play them continuously by switching from one device to another with the wide spreading mobile devices. For example, N-Screen services allow users to manage their active sessions among multiple devices having different capabilities and architectures. In this paper, the basic sharing configuration consists of three devices: PC, Smartphone, and Tablets. The application was implemented with RESTful web services and an open service platform. The prototype was successfully implemented and its performance was simulated on sample 3D video with different file sizes to minimize load latency when changing devices. The latency was decreased greatly on Smartphone from 1.6 to 0.9 seconds being compared with the one before.

Nowadays, inter-program level jumps in digital broadcasting programs have been a major source of sound nuisance. Therefore, control of loudness becomes one of the most important audio issues. In early days of digital audio, the level of a given piece of audio was determined by measuring sample-peak level. Later, the concept of perceived loudness was introduced. In this paper, we introduce a system design for audio level measurement based on ITU- R BS.1770-3 in order to measure true-peak audio level. The system board is designed with TMS320C6727 Floating Point Digital Signal Processor (DSP).

One of the most effective ways to improve cache performance is to exploit both temporal and spatial locality given by any program executional characteristics. This paper proposes a data cache with small space for low power but high performance on multimedia applications. The basic architecture is a split-cache consisting of a direct-mapped cache with small block sire and a fully-associative buffer with large block size. To overcome the disadvantage of small cache space, two mechanisms are enhanced by considering operational behaviors of multimedia applications: an adaptive multi-block prefetching to initiate various fetch sizes and an efficient block filtering to remove rarely reused data. The simulations on MediaBench show that the proposed 5KB-cache can provide equivalent performance and reduce energy consumption up to 40% as compared with 16KB 4-way set associative cache.

Newly emerging non-volatile memory's future is promising and challenging because its performance and power consumption has been improved significantly. The performance improvement triggers these to be a major part of the today's generation computer systems in replacing main memory specially. This research particularly focuses on the page fault and page swap management via Operating System (OS) in order to improve the performance by employing unified memory system (UMS). This proposes, merging of conventional main memory and storage into a single memory layer, called as Unified Memory System. Also the proposed module is designed virtually in two zones, static zone and dynamic zone to support conventional memory management. For this, we analyze the operating system memory management behavior and its tendency to manage the non-volatile UMS through OS kernel for improving system performance. Avoiding data duplication between main memory and storage and frequent page faults are the major concern of this research, unlike a conventional DRAM main memory based system. We utilize phase change memory (PCM) as a suitable candidate for constructing UMS, because of its high density and non-volatility features. We depict the significant number of reduced page faults and execution improvement which will support the fast booting of the systems in near future.