Root-cause identification plays a vital role in business decision making by providing effective future directions for the organizations. Aspect extraction and sentiment extraction plays a vital role in identifying the root-causes. This paper proposes the Ensemble based temporal weighting and pareto ranking (ETP) model for Root-cause identification. Aspect extraction is performed based on rules and is followed by opinion identification using the proposed boosted ensemble model. The obtained aspects are validated and ranked using the proposed aspect weighing scheme. Pareto-rule based aspect selection is performed as the final selection mechanism and the results are presented for business decision making. Experiments were performed with the standard five product benchmark dataset. Performances on all five product reviews indicate the effective performance of the proposed model. Comparisons are performed using three standard state-of-the-art models and effectiveness is measured in terms of F-Measure and Detection rates. The results indicate improved performances exhibited by the proposed model with an increase in F-Measure levels at 1%–15% and detection rates at 4%–24% compared to the state-of-the-art models. 相似文献
Journal of Materials Science: Materials in Electronics - In the present research work, Mg-doped zinc oxide Zn0.1?xMgxO (For x?=?0.000, 0.002, 0.006, 0.010) nanoparticles were... 相似文献
Journal of Materials Science: Materials in Electronics - Present study portrays, physicochemical investigations of pristine and Pd2+ modified ZnO nanoflowers (NFs) compositional series... 相似文献
Wireless Personal Communications - This paper analyzes the performance of two-way OFDMA based cooperative device-to-device communication (C-D2D) framework in a heterogeneous cellular network. In... 相似文献
Simultaneously obtaining high efficiency and deep blue emission in organic light emitting diodes (OLEDs) remains a challenge. To overcome the demands associated with deep blue thermally activated delayed fluorescence (TADF) emitters, two deep blue TADF materials namely, DBA–BFICz and DBA–BTICz, are designed and synthesized by incorporating oxygen-bridged boron (DBA) acceptor with heteroatoms, oxygen and sulphur-based donors, BFICz and BTICz, respectively. Both TADF materials show deep blue photoluminescence emissions below 450 nm by enhancing the optical band gap over 2.8 eV through deeper highest occupied molecular orbital (HOMO) level of heteroatom based donor moieties. At the same time, the photoluminescence quantum yields (PLQYs) of both TADF materials remain over 94%. The TADF device with DBA–BFICz as an emitter exhibits a good external quantum efficiency (EQE) of 33.2%. Since both new TADF materials show deep blue emissions and high efficiencies, hyperfluorescence (HF) OLED devices are fabricated using ν-DABNA as a fluorescence dopant. DBA–BFICz as a TADF sensitized host in HF–OLED reveals an outstanding EQE of 38.8% along with narrow full width at half maximum of 19 nm in the bottom emission pure blue OLEDs. This study provides an approach to develop deep blue TADF emitters for highly efficient OLEDs. 相似文献
People communicate in a variety of ways via multimedia through the propagation of various techniques. Nowadays, variety of multimedia frameworks or techniques is used in various applications such as industries, software processing, vehicles and medical systems. The usage of multimedia frameworks in healthcare systems makes it possible to process, record and store huge amount of information generated by various medical records. However, the processing and management of huge records of every individual lead to overload the security risk and human efforts. The aim of this paper is to propose a secure and efficient technique that helps the medical organizations to process every record of individuals in a secure and efficient way. The proposed mechanism is validated against various security and processing metrics over conventional mechanisms such as Response Time, Message Alteration Record, Trusted Classification Accuracy and Record Accuracy. The analyzed results claim the significant improvement of proposed mechanism as compare to other schemes.
Multimedia Tools and Applications - The advancements of the Internet of Things (IoT) and voice-based multimedia applications have resulted in the generation of big data consisting of patterns,... 相似文献
This paper illustrates the performance of bit error rate based selection combining (BER-SC) protocol for adaptive cooperative cognitive radios. In the proposed framework, the unlicensed (i.e. secondary) system utilizes an adaptive mode of transmission to help the licensed (i.e. primary) system to achieve the desired quality of service in exchange for opportunistic spectrum access. The total transmission is divided in two phases. In Phase I, the primary transmitter (PT) broadcasts the data to the primary receiver (PR), which is overheard by the secondary transmitter (ST) and secondary receiver (SR). In Phase II, ST decodes the primary data and linearly combines its own data with the primary data. Using M-QAM the combined data is adaptively modulated, where M = 4, 16 or 64 depending on the received channel feedback, and relayed to PR and SR. At PR, BER-SC is employed to retrieve the primary data, and at SR interference cancellation is used to retrieve the secondary data. The analytical expressions are derived for the BER and the outage probability. The obtained results demonstrate the higher performance gains for both primary and secondary system by using adaptive mode of transmission at ST and BER-SC at PR.
The latest developments in mobile computing technology have increased the computing capabilities of smart mobile devices (SMDs). However, SMDs are still constrained by low bandwidth, processing potential, storage capacity, and battery lifetime. To overcome these problems, the rich resources and powerful computational cloud is tapped for enabling intensive applications on SMDs. In Mobile Cloud Computing (MCC), application processing services of computational clouds are leveraged for alleviating resource limitations in SMDs. The particular deficiency of distributed architecture and runtime partitioning of the elastic mobile application are the challenging aspects of current offloading models. To address these issues of traditional models for computational offloading in MCC, this paper proposes a novel distributed and elastic applications processing (DEAP) model for intensive applications in MCC. We present an analytical model to evaluate the proposed DEAP model, and test a prototype application in the real MCC environment to demonstrate the usefulness of DEAP model. Computational offloading using the DEAP model minimizes resources utilization on SMD in the distributed processing of intensive mobile applications. Evaluation indicates a reduction of 74.6% in the overhead of runtime application partitioning and a 66.6% reduction in the CPU utilization for the execution of the application on SMD.