Search results

Many strategies have been put forward for training deep network models, however, stacking of several layers of non-linearities typically results in poor propagation of gradients and activations. The purpose of this paper is to explore the use of two steps strategy where initial deep learning model is obtained first by unsupervised learning and then optimizing the initial deep learning model by fine tuning. A number of fine tuning algorithms are explored in this work for optimizing deep learning models. This includes proposing a new algorithm where Backpropagation with adaptive gain algorithm is integrated with Dropout technique and the authors evaluate its performance in the fine tuning of the pretrained deep network.

The parameters of deep neural networks are first learnt using greedy layer-wise unsupervised pretraining. The proposed technique is then used to perform supervised fine tuning of the deep neural network model. Extensive experimental study is performed to evaluate the performance of the proposed fine tuning technique on three benchmark data sets: USPS, Gisette and MNIST. The authors have tested the approach on varying size data sets which include randomly chosen training samples of size 20, 50, 70 and 100 percent from the original data set.

Through extensive experimental study, it is concluded that the two steps strategy and the proposed fine tuning technique significantly yield promising results in optimization of deep network models.

This paper proposes employing several algorithms for fine tuning of deep network model. A new approach that integrates adaptive gain Backpropagation (BP) algorithm with Dropout technique is proposed for fine tuning of deep networks. Evaluation and comparison of various algorithms proposed for fine tuning on three benchmark data sets is presented in the paper.

This study aims to construct a sentiment series generation method for danmu comments based on deep learning, and explore the features of sentiment series after clustering.

This study consisted of two main parts: danmu comment sentiment series generation and clustering. In the first part, the authors proposed a sentiment classification model based on BERT fine-tuning to quantify danmu comment sentiment polarity. To smooth the sentiment series, they used methods, such as comprehensive weights. In the second part, the shaped-based distance (SBD)-K-shape method was used to cluster the actual collected data.

The filtered sentiment series or curves of the microfilms on the Bilibili website could be divided into four major categories. There is an apparently stable time interval for the first three types of sentiment curves, while the fourth type of sentiment curve shows a clear trend of fluctuation in general. In addition, it was found that “disputed points” or “highlights” are likely to appear at the beginning and the climax of films, resulting in significant changes in the sentiment curves. The clustering results show a significant difference in user participation, with the second type prevailing over others.

Their sentiment classification model based on BERT fine-tuning outperformed the traditional sentiment lexicon method, which provides a reference for using deep learning as well as transfer learning for danmu comment sentiment analysis. The BERT fine-tuning–SBD-K-shape algorithm can weaken the effect of non-regular noise and temporal phase shift of danmu text.

This study aims to adopt a systematic review approach to examine the existing literature on law and LLMs.It involves analyzing and synthesizing relevant research papers, reports and scholarly articles that discuss the use of LLMs in the legal domain. The review encompasses various aspects, including an analysis of LLMs, legal natural language processing (NLP), model tuning techniques, data processing strategies and frameworks for addressing the challenges associated with legal question-and-answer (Q&A) systems. Additionally, the study explores potential applications and services that can benefit from the integration of LLMs in the field of intelligent justice.

This paper surveys the state-of-the-art research on law LLMs and their application in the field of intelligent justice. The study aims to identify the challenges associated with developing Q&A systems based on LLMs and explores potential directions for future research and development. The ultimate goal is to contribute to the advancement of intelligent justice by effectively leveraging LLMs.

To effectively apply a law LLM, systematic research on LLM, legal NLP and model adjustment technology is required.

This study contributes to the field of intelligent justice by providing a comprehensive review of the current state of research on law LLMs.

The purpose of this paper is to identify and understand challenges related to transition processes that occur between projects and the permanent organisation, as well as the outcome of such processes.

The study is based on an explorative, in‐depth case study of a multi‐project setting. The concept phase of three projects was followed by participative observations and ongoing interviews over a 15‐week period at two sites and in two countries. The empirical material was analyzed through a process‐oriented approach focusing on daily project activities.

Transition processes are characterized by containing operational complexities. These operational complexities demand project stakeholders to perform multiple translational and transformative activities. The outcomes from these activities are, for example, strategic, operational, and functional fine‐tuning, but also attitudinal turnaround.

This research is based on an interorganizational vehicle platform project setting. Therefore, the findings from this study cannot easily be generalized to other settings. However, it is likely that actors in other interorganizational project settings can benefit from the finding, since there probably are a multitude of transition processes in such projects as well.

Managers can learn that it is important to map all related transition processes, analyze the implications that these processes have on the project, and perform a dialog with project members so that the sense of operational complexity and uncertainty can be reduced. This type of action will reduce feelings of frustration and create a sense of readiness to deal with unexpected events.

The paper's value is two‐fold. First, the setting “an interorganizational vehicle platform” is largely under studied; and second, the paper pinpoints three unique transition processes and thereby contributes to the sparsely researched area of transition processes.

In this paper, we present a study about an automated system for monitoring underwater ecosystems. The system here proposed is based on the fusion of different deep learning methods. We study how to create an ensemble based of different Convolutional Neural Network (CNN) models, fine-tuned on several datasets with the aim of exploiting their diversity. The aim of our study is to experiment the possibility of fine-tuning CNNs for underwater imagery analysis, the opportunity of using different datasets for pre-training models, the possibility to design an ensemble using the same architecture with small variations in the training procedure.

Our experiments, performed on 5 well-known datasets (3 plankton and 2 coral datasets) show that the combination of such different CNN models in a heterogeneous ensemble grants a substantial performance improvement with respect to other state-of-the-art approaches in all the tested problems. One of the main contributions of this work is a wide experimental evaluation of famous CNN architectures to report the performance of both the single CNN and the ensemble of CNNs in different problems. Moreover, we show how to create an ensemble which improves the performance of the best single model. The MATLAB source code is freely link provided in title page.

Dunhuang murals are rich in cultural and artistic value. The purpose of this paper is to construct a novel mobile visual search (MVS) framework for Dunhuang murals, enabling users to efficiently search for similar, relevant and diversified images.

The convolutional neural network (CNN) model is fine-tuned in the data set of Dunhuang murals. Image features are extracted through the fine-tuned CNN model, and the similarities between different candidate images and the query image are calculated by the dot product. Then, the candidate images are sorted by similarity, and semantic labels are extracted from the most similar image. Ontology semantic distance (OSD) is proposed to match relevant images using semantic labels. Furthermore, the improved DivScore is introduced to diversify search results.

The results illustrate that the fine-tuned ResNet152 is the best choice to search for similar images at the visual feature level, and OSD is the effective method to search for the relevant images at the semantic level. After re-ranking based on DivScore, the diversification of search results is improved.

This study collects and builds the Dunhuang mural data set and proposes an effective MVS framework for Dunhuang murals to protect and inherit Dunhuang cultural heritage. Similar, relevant and diversified Dunhuang murals are searched to meet different demands.

This paper aims to realize an in-situ quality inspection system rapidly for new injection molding (IM) tasks via transfer learning (TL) approach and automation technology.

The proposed in-situ quality inspection system consists of an injection machine, USB camera, programmable logic controller and personal computer, interconnected via OPC or USB communication interfaces. This configuration enables seamless automation of the IM process, real-time quality inspection and automated decision-making. In addition, a MobileNet-based deep learning (DL) model is proposed for quality inspection of injection parts, fine-tuned using the TL approach.

Using the TL approach, the MobileNet-based DL model demonstrates exceptional performance, achieving validation accuracy of 99.1% with the utilization of merely 50 images per category. Its detection speed and accuracy surpass those of DenseNet121-based, VGG16-based, ResNet50-based and Xception-based convolutional neural networks. Further evaluation using a random data set of 120 images, as assessed through the confusion matrix, attests to an accuracy rate of 96.67%.

The proposed MobileNet-based DL model achieves higher accuracy with less resource consumption using the TL approach. It is integrated with automation technologies to build the in-situ quality inspection system of injection parts, which improves the cost-efficiency by facilitating the acquisition and labeling of task-specific images, enabling automatic defect detection and decision-making online, thus holding profound significance for the IM industry and its pursuit of enhanced quality inspection measures.

The purpose of this study is to develop a novel region-based convolutional neural networks (R-CNN) approach that is more efficient while at least as accurate as existing R-CNN methods. In this way, the proposed method, namely R²-CNN, provides a more powerful tool for pedestrian extraction for person re-identification, which involve a huge number of images and pedestrian needs to be extracted efficiently to meet the real-time requirement.

The proposed R²-CNN is tested on two types of data sets. The first one the USC Pedestrian Detection data set, which consists of three sub-sets USC-A, UCS-B and USC-C, with respect to their characteristics. This data set is used to test the performance of R²-CNN in the pedestrian extraction task. The speed and performance of the investigated algorithms were collected. The second data set is the PASCAL VOC 2007 data set, which is a common benchmark data set for object detection. This data set was used to analyze characteristics of R²-CNN in the case of general object detection task.

This study proposes a novel R-CNN method that is both more efficient and more accurate than existing methods. The method, when used as an object detector, would facilitate the data preprocessing stage of person re-identification.

The study proposes a novel approach for object detection, which shows advantages in both efficiency and accuracy for pedestrian detection task. It contributes to both data preprocessing for person re-identification and the research on deep learning.

The aim of the paper is the fine‐tuning of proportional integral derivative (PID) controllers under model parameter uncertainties (noise).

The fine‐tuning of PID controllers achieved using the Taguchi method following the steps given: selection of the control factors of the PID with their levels; identification of the noise factors that cause undesirable variation on the quality characteristic of PID; design of the matrix experiment and definition of the data analysis procedure; analysis of the data; decision regarding optimum settings of the control parameters and predictions of the performance at optimum levels of control factors; calculation of the expected cost savings under optimum condition; and confirmation of experimental results.

An example of the proposed method is presented and demonstrates that given certain performance criteria, the Taguchi method can indeed provide sub‐optimal values for fine PID tuning in the presence of model parameter uncertainties (noise). The contribution of each factor to the variation of the mean and the variability of error is also calculated. The expected cost savings for PID under optimum condition are calculated. The confirmation experiments are conducted on a real PID controller.

As a further research it is proposed the contiguous fine‐tuning of PID controllers under a number of a variant controllable models (noise).

The enhancement of PID controllers by Taguchi method is proposed with the form of a hardware mechanism. This mechanism will be incorporated in the PID controller and automatically regulate the PID parameters reducing the noise influence.

Application of Taguchi method in the scientific field of automation control.

The paper aims to address the tracking algorithm based on deep learning and four deep learning tracking models developed. They compared with each other to prevent collision and to obtain target tracking in autonomous aircraft.

First, to follow the visual target, the detection methods were used and then the tracking methods were examined. Here, four models (deep convolutional neural networks (DCNN), deep convolutional neural networks with fine-tuning (DCNNFN), transfer learning with deep convolutional neural network (TLDCNN) and fine-tuning deep convolutional neural network with transfer learning (FNDCNNTL)) were developed.

The training time of DCNN took 9 min 33 s, while the accuracy percentage was calculated as 84%. In DCNNFN, the training time of the network was calculated as 4 min 26 s and the accuracy percentage was 91%. The training of TLDCNN) took 34 min and 49 s and the accuracy percentage was calculated as 95%. With FNDCNNTL, the training time of the network was calculated as 34 min 33 s and the accuracy percentage was nearly 100%.

Compared to the results in the literature ranging from 89.4% to 95.6%, using FNDCNNTL, better results were found in the paper.