Image restoration is a fundamental task in computer vision, yet restoring outdoor scenes under multiple adverse weather conditions remains challenging due to heterogeneous and spatially coupled degradations that jointly affect visibility and scene consistency. Existing all-in-one restoration frameworks have achieved remarkable progress; however, unified architectures often entangle weather-specific cues, thereby hindering discriminative representation learning and interpretability. Motivated by the observation that different weather degradations often affect common scene structures (e.g., object boundaries and global illumination) while introducing distinct degradation cues such as contrast attenuation in haze, streak artifacts in rain, and particle occlusion in snow, we propose CWE-Net, an adaptive and unified framework that integrates weather-aware expert routing with cross-condition generalization, enabling the model to adapt across single, compound, and spatially mixed weather conditions. CWE-Net employs a lightweight multi-label router for explicit degradation perception, which dynamically activates three Base Weather Experts (BWEs) corresponding to haze, rain, and snow. Their outputs are refined through a Cross-Weather Expert (CWE) module that performs learned convolutional fusion and refinement guided by coordinate attention, enabling coherent reconstruction under compound and spatially inconsistent degradations. The network is optimized using a composite loss with lightweight adaptive weighting of structural, perceptual, and edge-level fidelity. Extensive evaluations on synthetic and real-world benchmarks demonstrate that CWE-Net achieves competitive performance, strong generalization, and clear interpretability, offering an effective and scalable framework for all-weather image restoration.

Cybersecurity poses a growing threat to technology infrastructure, especially raising concerns for automobile technology. Modern vehicles, reliant on connectivity, face a critical challenge in safeguarding their in-vehicle networks from cyber-attacks. Although the Controller Area Network is a standard for in-vehicle networks, its lack of security features exposes vehicles to vulnerabilities. Especially, the use of AI for offensive purposes further intensifies the threat to automotive technology infrastructure to protect it from cyber-attacks. This study proposes an approach to enhance in-vehicle network security, employing machine learning algorithms to protect against both AI-based generated attacks and traditional attacks. The Conditional Tabular Generative Adversarial Network (CTGAN) is utilized to generate in-vehicle network traffic, which is then combined with benchmark in-vehicle network traffic to create a complex and diverse scenario. The Random Forest model achieved a significant accuracy score for both benchmark in-vehicle network traffic and AI-based traffic, with scores of 0.93 and 0.89, respectively.

Abstract Efficient word representation techniques (word embeddings) with modern machine learning models have shown reasonable improvement on automatic text classification tasks. However, the effectiveness of such techniques has not been evaluated yet in terms of insufficient word vector representation for training. Convolutional Neural Network has achieved significant results in pattern recognition, image analysis, and text classification. This study investigates the application of the CNN model on text classification problems by experimentation and analysis. We trained our classification model with a prominent word embedding generation model, Fast Text on publically available datasets, six benchmark datasets including Ag News, Amazon Full and Polarity, Yahoo Question Answer, Yelp Full, and Polarity. Furthermore, the proposed model has been tested on the Twitter US airlines non-benchmark dataset as well. The analysis indicates that using Fast Text as word embedding is a very promising approach.

Abstract With the multitude of companies that flourish today, job seekers want to join companies with highly satisfied employees. So, job satisfaction prediction is an important task that helps companies in sustaining or redesigning employee policies. Such predictions not only help in reducing employee attrition but also affect the goodwill and reputation of a company. The higher satisfaction level of current employees attracts potential new employees and confirms the positive policies of a company toward its employees. Job satisfaction prediction can be performed using employee reviews either manually or via automated machine learning algorithms. This study first evaluates four widely used machine learning algorithms, that is, random forest, logistic regression, support vector classifier, and gradient boosting, and then proposes a deep learning model to predict employee job satisfaction level. Experiments are carried out on a dataset that contains text reviews from the employees of Google, Facebook, Amazon, Microsoft, and Apple. Three feature extraction methods are analyzed as well including term frequency‐inverse document frequency (TF‐IDF), bag‐of‐words (BOW), and global vector for word representation (GloVe). Performance is evaluated using accuracy, precision, recall, F1 score, as well as, macro average precision, and weighted average. The performance of the proposed model is compared with state‐of‐the‐art deep learning models. Results demonstrate that the proposed model performs better than both the machine learning and state‐of‐the‐art approaches.

Abstract Sentiment analysis focuses on identifying and classifying the sentiments expressed in text messages and reviews. Social networks like Twitter, Facebook, and Instagram generate heaps of data filled with sentiments, and the analysis of such data is very fruitful when trying to improve the quality of both products and services alike. Classic machine learning techniques have a limited capability to efficiently analyze such large amounts of data and produce precise results; they are thus supported by deep learning models to achieve higher accuracy. This study proposes a combination of convolutional neural network and long short‐term memory (CNN‐LSTM) deep network for performing sentiment analysis on Twitter datasets. The performance of the proposed model is analyzed with machine learning classifiers, including the support vector classifier, random forest (RF), stochastic gradient descent (SGD), logistic regression, a voting classifier (VC) of RF and SGD, and state‐of‐the‐art classifier models. Furthermore, two feature extraction methods (term frequency‐inverse document frequency and word2vec) are also investigated to determine their impact on prediction accuracy. Three datasets (US airline sentiments, women's e‐commerce clothing reviews, and hate speech) are utilized to evaluate the performance of the proposed model. Experiment results demonstrate that the CNN‐LSTM achieves higher accuracy than those of other classifiers.

Camera calibration technique plays a vital role in three dimensional computer vision systems. The aim of this technique is to calibrate the camera in order to collect more precise three dimensional data from the images to utilize for robot navigation, three dimensional reconstruction, biomedical, virtual reality and visual surveillance. In camera calibration one of the major issue is to search out the set of image parameters describing the mapping between three dimensional images reference coordinates and two-dimensional images reference coordinates. Currently, MATLAB toolbox and OpenCv are the most popular tools used by the researchers for camera calibration. We utilize the concept of deep learning to recognize the chessboard corners. Our presented technique is a convolutional neural network (CNN) trained on a huge number of chessboard images. The network is trained on different datasets: noisy and with high lens malformation images. The proposed scheme is more accurate than the conventional MATLAB algorithm technique. The presented technique is more accurate against the different sort of ruination present in the training set. Results reaffirmed the correctness and effectiveness of our proposed CNN technique.

in recent time rapid and extraordinary technological advancement is dominated by the social internet of things (SIoT). SIoT connects people together socially and opens doors to people, to share ideas by using this information. Typically, SIoT deals with the massive amount of data and information. This data is used by various online social networks (ONS), i.e. Twitter, LinkedIn and Facebook etc. analyzing and mining of useful extracted information from these social networks is not an easy task. SIoT has a special interest in numerous research fields, i.e. computer sciences and social sciences. The detection and mining of a community reveal how the structure affects the people and their relationships. In order to facilitate the community discovery, a wide range of tools has been developed over years. Each of them differs from other, in respect of features and benefits. Choosing the right tool is somehow a difficult task. In order to overcome this difficulty, our work offers an analysis by dividing them into various categories such as network platform, algorithm complexity, community detection and their execution time. Finally, we discussed various visualization layouts of social networks which are helpful in order to precise the network data.

Phase change memory (PCM) is non-volatile memory that is byte-addressable. It is two to four times denser than DRAM, orders of magnitude better than NAND Flash memory in read latency, and 10 times better than NAND Flash memory in write endurance. However, it still limits the number of write operations to at most 106 times per PCM cell. To extend its lifetime, it is necessary to evenly distribute write operations over all the memory cells. Up to now, the B+-Tree index structure has been used to quickly locate a search key in a relational database management system (RDBMS). All the record keys in each node are sorted and packed upon insertion in, and deletion from, the B+-Tree. In addition, a counter keeps track of the number of valid keys in the B+-Tree. Consequently, a B+-Tree algorithm results in a large number of write operations, which deteriorates the endurance of PCM. This restricts the usage of PCM on a database server and deteriorates performance of database servers. In this paper, we propose a novel PCM-aware B+-Tree index structure, called PB+-Tree, to provide wear-leveling in PCM. According to our experiment results, PB+-Tree is much faster than the existing B+-Tree algorithms for PCM and NAND Flash memory with versatile workloads. More importantly, our scheme also greatly reduces the number of write operations compared to other B+-Tree algorithms. All of these results suggest that PB+-Tree is the B+-Tree algorithm best fitted to PCM.

An optimum power and rate allocation rule for cellular code division multiple access (CDMA) downlink networks is derived; it minimises mean transmission delay of the active users with different channel qualities under the constraints of total transmission power and the required signal-to-interference ratio. The proposed rule states that the power assigned to a user is inversely proportional to the square root of the user's channel quality factor, whereas the rate assigned to a user is proportional to the square root of the user's channel quality factor. The amount of reduction in average mean transmission delay by the proposed optimum allocation rule against the equal rate allocation with power control and the equal power allocation with rate control is also derived for the case when each user undergoes shadowing, path loss and inter-cell interference. It is shown that the proposed allocation rule not only achieves the minimum mean transmission delay, but also minimises the probability of the data rate being less than a tolerable threshold, against the equal rate or equal power allocation schemes.

State-of-the-art cluster-based data centers consisting of three tiers (Web server, application server, and database server) are being used to host complex Web services such as e-commerce applications. The application server handles dynamic and sensitive Web contents that need protection from eavesdropping, tampering, and forgery. Although the secure sockets layer (SSL) is the most popular protocol to provide a secure channel between a client and a cluster-based network server, its high overhead degrades the server performance considerably and, thus, affects the server scalability. Therefore, improving the performance of SSL-enabled network servers is critical for designing scalable and high-performance data centers. In this paper, we examine the impact of SSL offering and SSL-session-aware distribution in cluster-based network servers. We propose a back-end forwarding scheme, called ssl_with_bf, that employs a low-overhead user-level communication mechanism like virtual interface architecture (VIA) to achieve a good load balance among server nodes. We compare three distribution models for network servers, round robin (RR), ssl_with_session, and ssl_with_bf, through simulation. The experimental results with 16-node and 32-node cluster configurations show that, although the session reuse of ssl_with_session is critical to improve the performance of application servers, the proposed back-end forwarding scheme can further enhance the performance due to better load balancing. The ssl_with_bf scheme can minimize the average latency by about 40 percent and improve throughput across a variety of workloads.

Improving the performance of Web servers has become a critical issue to handle the increasing demand on various network-based services. In this context, we exploit the local memory of programmable network interface cards (NICs) to improve the performance of cluster-based Web servers, which are increasingly used in designing Web server platforms. We use the NIC memory for caching recently accessed data blocks to improve server performance. We have implemented a prototype of the proposed NIC caching mechanism for a distributed Web server, based on PRESS (Carrera et al., 2002), on an 8-node, Myrinet-connected Linux cluster. Measurements with several server workloads show that NIC caching can enhance throughput by up to 27% compared to the original PRESS Web server without NIC caching, by minimizing the DMA and PCI bus overhead

Although the secure sockets layer (SSL) is the most popular protocol to provide a secure channel between a client and a cluster-based network server, its high overhead degrades the server performance considerably, and thus, affects the server scalability. Therefore, improving the performance of SSL-enabled network servers is critical for designing scalable and high performance data centers. In this paper, we examine the impact of SSL offering and SSL-session aware distribution in cluster-based network servers. We propose a backend forwarding scheme, called ssl_with_bf that employs a low-overhead user-level communication mechanism like VIA to achieve good load balance among server nodes. We compare three distribution models for network servers: round robin (RR), ssl_with_session and ssl_with_bf through simulation. The experimental results with 16-node and 32-node cluster configurations show that while session reuse of ss_with_session is critical to improve the performance of application servers, the proposed backend forwarding scheme can further enhance the performance due to better load balancing. The ssl_with_bf scheme can minimize average latency by about 40% and improve throughput across a variety of workloads

In this paper, we have investigated the performance implications of SSL protocol for providing secure service in a cluster-based application server, and have proposed a backend forwarding scheme for improving server performance through better load balance. The proposed SSL/spl I.bar/with/spl I.bar/bf scheme exploits the underlying user-level communication minimizing the intra-cluster communication overhead. All results in this paper indicate that the proposed backend forwarding scheme is a viable mechanism for improving the performance of application servers in cluster-based data centers.

Design of high performance Web servers has become a recent research thrust to meet the increasing demand of network-based services. In this paper, we propose a new Web server architecture, called multi-threaded PIPELINED Web server, suitable for Symmetric Multi-Processor (SMP) or System-on-Chip (SoC) architectures. The proposed PIPELINED model consists of multiple thread pools, where each thread pool consists of five basic threads and two helper threads. The main advantages of the proposed model are global information sharing by the threads, minimal synchronization overhead due to less number of threads, and non-blocking I/O operations, possible with the helper threads.We have conducted an in-depth performance analysis of the proposed server model along with four prior Web server models (Multi-Process (MP), Multi-Thread (MT), Single-Process Event-Driven (SPED) and Asynchronous Multi-Process Event-Driven (AMPED)) via simulation using six Web server workloads. The experiments are conducted to investigate the impact of various factors such as the memory size, disk speed and numbers of clients. The simulation results indicate that the proposed PIPELINED Web server architecture shows the best performance across all system and workload parameters compared to the MP, MT, SPED and AMPED models. Although the MT and AMPED models show competitive performance with less number of processors, the advantage of the PIPELINED model becomes obvious as the number of processors or clients in an SMP/SoC machine increases. The MP model shows the worst performance in most of the cases. The results indicate that the proposed server architecture can be used in future large-scale SMP/SoC machines to boost system performance.

Summary form only given. We investigate the feasibility of minimizing the response time of a Web server by exploiting the advantages of both user-level communication and coscheduling. We, thus, propose a coscheduled server model, based on the PRESS design where the remote cache accesses can be coscheduled on different nodes to reduce the response time. We experiment this concept using two known coscheduling techniques, called dynamic coscheduling (DCS) and DCS with immediate blocking. Extensive simulation of four server models (PRESS over TCP/IP, PRESS over VIA, coscheduled PRESS model with DCS, and with DCS and blocking) using 16-node and 32-node cluster configurations indicates that the average response time of a distributed server can be minimized significantly by coscheduling the communicating processes. The use of the DCS scheme reduced the average latency up to 80%, on an average 40%, compared to the PRESS over VIA model that uses only user-level communication, and by order of magnitude compared to the TCP/IP model. The throughput of the three user-level communication models is at least 25% better compared to the PRESS over TCP/IP model. Experiments with varying file size and cache size also confirmed the advantage of using a coscheduling mechanism for improving the response time behavior.

In this paper, we conduct an in-depth evaluation of a broad spectrum of scheduling alternatives for clusters. These include the widely used batch scheduling, local scheduling, gang scheduling, all prior communication-driven coscheduling algorithms (Dynamic Coscheduling (DCS), Spin Block (SB), Periodic Boost (PB), and Co-ordinated Coscheduling (CC)) and a newly proposed HYBRID coscheduling algorithm on a 16-node, Myrinet-connected Linux cluster. Performance and energy measurements using several NAS, LLNL and ANL benchmarks on the Linux cluster provide several interesting conclusions. First, although batch scheduling is currently used in most clusters, all blocking-based coscheduling techniques such as SB, CC and HYBRID and the gang scheduling can provide much better performance even in a dedicated cluster platform. Second, in contrast to some of the prior studies, we observe that blocking-based schemes like SB and HYBRID can provide better performance than spin-based techniques like PB on a Linux platform. Third, the proposed HYBRID scheduling provides the best performance-energy behavior and can be implemented on any cluster with little effort. All these results suggest that blocking-based coscheduling techniques are viable candidates to be used in clusters for significant performance-energy benefits.

In this paper, we attempt to address several key issues in designing coscheduling algorithms for clusters. First, we propose a generic framework for deploying coscheduling techniques by providing a reusable and dynamically loadable kernel module. Second, we implement all prior dynamic coscheduling algorithms (dynamic coscheduling (DCS), spin block (SB) and periodic boost (PB)) and a new coscheduling technique, called co-ordinated coscheduling (CC), using the above framework. Third, with exhaustive experimentation using mixed workloads, we observe that unlike PB, which provided the best performance on a Solaris platform (followed by SB and DCS), the proposed CC scheme outperforms all other techniques on a Linux platform, followed by SB, PB and DCS, in that order. Finally, we argue that due to its modular design, portable implementation on a standard platform, high performance and tolerance to workload mixes, the proposed CC scheme can be a viable scheduling option for time-sharing clusters.