The rapid growth of AI systems, particularly large language models, has raised significant concerns about their environmental impact due to excessive energy consumption and carbon emissions. Despite these concerns, the trend in AI development continues to prioritize performance gains through increasingly resource-intensive approaches, such as utilizing more powerful hardware and larger datasets, often at the expense of efficiency. This study contributes to the efforts towards more efficient AI by proposing and empirically evaluating two dataset curation strategies, DS-1 and DS-2, which are linguistically-informed by syntactic features like Part-of-Speech (POS) tags to prune lexical content, for fine-tuning LLMs. The focus of this work is the empirical demonstration of how these linguistically-motivated curation approaches can create a balance between computational efficiency gains and performance maintenance during the LLM fine-tuning process. This approach represents a promising step in addressing the critical issue of AI's environmental impact. The evaluation is conducted on sentiment analysis tasks, serving as a focused case study. We evaluate two curation approaches, DS-1 and DS-2, applied to sentiment analysis tasks across three datasets, achieving substantial dataset size reductions while preserving essential linguistic information. Our assessment of six state-of-the-art LLMs—RoBERTa, ALBERT, ERNIE, DeBERTa, BERT, and GPT-2—on both curated and original datasets reveals that curated datasets can yield comparable performance to uncurated ones, with efficiency gains of up to 70% in tokenization time and up to 80% in training energy. Notably, the study uncovers varying resilience of different model architectures to curation, with the GPT-based model demonstrating perfect performance adaptation, while other advanced models like ERNIE and DeBERTa also showed strong resilience. This research is crucial in promoting the development of more sustainable and resource-efficient NLP systems, challenging the prevailing notion that larger datasets invariably lead to better performance in fine-tuning LLMs, and paving the way for more environmentally conscious AI development practices. The generalizability of these specific curation strategies to other NLP tasks is an avenue for future investigation.

The rapid growth of the Internet of Things (IoT) devices is paralleled by them being on the front-line of malicious attacks. This has led to an explosion in the number of IoT malware, with continued mutations, evolution, and sophistication. Malware samples are detected using machine learning (ML) algorithms alongside the traditional signature-based methods. Although ML-based detectors improve the detection performance, they are susceptible to malware evolution and sophistication, making them limited to the patterns that they have been trained upon. This continuous trend motivates large body of literature on malware analysis and detection research, with many systems emerging constantly, outperforming their predecessors. In this paper, we systematically examine the state-of-the-art malware detection approaches, that utilize various representation and learning techniques, under a range of adversarial settings. Our analyses highlight the instability of the proposed detectors in learning patterns that distinguish the benign from the malicious software. The results exhibit that software mutations with functionality-preserving operations, such as stripping and padding, significantly deteriorate the accuracy of such detectors. Additionally, our analysis of the industry-standard malware detectors shows their instability to the malware mutations. Through extensive experiments, we highlight the gap between the capabilities of the adversary and that of the existing malware detectors. The evaluations and analyses show that the optimal malware detection system is nowhere near and calls for the community to streamline their efforts towards testing the robustness of malware detectors to different manipulation techniques.

Abstract Lung cancer is one of the most profound causes of cancer‐related deaths in the world. Early detection is known to significantly improve the chances of survival. Several detection and diagnostic methods are used for this purpose. CT is one of the most widely used non‐invasive medical imaging modalities in this domain. The biggest challenge faced by radiologists in this case is detection and diagnosis of cancerous lung nodules. The growth of ground glass opacity (GGO) lesions is an indication of malignancy. However, GGO is difficult to capture for physicians as it manifests in the form of tiny, faint shadows. This research paper proposes an approach for aiding GGO identification in CT lung images for improved lung cancer prognosis. In the proposed approach, morphological reconstruction is used for segmentation. Once the region of interest (ROI) is extracted, statistical analysis using mean, standard deviation, variance, entropy, skewness, kurtosis, minimum grey scale value, maximum grey scale value and range is performed. The same statistical measures are determined for normal lung and distribution plot is drawn for comparison. It is observed that maximum grey‐scale value demonstrates minimum overlap of approximately 7.4%. To reduce this, a joint feature by summing values of feature mean, skewness, and maximum grey‐scale value was used. This approach reduced the overlap to approximately 1.32%. Lastly, ANN was used for classification of GGO and non‐GGO lung tissue with an achieved accuracy of 99.5%.

Solid waste management (SWM) is a key administrative unit for managing the urban waste to deliver an eco-friendly environment to the citizens residing in urban cities. Generally, many technologies are implemented and developed by researchers for enhancing the mechanism of SWM and minimizing the waste generation. Yet, the management of waste generation is still a concern. So, here, there is requirement of technology that can involve the individuals for achieving the target reducing the waste. At present, the blockchain technology is an appropriate technology for SWM, as it provides the applications of time tracing activities, secure data transactions, and automatic reward system. In this study, a blockchain-based reward system is proposed to generate the rewards based on real-time series data such as quantity of garbage and level of waste. Furthermore, LoRa-range-based customized sensors are developed for bins to obtain real time information. Moreover, the generated information further transferred to cloud by utilizing LoRa wireless enabled gateway. By the use of flask server, a technique is proposed for integrating real-time data with blockchain via a local network application programming interface (API). A real-time implementation is evaluated on the data to the check the performance efficiency of the proposed approach, where the procedure of automatic reward system is presented in detail.

Ultra-reliable low-latency communication (uRLLC) and enhanced mobile broadband (eMBB) are two influential services of the emerging 5G cellular network. Latency and reliability are major concerns for uRLLC applications, whereas eMBB services claim for the maximum data rates. Owing to the trade-off among latency, reliability and spectral efficiency, sharing of radio resources between eMBB and uRLLC services, heads to a challenging scheduling dilemma. In this paper, we study the co-scheduling problem of eMBB and uRLLC traffic based upon the puncturing technique. Precisely, we formulate an optimization problem aiming to maximize the minimum expected achieved rate (MEAR) of eMBB user equipment (UE) while fulfilling the provisions of the uRLLC traffic. We decompose the original problem into two sub-problems, namely scheduling problem of eMBB UEs and uRLLC UEs while prevailing objective unchanged. Radio resources are scheduled among the eMBB UEs on a time slot basis, whereas it is handled for uRLLC UEs on a mini-slot basis. Moreover, for resolving the scheduling issue of eMBB UEs, we use penalty successive upper bound minimization (PSUM) based algorithm, whereas the optimal transportation model (TM) is adopted for solving the same problem of uRLLC UEs. Furthermore, a heuristic algorithm is also provided to solve the first sub-problem with lower complexity. Finally, the significance of the proposed approach over other baseline approaches is established through numerical analysis in terms of the MEAR and fairness scores of the eMBB UEs.

Volunteer computing based data processing is a new trend in healthcare applications. Researchers are now leveraging volunteer computing power to train deep learning networks consisting of billions of parameters. Breast cancer is the second most common cause of death in women among cancers. The early detection of cancer may diminish the death risk of patients. Since the diagnosis of breast cancer manually takes lengthy time and there is a scarcity of detection systems, development of an automatic diagnosis system is needed for early detection of cancer. Machine learning models are now widely used for cancer detection and prediction research for improving the successive therapy of patients. Considering this need, this study implements pre-trained convolutional neural network based models for detecting breast cancer using ultrasound images. In particular, we tuned the pre-trained models for extracting key features from ultrasound images and included a classifier on the top layer. We measured accuracy of seven popular state-of-the-art pre-trained models using different optimizers and hyper-parameters through fivefold cross validation. Moreover, we consider Grad-CAM and occlusion mapping techniques to examine how well the models extract key features from the ultrasound images to detect cancers. We observe that after fine tuning, DenseNet201 and ResNet50 show 100% accuracy with Adam and RMSprop optimizers. VGG16 shows 100% accuracy using the Stochastic Gradient Descent optimizer. We also develop a custom convolutional neural network model with a smaller number of layers compared to large layers in the pre-trained models. The model also shows 100% accuracy using the Adam optimizer in classifying healthy and breast cancer patients. It is our belief that the model will assist healthcare experts with improved and faster patient screening and pave a way to further breast cancer research.

Current research in Internet of Things (IoT) is focused on the security enhancements to every communicated message in the network. Keeping this thought in mind, researcher in this work emphasizes on a security oriented cryptographic solution. Commonly used security cryptographic solutions are heavy in nature considering their key size, operations, and mechanism they follow to secure a message. This work first determines the benefit of applying lightweight security cryptographic solutions in IoT. The existing lightweight counterparts are still vulnerable to attacks and also consume calculative more power. Therefore, this research work proposes a new hybrid lightweight logical security framework for offering security in IoT (LLSFIoT). The operations, key size, and mechanism used in the proposed framework make its lightweight. The proposed framework is divided into three phases: registration, authentication, and light data security (LDS). LDS offers security by using unique keys at each round bearing small size. Key generation mechanism used is comparatively fast making the compromise of keys as a difficult task. These steps followed in the proposed algorithm design make it lightweight and a better solution for IoT‐based networks as compared to the existing solutions that are relatively heavy weight in nature.

xCalamities such as earthquakes and tsunami affect communication services by devastating the communication network and electrical infrastructure. Multihop relay networks can be deployed to restore the communication environment quickly in catastrophe‐stricken areas. However, performance in terms of throughput is affected by deploying the relay networks. In wireless local area networks (WLANs), the primary purpose of multiband transmission employing multihop relay networks is to increase the throughput and reduce the latency. In the future, wireless networks are believed to carry high throughput, more data rates, and less latency by expanding bandwidth‐demanding applications. Simultaneous multiband transmission in WLAN systems is considered to increase the coverage area without power escalation. Due to the inherent characteristics of different bands and channel conditions, transmission rates tend to be different. The impact of such conditions may cater to the disproportional distribution of data among bands, causing some of the bands to be overwhelmed, which incurs buffer overflow and packet loss. In contrast, the channel capacity of some of the bands remains underutilized. In this paper, we consider the channel conditions and transmission rates of each band on either side of the relay to address the problems mentioned above. Furthermore, this paper proposes a load distribution‐based end‐to‐end traffic scheduling technique to improve system performance. The simulation results demonstrate the effectiveness of our proposed method with maximizing throughput and minimizing end‐to‐end delay.

Achievement of precision measurement is highly desired in a current industrial revolution where a significant increase in living standards increased municipal solid waste. The current industry 4.0 standards require accurate and efficient edge computing sensors towards solid waste classification. Thus, if waste is not managed properly, it would bring about an adverse impact on health, the economy, and the global environment. All stakeholders need to realize their roles and responsibilities for solid waste generation and recycling. To ensure recycling can be successful, the waste should be correctly and efficiently separated. The performance of edge computing devices is directly proportional to computational complexity in the context of nonorganic waste classification. Existing research on waste classification was done using CNN architecture, e.g., AlexNet, which contains about 62,378,344 parameters, and over 729 million floating operations (FLOPs) are required to classify a single image. As a result, it is too heavy and not suitable for computing applications that require inexpensive computational complexities. This research proposes an enhanced lightweight deep learning model for solid waste classification developed using MobileNetV2, efficient for lightweight applications including edge computing devices and other mobile applications. The proposed model outperforms the existing similar models achieving an accuracy of 82.48% and 83.46% with Softmax and support vector machine (SVM) classifiers, respectively. Although MobileNetV2 may provide a lower accuracy if compared to CNN architecture which is larger and heavier, the accuracy is still comparable, and it is more practical for edge computing devices and mobile applications.

Social media platforms have been growing at a rapid pace, attracting users engagement with contents due to their convenience facilitated by many usable features. Such platforms provide users with interactive options such as likes, dislikes as well as a way of expressing their opinions in the form of text (i.e., comments). The ability of posting comments on these online platforms has allowed some users to post racist, obscene, as well as to spread hate on these platforms. In some cases, this kind of toxic behavior might turn the comment section from a space where users can share their views to a place where hate and profanity are spread. Such issues are observed across various social media platforms and many users are often exposed to these kinds of behaviors which requires comment moderators to spend a lot of time filtering out such inappropriate comments. Moreover, such textual "inappropriate contents" can be targeted towards users irrespective of age, concerning variety of topics (not only controversial), and triggered by various events. My doctoral dissertation work, therefore, is primarily focused on studying, detecting and analyzing users exposure to this kind of toxicity on different social media platforms utilizing the state-of-art techniques in deep learning and natural language processing. This paper presents one example of my works on detecting and measuring kids exposure to inappropriate comments posted on YouTube videos targeting young users. In the meantime, the same pipeline is being examined for measuring users interaction with mainstream news media and sentiment towards various topics in the public discourse in light of the Coronavirus disease 2019 (COVID'19).

The Internet has become an essential part of children’s and adolescents’ daily life. Social media platforms are used as educational and entertainment resources on daily bases by young users, leading enormous efforts to ensure their safety when interacting with various social media platforms. In this paper, we investigate the exposure of those users to inappropriate and malicious content in comments posted on YouTube videos targeting this demographic. We collected a large-scale dataset of approximately four million records, and studied the presence of malicious and inappropriate URLs embedded in the comments posted on these videos. Our results show a worrisome number of malicious and inappropriate URLs embedded in comments available for children and young users. In particular, we observe an alarming number of inappropriate and malicious URLs, with a high chance of kids exposure, since the average number of views on videos containing such URLs is 48 million. When using such platforms, children are not only exposed to the material available in the platform, but also to the content of the URLs embedded within the comments. This highlights the importance of monitoring the URLs provided within the comments, limiting the children’s exposure to inappropriate content.

Malaria is a contagious disease that affects millions of lives every year. Traditional diagnosis of malaria in laboratory requires an experienced person and careful inspection to discriminate healthy and infected red blood cells (RBCs). It is also very time-consuming and may produce inaccurate reports due to human errors. Cognitive computing and deep learning algorithms simulate human intelligence to make better human decisions in applications like sentiment analysis, speech recognition, face detection, disease detection, and prediction. Due to the advancement of cognitive computing and machine learning techniques, they are now widely used to detect and predict early disease symptoms in healthcare field. With the early prediction results, healthcare professionals can provide better decisions for patient diagnosis and treatment. Machine learning algorithms also aid the humans to process huge and complex medical datasets and then analyze them into clinical insights. This paper looks for leveraging deep learning algorithms for detecting a deadly disease, malaria, for mobile healthcare solution of patients building an effective mobile system. The objective of this paper is to show how deep learning architecture such as convolutional neural network (CNN) which can be useful in real-time malaria detection effectively and accurately from input images and to reduce manual labor with a mobile application. To this end, we evaluate the performance of a custom CNN model using a cyclical stochastic gradient descent (SGD) optimizer with an automatic learning rate finder and obtain an accuracy of 97.30% in classifying healthy and infected cell images with a high degree of precision and sensitivity. This outcome of the paper will facilitate microscopy diagnosis of malaria to a mobile application so that reliability of the treatment and lack of medical expertise can be solved.

The emergence of cognitive computing and big data analytics revolutionize the healthcare domain, more specifically in detecting cancer. Lung cancer is one of the major reasons for death worldwide. The pulmonary nodules in the lung can be cancerous after development. Early detection of the pulmonary nodules can lead to early treatment and a significant reduction of death. In this paper, we proposed an end-to-end convolutional neural network- (CNN-) based automatic pulmonary nodule detection and classification system. The proposed CNN architecture has only four convolutional layers and is, therefore, light in nature. Each convolutional layer consists of two consecutive convolutional blocks, a connector convolutional block, nonlinear activation functions after each block, and a pooling block. The experiments are carried out using the Lung Image Database Consortium (LIDC) database. From the LIDC database, 1279 sample images are selected of which 569 are noncancerous, 278 are benign, and the rest are malignant. The proposed system achieved 97.9% accuracy. Compared to other famous CNN architecture, the proposed architecture has much lesser flops and parameters and is thereby suitable for real-time medical image analysis.